[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2020135510A1 - Burst load prediction method and device, storage medium and electronic device - Google Patents

Burst load prediction method and device, storage medium and electronic device Download PDF

Info

Publication number
WO2020135510A1
WO2020135510A1 PCT/CN2019/128337 CN2019128337W WO2020135510A1 WO 2020135510 A1 WO2020135510 A1 WO 2020135510A1 CN 2019128337 W CN2019128337 W CN 2019128337W WO 2020135510 A1 WO2020135510 A1 WO 2020135510A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
load
burst
congestion
burst load
Prior art date
Application number
PCT/CN2019/128337
Other languages
French (fr)
Chinese (zh)
Inventor
孟晟
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2020135510A1 publication Critical patent/WO2020135510A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/147Network analysis or design for predicting network behaviour
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/06Testing, supervising or monitoring using simulated traffic
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks
    • Y02D30/70Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • This disclosure relates to, but is not limited to, the field of communications.
  • Service networks usually have limited resources, and there are usually several situations where the load of an access node or the entire network approaches or even reaches the upper limit.
  • Short-term to long-term load forecasting with granularity above hour is generally based on time series models.
  • the sudden load surge is usually mainly determined by the random behavior of network users, and is only related to the time period close to the time of occurrence. The congestion caused by this is an open problem.
  • a cellular communication network when the cell load exceeds a certain level, the service performance of users in the cell will be reduced (such as delays and stalls). In severe cases, congestion will cause the basic index of the system to deteriorate sharply, so that user services cannot proceed normally. Especially in scenarios with high user density, such as sports games, concerts, and large-scale gatherings, how to relieve or even avoid real-time congestion is a pain point for operators and users.
  • a method for predicting a sudden load including: collecting load index data of a specified area, wherein the load index data is used to characterize the load of the specified area; and The load generation model analyzes the load index data to predict the occurrence of sudden load, wherein the sudden load model is trained by machine learning using multiple sets of data.
  • a device for predicting a sudden load including: a collection module for collecting load index data of a specified area, wherein the load index data is used to characterize the load of the specified area Situation; and a prediction module for analyzing the load index data using a burst load model to predict the occurrence of the burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
  • a storage medium in which a computer program is stored, wherein, when the computer program is executed by a processor, the processor executes the burst load according to the present disclosure method of prediction.
  • an electronic device including a memory and a processor, the memory stores a computer program, and when the processor runs the computer program, the burst according to the present disclosure is executed Load forecasting method.
  • FIG. 1 is a flowchart of a method for predicting burst load according to an embodiment of the present disclosure
  • FIG. 2 is a structural block diagram of a burst load prediction device according to an embodiment of the present disclosure
  • FIG. 3 is another structural block diagram of a burst load prediction device according to an embodiment of the present disclosure.
  • FIG. 4 is a structural block diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 5 is a system block diagram according to an embodiment of the present disclosure.
  • FIG. 9 is a schematic diagram of screening equivalent evaluation index services according to an embodiment of the present disclosure.
  • FIG. 10 is a decision tree method for real-time congestion automatic labeling according to an embodiment of the present disclosure.
  • FIG. 1 is a flowchart of a method for predicting a burst load according to an embodiment of the present disclosure. As shown in FIG. 1, the method for burst load according to an embodiment of the present disclosure The prediction method includes steps S102 to S104.
  • step S102 load index data of a specified area is collected, wherein the load index data is used to characterize the load condition of the specified area.
  • step S104 the load index data is analyzed using a burst load model to predict the occurrence of burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
  • the load index data of the specified area where the load index data is used to characterize the load of the specified area; use the burst load model to analyze the load index data to predict the occurrence of sudden load
  • the burst load model is trained by machine learning using multiple sets of data.
  • the occurrence of the sudden load may refer to the time of occurrence of the sudden load, the duration of the occurrence of the sudden load, etc. and the technical solutions related to the sudden load.
  • the method before the step of analyzing the load index data using the burst load model, the method further includes: selecting a burst load model suitable for the designated area from a plurality of burst load models .
  • the method before the step of selecting a burst load model suitable for the specified area from a plurality of burst load models, the method further includes: acquiring historical data collected at the base station; Pre-processing is performed to obtain the entire region cell data set; from the entire region cell data set, a congestion data set is selected according to a specified rule; and the congestion data set is annotated to obtain a plurality of the burst load models.
  • the historical data includes at least one of the following: load indicator data, network key performance indicator data, key service quality indicator data, and user behavior indicator data.
  • the entire area cell data set includes: independent variable data and dependent variable data
  • the entire area cell data set is obtained at least in the following manner: obtaining independent variable data and dependent variable data that satisfy preset conditions ,
  • the independent variable data includes: load type data
  • the dependent variable data and the independent variable data have a specified functional relationship.
  • the step of selecting the congestion data set from the entire cell data set of the area according to a specified rule includes: analyzing the dependent variable data and the independent variable data according to the comparison detection method; comparing the number of comparison detections Dependent variable data satisfying a preset number of times is used as congestion indicator data; and n independent variable indicator data whose association degree with the congestion indicator data satisfies a preset value is used as the congestion data set, where n is a positive integer .
  • the above-mentioned congestion data set can be obtained by: determining independent variables (load-type indicators) and dependent variables (perceived cumulative indicators); with “there are customer complaints or O&M personnel clearly mark the number of times that congestion exists, or all The data of the average and standard deviation of the load index in the session are in the top 20%" to learn, first determine the high load of the independent variable, and then find out the dependent variable index with high correlation by comparing the detection methods, and then determine the threshold of the dependent variable (Threshold of perception index); and exclude cells that are generally low-load and have a short perception difference time to obtain a congestion data set.
  • the method further includes: using gradient to improve decision The tree GBDT method labels the second load index data to obtain a labeling result, where the labeling result includes: a first burst level and a second burst level.
  • the above-mentioned burst load model includes at least one of the following information: input data length (or observation time window, that is, the burst load model is matched based on the data of this period of time, and the specific model is obtained after matching); advance Quantity; burst load width (or burst load duration); burst load level.
  • the burst load level includes at least: the first burst level and the second burst level.
  • the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware.
  • the technical solution of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, and optical disk) and includes several instructions to make a terminal
  • the device which may be a mobile phone, computer, server, or network device, etc.) executes the methods described in the various embodiments of the present disclosure.
  • the embodiments of the present disclosure also provide a device for predicting burst load.
  • the device is used to implement the above-mentioned embodiments and example implementations, and those that have already been described will not be repeated.
  • the term "module" may implement a combination of software and/or hardware that performs predetermined functions.
  • the devices described in the following embodiments are preferably implemented in software, implementation of hardware or a combination of software and hardware is also possible and conceived.
  • FIG. 2 is a structural block diagram of a burst load prediction apparatus according to an embodiment of the present disclosure. As shown in FIG. 2, the burst load prediction apparatus according to an embodiment of the present disclosure includes an acquisition module 20 and a prediction module 22.
  • the collection module 20 is used to collect load index data of the specified area, wherein the load index data is used to characterize the load of the specified area.
  • the prediction module 22 is used to analyze the load index data using a burst load model to predict the occurrence of the burst load, where the burst load model is trained through machine learning using multiple sets of data.
  • the load index data of the designated area is collected, wherein the load index data is used to characterize the load situation of the designated area; the load index data is analyzed using a sudden load model to predict the occurrence of sudden load
  • the burst load model is trained by machine learning using multiple sets of data.
  • the device further includes a selection module 24 for selecting a burst load model suitable for the designated area from a plurality of burst load models.
  • the occurrence of the sudden load may refer to the time of occurrence of the sudden load, the duration of the occurrence of the sudden load, etc. and the technical solutions related to the sudden load.
  • the collection module 20 is used to obtain the historical data collected at the base station; pre-process the historical data to obtain the entire area cell data set; from the entire area cell data set, select congestion according to a specified rule A data set; and annotating the congestion data set to obtain a plurality of the burst load models.
  • the historical data includes at least one of the following: load indicator data, network key performance indicator data, key service quality indicator data, and user behavior indicator data.
  • the data set of all cells in the area includes: independent variable data and dependent variable data.
  • the collection module 20 is used to obtain independent variable data and dependent variable data that satisfy preset conditions, wherein the independent variable data It includes: load data, and the dependent variable data and the independent variable data have a specified functional relationship.
  • the selection module 24 is further configured to analyze the dependent variable data and the independent variable data according to the comparison detection method; use the dependent variable data whose comparison detection times satisfy a preset number of times as the congestion indicator data; And using n independent variable index data whose degree of association with the congestion indicator data satisfies a preset value as the congestion data set.
  • the above-mentioned congestion data set can be obtained by: determining independent variables (load-type indicators) and dependent variables (perceived cumulative indicators); with “there are customer complaints or O&M personnel clearly mark the number of times that congestion exists, or all The data of the average and standard deviation of the load index in the session are in the top 20%" to learn, first determine the high load of the independent variable, and then find out the dependent variable index with high correlation by comparing the detection methods, and then determine the threshold of the dependent variable (Threshold of perception index); and exclude cells that are generally low-load and have a short perception difference time to obtain a congestion data set.
  • the selection module 24 is also used for the gradient boosting decision tree GBDT method Marking the second load index data to obtain a marking result, wherein the marking result includes: a first burst level and a second burst level.
  • the congestion prediction depends on predicting the real-time traffic value, and the real-time traffic prediction is strongly related to the random behavior of the user and is difficult to accurately predict Or the cost is huge; there is no way to accurately label the data.
  • An embodiment of the present disclosure also provides an electronic device. As shown in FIG. 4, it includes a memory 40 and a processor 42.
  • the memory stores a computer program.
  • the processor 42 runs the computer program, the The burst load prediction method of the embodiment is disclosed.
  • the technical solution of the exemplary embodiment is mainly applied to the structural scenario as shown in FIG. 5, which takes the Long Term Evolved (LTE for short) system as an example, OMC stands for Network Management, and Evolved Node B , Referred to as eNB) means base station, UE means user equipment (mobile phone, tablet, etc.).
  • LTE Long Term Evolved
  • OMC Network Management
  • eNB Evolved Node B
  • UE means user equipment (mobile phone, tablet, etc.).
  • FIG. 5 also shows: Edge Computing Center (Edge Computing Unit, referred to as ECU), which is connected to all eNBs, can exist alone or can be used by existing eNB boards, and is responsible for real-time calculation processing in the venue, for example Online reasoning, real-time counter collection, audio and video auxiliary information recognition; and external data source collection unit (External Source Unit, referred to as ESU), such as cameras, drones, temperature and humidity sensors, etc. If these external data can be obtained, the performance of the venue security algorithm can be improved.
  • ESU External Source Unit
  • the ESU unit is optional and does not affect the core functions.
  • FIG. 6 is an overall flowchart according to an exemplary embodiment of the present disclosure. As shown in FIG. 6, the flow includes the following steps S402 to S420.
  • step S402 historical data is collected and integrated.
  • the granularity of the real-time data (from the eNB counter) is 5 to 15 seconds, which can be 10 seconds in the exemplary embodiment of the present disclosure.
  • Data sources include: network management performance statistics, alarm data, measurements, counter data reported by the base station in real time, counter data, and unstructured data (log files, on-site monitoring pictures and videos, etc.).
  • KPI Key Performance Indicator
  • KQI Key Quality Indicator
  • UBI user behavior indicator
  • step S404 the data health check and the data protocol.
  • This step includes both the internal data of the system and the data of the ESU. The two can be parallel and have no sequential relationship.
  • the pre-processed venue cell data set ⁇ CellDataOrigin ⁇ is output.
  • the embodiments of the present disclosure mainly use the following internal data of the system: the number of user connections, the utilization rate of physical resource blocks, the number of traffic bytes, the number of pairs of neighboring cells, the transmission delay on the wireless side, the MCS level indication, and the core customer focus on KPI.
  • External data is used in combination with internal data to improve the accuracy of burst load or congestion determination.
  • Audio and video are mainly used to extract information about the moment of excitement of the audience and the moment of high-density mobile phone operation.
  • step S406 a method for adaptively identifying congestion scenarios and determining a congestion indicator.
  • the input data set is the entire cell data set ⁇ CellDataOrigin ⁇ output in step S404.
  • the core idea is described as: a sudden large number of user connections/data services appear. Due to the limitation of the acceptance/switching capabilities of the system equipment, certain corresponding network KPIs will deteriorate after a certain delay. Therefore, a causal relationship is formed.
  • the independent variables are load indicators (such as the number of connections, the number of traffic bytes, the hardware load rate, etc.), and the dependent variable is the KPI of some systems or networks.
  • the sequence dependent detection method is used to determine the corresponding dependent variable under the premise that the independent variable is known.
  • the confidence range of the delay time is determined according to the information contained in the historical data.
  • Sudden load can only be regarded as a sudden load that causes a decrease in customer experience. You can use data on the wireless side, for example, if there are customer complaints or the operation and maintenance personnel clearly mark the sessions where there is a congestion period, or the data of the average and standard deviation of the load index in the entire session are in the top 20%. In addition, sequence comparison detection methods can also be used.
  • the venue (equivalent to the designated area in the above embodiment) mainly covers the admission control, load balancing strategy algorithm and threshold of the corresponding version of the eNB, if there are significant differences, it needs to be divided into different categories for processing.
  • the load index is used as an independent variable group to perform normalized discretization.
  • the discretization of records higher than 80 quantiles is 1, and the rest are 0.
  • the indicators of time delay and signal-to-interference-noise ratio are used as dependent variable groups.
  • the statistical mean and standard deviation are discretized to 1 (mean + 3*standard deviation), and the rest are 0.
  • Two dependent variable indicators with the highest number of comparison detections are selected as wireless side congestion indicator. According to 4), two independent variable load indexes with the highest differential correlation with the congestion indicator are selected as the congestion load indexes.
  • the number of radio resource control (Radio Resource Control, RRC for short) connections, physical resource block (Physical Resource Block, PRB for short) utilization, and the average value of byte traffic are all lower than a preset threshold. Different operators may have different requirements for this.
  • the threshold of the congestion indicator of the entire field is scanned. If the total congestion indicator threshold is less than 60 seconds, it is determined that there are no congestion sessions, and then removed from the training data.
  • step S408 the historical data is adaptively labeled.
  • the usage data set is ⁇ CellDataCongestion ⁇ . Perform this step separately for venues where the software and hardware versions of the base station are basically the same.
  • the search range of the search interval is determined based on the statistical information of historical data, for example, a 95% probability falls within 5 to 35 seconds.
  • the time TA at which the congestion load index starts to rise is determined based on "collection of non-communication system data”.
  • the congestion period is divided and sorted according to the scene, business significance and historical data statistical characteristics. For example, in Figure 7, each grid represents a time granularity, where dark periods with "C" represent congestion periods.
  • the congestion interval between two segments is 1 time granularity, the granularity is marked as congestion, that is, two segments of congestion separated by only one time granularity are considered to be the same segment; when the congestion interval between two segments is 2 or more time granularities, it is considered to be two Segment independent congestion.
  • This sub-step can make the subsequent data labeling stage clearer and make the congestion recognition rate higher.
  • step S410 the optimal model parameter combination is adaptively searched.
  • the optimal boundary conditions for model training need to be determined by adaptive search.
  • the optimal boundary combination is used to approximate the upper limit of the congestion prediction recognition rate contained in the data set.
  • This step uses a simple approximation method to search for the upper limit of the congestion recognition rate and the corresponding optimal parameter set ⁇ boundary condition 1, boundary condition 2, ..., boundary condition n ⁇ .
  • burst load prediction model there are four boundary conditions for the burst load prediction model: the number of input data records (time dimension boundary), the amount of burst load advancement, burst load width, and burst load level.
  • boundary parameters By performing a poor search or optimization on these four boundary parameters, a combination of boundary parameters that is most suitable for the current service (the optimal effect of the service's burst load or congestion recognition is equivalent to the highest accuracy of congestion prediction) is found.
  • step S412 the real-time congestion recognition model training.
  • the input data is the ⁇ completed label> data obtained in step S408, and the boundary parameter is the optimal parameter combination obtained in step S410. If there is no step S406-step S410, the situation faced in this step can be understood as a complex network with many super-parameters, the calculation amount is huge and it is difficult to find the optimal/approximate optimal congestion recognition rate. Steps S406-S410 are equivalent to separating relatively independent hyperparameter subspaces from the data space (steps S406-step S408), and individually seeking solutions (step S410).
  • this step only needs to face a relatively simple data space, which is convenient for solution and model training; for example, in Example 1, the problem faced by this step has been decomposed into available linear support vector machines (Support Vector Machine, referred to as SVM for short) ) A simple model for solving.
  • SVM Simple Vector Machine
  • the training set and the verification set are divided, and model evaluation and optimal model decision are performed.
  • the criteria for the sudden load forecasting model may include, for example, the minimum structured risk; correspondingly, the model hyperparameter mainly considers the convergence conditions and penalty parameters to improve the generalization ability.
  • the best load prediction model suitable for the current area and current business is selected from the candidate models as the application model for real-time calculation.
  • step S414 the real-time congestion recognition model is released.
  • Model training and online model application can be performed at the same computing node or at different nodes. Therefore, the model training and the model application are separated in terms of logic functions.
  • the model trained in step S412 is saved in a general or special format, and published/delivered to the online application node (ECU).
  • step S416 the real-time congestion recognition model is applied online.
  • step S41 online performance monitoring and evaluation of real-time congestion recognition.
  • the misjudgment rate and missed judgment rate of the online model for sudden load are detected, and at the same time, the other on-site indicators are integrated to judge whether the model is the cause, the user behavior pattern is abrupt or other reasons.
  • the sudden load forecast will also run simultaneously with other safeguards, as a reference basis for network dynamic parameter configuration.
  • step S420 maintain/close/recalculate.
  • step S4108 it is determined whether the current prediction and the pre-optimization strategy are maintained (good in effect) or closed (failed).
  • Burst load forecasting is a real-time strategy, and it needs to regularly incorporate the latest data to retrain and evaluate the model.
  • a solution is to dynamically adjust the parameters of the execution node based on the sudden load prediction, and take measures to avoid or slow down before the load arrives.
  • This exemplary embodiment can be understood as a further detailed technical solution of the foregoing exemplary embodiment, which includes the following steps.
  • Step 1 Real-time data collection of regional history.
  • the network unified operation and maintenance management center issues the collection task to the strategy centralized control node.
  • the strategy centralized control node collects the data reported by the eNB at a specified time and sends it to the network unified operation and maintenance management center in an agreed manner.
  • the data includes three categories: load indicators, cell service quality evaluation indicators, and base station hardware resource occupancy rate, with a granularity of 5 to 20 seconds. The time granularity of this embodiment is 10 seconds.
  • Step 2 Data health check and data specification. This step is performed automatically according to rules (which can be combined with expert interfaces).
  • the collected cell-level data may have several health problems that need to be checked and preprocessed according to the rule base. Then, according to the feature generation rules, the features used for subsequent calculations are generated from the original data fields.
  • Step 3 Discover the principles that define sudden loads.
  • the business objective is defined as solving or alleviating the severe stuck of user data business.
  • the equivalent evaluation index that most likely reflects the low stall/download is generated.
  • the load type indicators include (but are not limited to): total traffic, data bytes, maximum RRC connections, average RRC connections, board CPU usage, board memory usage, PRB usage Wait.
  • the load index that is finally used to define the burst load after data analysis is as follows: the following line PRB utilization is mainly used, and the number of RRC connections is supplemented (only when the number of RRC connections is high ), the corresponding cell equivalent evaluation indicators include: downlink PDCP packet average normalized delay, downlink QPSK coding ratio.
  • Step 4 Automatically label the historical data with sudden load.
  • step 3 some of the "burst load" data that can be identified as causing cell users to feel stuck are marked and divided into burst level 1 and burst level 2.
  • the thresholds in FIG. 10 are gradually determined using, for example, the GBDT method in combination with the existing threshold, the existing guarantee strategy process, and human experience.
  • DDR represents the relative ratio of downlink PDCP average delay
  • DPR represents the utilization rate of downlink Prb
  • RUR represents the proportion of RRC connected users.
  • DDR corresponds to the dependent variable indicating congestion
  • DPR and RUR correspond to the load type independent variables.
  • the finally obtained indivisible data parts are: cells with too low number of users, cells with unreasonable CA policies, and cells with overloaded eNB boards.
  • Step 5 Adaptive search for optimal model parameter combination.
  • burst load prediction is determined by the combination of the following time window lengths: the number of input data records (time length); how long before the marked burst load is predicted (advance); how long the marked burst load lasts;
  • the burst load level has been specified in step 4 in conjunction with the service specification and is no longer used as a parameter here.
  • the available methods are decision tree and neural network.
  • the data collection granularity of the input classifier is 10 seconds interval
  • the time span search range is 10 seconds to 100 seconds
  • the advance search range is 10 seconds to 60 seconds
  • the burst load duration search range is 10 seconds to 200 seconds to collect the input data.
  • the granularity is the step size (10 seconds in this embodiment), and the burst load has a relative grade range of 30% to 60%.
  • the optimal time window combination is:
  • the input time span is 40 seconds
  • the advance is 10 seconds
  • the burst load duration is 60 seconds.
  • Step 6 Offline training of the burst load prediction model.
  • the algorithm selects Support Vector Classifier (SVC for short), which mainly considers the limitation of single-board computing capability of the existing network base station, and the online model must consume less resources.
  • SVC Support Vector Classifier
  • the input data includes the load and equivalent evaluation index data of the cell and the main neighboring cell (from step 3).
  • the resulting model has Precision about 0.8, Recall about 0.7, and F1-Measure about 0.75.
  • Step 7 The model is delivered.
  • the network unified operation and maintenance management center will deliver the model trained in step 6 to the strategy centralized control node.
  • Step 8 Online load forecasting and pre-optimization are performed.
  • the real-time calculation of the online model and the corresponding adjustment strategy decision when the sudden load is predicted are all performed at the policy centralized control node, to avoid consuming the computing power of the eNB.
  • the real-time adjustment strategy decided by the centralized control node of the strategy is immediately issued to the eNB for execution, and at the same time, the detailed information of the misjudgment and missed judgment of the sudden load prediction is monitored and recorded.
  • subsequent processing measures include, for example, centralized load balancing and automatic adjustment of high traffic parameters.
  • Step 9 Evaluation and subsequent processing.
  • the evaluation criteria include: regional spectrum efficiency, average delay, and user complaint rate (operator index). According to the evaluation criteria, the effectiveness of the sudden load forecast and the subsequent supporting measures are comprehensively judged, and the hyperparameters of the optimal model training are adjusted accordingly.
  • the beneficial effects achieved are as follows: flexible architecture deployment, less resource consumption, taking into account the hardware capabilities of the existing system and the next generation network; the results obtained during the exploration of data and business rules
  • the intermediate result can be used to support other services under the same system architecture; it can be used as an overall framework for intelligent operation and maintenance, and the program can be used as an implementation subset.
  • the disclosed solution can coexist with other intelligent methods, share architecture, and be jointly optimized.
  • An embodiment of the present disclosure also provides a storage medium that stores a computer program, which when executed by the processor, causes the processor to execute the burst load prediction method according to various embodiments of the present disclosure.
  • the processor when the computer program is run by the processor, the processor may be caused to perform the step of: collecting load index data of a specified area, where the load index data is used to characterize the load of the specified area Situation; and use the burst load model to analyze the load index data and predict the occurrence of burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
  • the above storage medium may include, but is not limited to: a USB flash drive, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), Various media that can store program codes, such as removable hard disks, magnetic disks, or optical disks.
  • modules or steps of the present disclosure can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed in a network composed of multiple computing devices Above, optionally, they can be implemented with program code executable by the computing device, so that they can be stored in the storage device to be executed by the computing device, and in some cases, can be in a different order than here
  • the steps shown or described are performed, or they are made into individual integrated circuit modules respectively, or multiple modules or steps among them are made into a single integrated circuit module to achieve. In this way, the present disclosure is not limited to any specific combination of hardware and software.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Educational Administration (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Telephonic Communication Services (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Provided by the present disclosure are a burst load prediction method and device, a storage medium and electronic device. The burst load prediction method comprises: collecting load index data of a designated area, the load index data being used to express load conditions of the designated area; and using a burst load model to analyze the load index data and predict the occurrence of a burst load, the burst load model being trained by means of machine learning using a plurality of groups of data.

Description

突发负荷的预测方法及装置、存储介质、电子装置Method and device for predicting sudden load, storage medium, electronic device 技术领域Technical field
本公开涉及(但不限于)通信领域。This disclosure relates to, but is not limited to, the field of communications.
背景技术Background technique
服务网络通常资源有限,接入节点或全网的负荷逼近甚至达到上限通常有几种情形。一种是中长期逐渐逼近容量上限,一种是中短期周期性负荷冲高,还有一种是实时突发性激增。小时以上粒度的短期到长期负荷预测,一般以时间序列模型为主。而突发性负荷激增通常主要由网络用户随机行为决定,只和距发生时刻很近的时段有关,由此引起的拥塞是公开难题。Service networks usually have limited resources, and there are usually several situations where the load of an access node or the entire network approaches or even reaches the upper limit. One is to gradually approach the upper limit of capacity in the medium and long term, one is the periodic load surge in the short and medium term, and the other is the real-time sudden surge. Short-term to long-term load forecasting with granularity above hour is generally based on time series models. The sudden load surge is usually mainly determined by the random behavior of network users, and is only related to the time period close to the time of occurrence. The congestion caused by this is an open problem.
以蜂窝通信网络为例,小区负荷超过一定程度时,将会降低小区中用户的业务性能(例如出现延迟、卡顿),严重时产生拥塞导致系统基础指标急剧恶化以致用户业务无法正常进行。尤其用户密度较高的场景下,例如体育比赛、演唱会、大型集会时,如何缓解乃至避免实时拥塞,是运营商与用户的痛点。Taking a cellular communication network as an example, when the cell load exceeds a certain level, the service performance of users in the cell will be reduced (such as delays and stalls). In severe cases, congestion will cause the basic index of the system to deteriorate sharply, so that user services cannot proceed normally. Especially in scenarios with high user density, such as sports games, concerts, and large-scale gatherings, how to relieve or even avoid real-time congestion is a pain point for operators and users.
传统方案主要有三种实现方式:(1)按照拥塞时刻对应的用户容量进行区域规划与布置。这样在普通时段会严重降低频谱利用率并极大提高网络成本;(2)把区域内小区参数固定到“最高接入数”档位,仅保证用户的基础连接。这样会牺牲用户速率与业务种类;(3)为兼顾频谱利用率与用户体验,在用户密度很高(或称为高话务)的场景发生时,人工监控各项网络指标,根据指标是否超过预定门限来不停手动调整网络参数,然而这样的技术方案需要在现场布置很多运维人员,极大增加人工成本。There are three main ways to implement the traditional scheme: (1) Regional planning and layout according to the user capacity corresponding to the time of congestion. This will seriously reduce the spectrum utilization rate and greatly increase the network cost in ordinary time periods; (2) Fix the cell parameters in the area to the "maximum number of accesses" to ensure only the basic connection of users. This will sacrifice user rate and service type; (3) In order to balance spectrum utilization and user experience, when scenarios with high user density (or high traffic) occur, manually monitor various network indicators, according to whether the indicators exceed The threshold is set to manually adjust the network parameters. However, this technical solution requires a lot of operation and maintenance personnel to be deployed on site, which greatly increases labor costs.
发明内容Summary of the invention
根据本公开的实施例,还提供了一种突发负荷的预测方法,包括:采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;以及使用突发负荷模型对所述负载指标 数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。According to an embodiment of the present disclosure, there is also provided a method for predicting a sudden load, including: collecting load index data of a specified area, wherein the load index data is used to characterize the load of the specified area; and The load generation model analyzes the load index data to predict the occurrence of sudden load, wherein the sudden load model is trained by machine learning using multiple sets of data.
根据本公开的实施例,还提供了一种突发负荷的预测装置,包括:采集模块,用于采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;以及预测模块,用于使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。According to an embodiment of the present disclosure, there is also provided a device for predicting a sudden load, including: a collection module for collecting load index data of a specified area, wherein the load index data is used to characterize the load of the specified area Situation; and a prediction module for analyzing the load index data using a burst load model to predict the occurrence of the burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
根据本公开的实施例,还提供了一种存储介质,所述存储介质中存储有计算机程序,其中,所述计算机程序被处理器运行时,所述处理器执行根据本公开的突发负荷的预测方法。According to an embodiment of the present disclosure, there is also provided a storage medium in which a computer program is stored, wherein, when the computer program is executed by a processor, the processor executes the burst load according to the present disclosure method of prediction.
根据本公开的另一个实施例,还提供了一种电子装置,包括存储器和处理器,所述存储器中存储有计算机程序,所述处理器运行所述计算机程序时,执行根据本公开的突发负荷的预测方法。According to another embodiment of the present disclosure, there is also provided an electronic device including a memory and a processor, the memory stores a computer program, and when the processor runs the computer program, the burst according to the present disclosure is executed Load forecasting method.
附图说明BRIEF DESCRIPTION
此处所说明的附图用来提供对本公开的进一步理解,构成本公开的一部分,本公开的示意性实施例及其说明用于解释本公开,并不构成对本公开的不当限定。在附图中:The drawings described herein are used to provide a further understanding of the present disclosure and form a part of the present disclosure. The exemplary embodiments and descriptions of the present disclosure are used to explain the present disclosure and do not constitute an undue limitation on the present disclosure. In the drawings:
图1为根据本公开实施例的突发负荷的预测方法的流程图;1 is a flowchart of a method for predicting burst load according to an embodiment of the present disclosure;
图2是根据本公开实施例的突发负荷的预测装置的结构框图;2 is a structural block diagram of a burst load prediction device according to an embodiment of the present disclosure;
图3是根据本公开实施例的突发负荷的预测装置的另一结构框图;3 is another structural block diagram of a burst load prediction device according to an embodiment of the present disclosure;
图4是根据本公开实施例的电子装置的结构框图;4 is a structural block diagram of an electronic device according to an embodiment of the present disclosure;
图5是根据本公开实施例的系统框图;5 is a system block diagram according to an embodiment of the present disclosure;
图6为根据本公开示例实施例的整体流程图;6 is an overall flowchart according to an exemplary embodiment of the present disclosure;
图7是根据本公开实施例的序列对齐搜索示意图;7 is a schematic diagram of sequence alignment search according to an embodiment of the present disclosure;
图8是根据本公开实施例的边界参数示意图;8 is a schematic diagram of boundary parameters according to an embodiment of the present disclosure;
图9是根据本公开实施例的筛选等效评价指标业务的示意图;9 is a schematic diagram of screening equivalent evaluation index services according to an embodiment of the present disclosure;
图10是根据本公开实施例的实时拥塞自动标注的决策树方法。FIG. 10 is a decision tree method for real-time congestion automatic labeling according to an embodiment of the present disclosure.
具体实施方式detailed description
下文中将参考附图并结合实施例来详细说明本公开。需要说明的是,在不冲突的情况下,本公开的实施例及实施例中的特征可以相互组合。Hereinafter, the present disclosure will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
需要说明的是,本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。It should be noted that the terms “first”, “second”, etc. in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence.
本公开实施例提供了一种突发负荷的预测方法,图1为根据本公开实施例的突发负荷的预测方法的流程图,如图1所示,根据本公开实施例的突发负荷的预测方法包括步骤S102至S104。An embodiment of the present disclosure provides a method for predicting a burst load. FIG. 1 is a flowchart of a method for predicting a burst load according to an embodiment of the present disclosure. As shown in FIG. 1, the method for burst load according to an embodiment of the present disclosure The prediction method includes steps S102 to S104.
在步骤S102,采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况。In step S102, load index data of a specified area is collected, wherein the load index data is used to characterize the load condition of the specified area.
在步骤S104,使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。In step S104, the load index data is analyzed using a burst load model to predict the occurrence of burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
通过上述步骤,采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的,采用上述技术方案,解决了相关技术中,对于突发性负荷激增引起的实时拥塞,传统技术方案存在成本高等问题,进而能够对突发性负荷激增引起的拥塞进行处理,降低了人工成本。Through the above steps, collect the load index data of the specified area, where the load index data is used to characterize the load of the specified area; use the burst load model to analyze the load index data to predict the occurrence of sudden load In the case, the burst load model is trained by machine learning using multiple sets of data. The above technical solution is adopted to solve the real-time congestion caused by the sudden load surge in the related technology. The traditional technical solution has high costs. Problem, and then can deal with the congestion caused by the sudden load surge, reducing labor costs.
需要说明的是,突发负荷的发生情况可以指的是突发负荷的发生时刻,突发负荷的发生时长等等和突发负荷相关的技术方案。It should be noted that the occurrence of the sudden load may refer to the time of occurrence of the sudden load, the duration of the occurrence of the sudden load, etc. and the technical solutions related to the sudden load.
在本公开实施例中,在使用突发负荷模型对所述负载指标数据进行分析的步骤之前,所述方法还包括:从多个突发负荷模型中选择适合所述指定区域的突发负荷模型。In the embodiment of the present disclosure, before the step of analyzing the load index data using the burst load model, the method further includes: selecting a burst load model suitable for the designated area from a plurality of burst load models .
在本公开实施例中,在从多个突发负荷模型中选择适合所述指定区域的突发负荷模型的步骤之前,所述方法还包括:获取基站处采 集的历史数据;对所述历史数据进行预处理,得到区域全体小区数据集;从所述区域全体小区数据集中按照指定规则选择出拥塞数据集;以及对所述拥塞数据集进行标注,得到多个所述突发负荷模型。In an embodiment of the present disclosure, before the step of selecting a burst load model suitable for the specified area from a plurality of burst load models, the method further includes: acquiring historical data collected at the base station; Pre-processing is performed to obtain the entire region cell data set; from the entire region cell data set, a congestion data set is selected according to a specified rule; and the congestion data set is annotated to obtain a plurality of the burst load models.
在本公开实施例中,所述历史数据至少包括以下之一:负载指标数据,网络关键性能指标数据,关键服务质量指标数据,用户行为指示数据。In the embodiment of the present disclosure, the historical data includes at least one of the following: load indicator data, network key performance indicator data, key service quality indicator data, and user behavior indicator data.
在本公开实施例中,所述区域全体小区数据集包括:自变量数据,因变量数据,至少通过以下方式获取所述区域全体小区数据集:获取满足预设条件的自变量数据和因变量数据,其中,所述自变量数据包括:负荷类数据,所述因变量数据与所述自变量数据存在指定函数关系。In the embodiment of the present disclosure, the entire area cell data set includes: independent variable data and dependent variable data, and the entire area cell data set is obtained at least in the following manner: obtaining independent variable data and dependent variable data that satisfy preset conditions , Where the independent variable data includes: load type data, and the dependent variable data and the independent variable data have a specified functional relationship.
在本公开实施例中,从所述区域全体小区数据集中按照指定规则选择出拥塞数据集的步骤包括:根据对比检测方法对所述因变量数据与所述自变量数据进行分析;将对比检测次数满足预设次数的因变量数据作为拥塞指示指标数据;以及将与所述拥塞指示指标数据的关联度满足预设值的n个自变量指标数据作为所述拥塞数据集,其中,n为正整数。In the embodiment of the present disclosure, the step of selecting the congestion data set from the entire cell data set of the area according to a specified rule includes: analyzing the dependent variable data and the independent variable data according to the comparison detection method; comparing the number of comparison detections Dependent variable data satisfying a preset number of times is used as congestion indicator data; and n independent variable indicator data whose association degree with the congestion indicator data satisfies a preset value is used as the congestion data set, where n is a positive integer .
更具体地,上述拥塞数据集可以通过以下方式获取:确定自变量(负荷类指标)和因变量(感知累指标);以“存在客户投诉或运维人员明确标注存在拥塞时段的场次,或全体场次中负荷指标均值、标准差都在前20%的数据”进行学习,先确定自变量的高负荷,再通过对比检测方法,找出相关性较高的因变量指标,继而确定因变量的门限(感知指标的门限);以及排除总体都是低负荷、感知差时间短的小区,得到拥塞数据集。More specifically, the above-mentioned congestion data set can be obtained by: determining independent variables (load-type indicators) and dependent variables (perceived cumulative indicators); with “there are customer complaints or O&M personnel clearly mark the number of times that congestion exists, or all The data of the average and standard deviation of the load index in the session are in the top 20%" to learn, first determine the high load of the independent variable, and then find out the dependent variable index with high correlation by comparing the detection methods, and then determine the threshold of the dependent variable (Threshold of perception index); and exclude cells that are generally low-load and have a short perception difference time to obtain a congestion data set.
在本公开实施例中,在将与所述拥塞指示指标数据的关联度满足预设值的n个自变量指标数据作为所述拥塞数据集的步骤之后,所述方法还包括:用梯度提升决策树GBDT方法对所述第二负载指标数据进行标注,得到标注结果,其中,所述标注结果包括:第一突发等级,第二突发等级。In an embodiment of the present disclosure, after the step of taking n independent variable index data whose degree of association with the congestion indicator data satisfies a preset value as the congestion data set, the method further includes: using gradient to improve decision The tree GBDT method labels the second load index data to obtain a labeling result, where the labeling result includes: a first burst level and a second burst level.
需要说明的是,上述突发负荷模型至少包括以下之一信息:输 入数据长度(或者叫观察时间窗,即基于这段时间的数据来匹配突发负荷模型,匹配上之后得到具体模型);提前量;突发负荷宽度(或者叫突发负荷持续时间);突发负荷等级。突发负荷等级至少包括:第一突发等级,第二突发等级。It should be noted that the above-mentioned burst load model includes at least one of the following information: input data length (or observation time window, that is, the burst load model is matched based on the data of this period of time, and the specific model is obtained after matching); advance Quantity; burst load width (or burst load duration); burst load level. The burst load level includes at least: the first burst level and the second burst level.
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件。基于这样的理解,本公开的技术方案可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本公开各个实施例所述的方法。Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, and optical disk) and includes several instructions to make a terminal The device (which may be a mobile phone, computer, server, or network device, etc.) executes the methods described in the various embodiments of the present disclosure.
本公开实施例还提供了一种突发负荷的预测装置,该装置用于实现上述实施例及示例实施方式,已经进行过说明的不再赘述。如以下所使用的,术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现,但是硬件,或者软件和硬件的组合的实现也是可能并被构想的。The embodiments of the present disclosure also provide a device for predicting burst load. The device is used to implement the above-mentioned embodiments and example implementations, and those that have already been described will not be repeated. As used below, the term "module" may implement a combination of software and/or hardware that performs predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation of hardware or a combination of software and hardware is also possible and conceived.
图2是根据本公开实施例的突发负荷的预测装置的结构框图,如图2所示,根据本公开实施例的突发负荷的预测装置包括采集模块20和预测模块22。FIG. 2 is a structural block diagram of a burst load prediction apparatus according to an embodiment of the present disclosure. As shown in FIG. 2, the burst load prediction apparatus according to an embodiment of the present disclosure includes an acquisition module 20 and a prediction module 22.
采集模块20用于采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况。The collection module 20 is used to collect load index data of the specified area, wherein the load index data is used to characterize the load of the specified area.
预测模块22用于使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。The prediction module 22 is used to analyze the load index data using a burst load model to predict the occurrence of the burst load, where the burst load model is trained through machine learning using multiple sets of data.
通过本公开,采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的,采用上述技术方案,解决了相关技术中,对于突发性负荷激增引起的实时拥塞,传统技术方案存在成本高等问题,进而能够对突发性负荷激增引起的拥塞 进行处理,降低了人工成本。Through the present disclosure, the load index data of the designated area is collected, wherein the load index data is used to characterize the load situation of the designated area; the load index data is analyzed using a sudden load model to predict the occurrence of sudden load In the case, the burst load model is trained by machine learning using multiple sets of data. The above technical solution is adopted to solve the real-time congestion caused by the sudden load surge in the related technology. The traditional technical solution has high costs. Problem, and then can deal with the congestion caused by the sudden load surge, reducing labor costs.
如图3所示,在本公开实施例中,所述装置还包括选择模块24,用于从多个突发负荷模型中选择适合所述指定区域的突发负荷模型。As shown in FIG. 3, in the embodiment of the present disclosure, the device further includes a selection module 24 for selecting a burst load model suitable for the designated area from a plurality of burst load models.
需要说明的是,突发负荷的发生情况可以指的是突发负荷的发生时刻,突发负荷的发生时长等等和突发负荷相关的技术方案。It should be noted that the occurrence of the sudden load may refer to the time of occurrence of the sudden load, the duration of the occurrence of the sudden load, etc. and the technical solutions related to the sudden load.
在本公开实施例中,采集模块20用于获取基站处采集的历史数据;对所述历史数据进行预处理,得到区域全体小区数据集;从所述区域全体小区数据集中按照指定规则选择出拥塞数据集;以及对所述拥塞数据集进行标注,得到多个所述突发负荷模型。In the embodiment of the present disclosure, the collection module 20 is used to obtain the historical data collected at the base station; pre-process the historical data to obtain the entire area cell data set; from the entire area cell data set, select congestion according to a specified rule A data set; and annotating the congestion data set to obtain a plurality of the burst load models.
在本公开实施例中,所述历史数据至少包括以下之一:负载指标数据,网络关键性能指标数据,关键服务质量指标数据,用户行为指示数据。In the embodiment of the present disclosure, the historical data includes at least one of the following: load indicator data, network key performance indicator data, key service quality indicator data, and user behavior indicator data.
在本公开实施例中,所述区域全体小区数据集包括:自变量数据,因变量数据,采集模块20用于获取满足预设条件的自变量数据和因变量数据,其中,所述自变量数据包括:负荷类数据,所述因变量数据与所述自变量数据存在指定函数关系。In the embodiment of the present disclosure, the data set of all cells in the area includes: independent variable data and dependent variable data. The collection module 20 is used to obtain independent variable data and dependent variable data that satisfy preset conditions, wherein the independent variable data It includes: load data, and the dependent variable data and the independent variable data have a specified functional relationship.
在本公开实施例中,选择模块24还用于根据对比检测方法对所述因变量数据与所述自变量数据进行分析;将对比检测次数满足预设次数的因变量数据作为拥塞指示指标数据;以及将与所述拥塞指示指标数据的关联度满足预设值的n个自变量指标数据作为所述拥塞数据集。In the embodiment of the present disclosure, the selection module 24 is further configured to analyze the dependent variable data and the independent variable data according to the comparison detection method; use the dependent variable data whose comparison detection times satisfy a preset number of times as the congestion indicator data; And using n independent variable index data whose degree of association with the congestion indicator data satisfies a preset value as the congestion data set.
更具体地,上述拥塞数据集可以通过以下方式获取:确定自变量(负荷类指标)和因变量(感知累指标);以“存在客户投诉或运维人员明确标注存在拥塞时段的场次,或全体场次中负荷指标均值、标准差都在前20%的数据”进行学习,先确定自变量的高负荷,再通过对比检测方法,找出相关性较高的因变量指标,继而确定因变量的门限(感知指标的门限);以及排除总体都是低负荷、感知差时间短的小区,得到拥塞数据集。More specifically, the above-mentioned congestion data set can be obtained by: determining independent variables (load-type indicators) and dependent variables (perceived cumulative indicators); with “there are customer complaints or O&M personnel clearly mark the number of times that congestion exists, or all The data of the average and standard deviation of the load index in the session are in the top 20%" to learn, first determine the high load of the independent variable, and then find out the dependent variable index with high correlation by comparing the detection methods, and then determine the threshold of the dependent variable (Threshold of perception index); and exclude cells that are generally low-load and have a short perception difference time to obtain a congestion data set.
在本公开实施例中,在将与所述拥塞指示指标数据的关联度满足预设值的n个自变量指标数据作为所述拥塞数据集之后,选择模块 24还用于梯度提升决策树GBDT方法对所述第二负载指标数据进行标注,得到标注结果,其中,所述标注结果包括:第一突发等级,第二突发等级。In the embodiment of the present disclosure, after using n independent variable index data whose correlation degree with the congestion indicator data satisfies a preset value as the congestion data set, the selection module 24 is also used for the gradient boosting decision tree GBDT method Marking the second load index data to obtain a marking result, wherein the marking result includes: a first burst level and a second burst level.
采用上述技术方案,克服了以下技术问题,即,不能自动识别拥塞高发区域、拥塞标识特征与拥塞主要原因;拥塞预测依赖于预测实时流量值,而实时流量预测与用户随机行为强相关难以准确预测或代价巨大;没有准确标注数据的方法。By adopting the above technical solutions, the following technical problems are overcome, that is, the areas with high congestion occurrence, the characteristics of the congestion identification and the main causes of congestion cannot be automatically identified; the congestion prediction depends on predicting the real-time traffic value, and the real-time traffic prediction is strongly related to the random behavior of the user and is difficult to accurately predict Or the cost is huge; there is no way to accurately label the data.
本公开实施例还提供了一种电子装置,如图4所示,包括存储器40和处理器42,所述存储器中存储有计算机程序,所述处理器42运行所述计算机程序时,执行根据本公开实施例的突发负荷的预测方法。An embodiment of the present disclosure also provides an electronic device. As shown in FIG. 4, it includes a memory 40 and a processor 42. The memory stores a computer program. When the processor 42 runs the computer program, the The burst load prediction method of the embodiment is disclosed.
需要说明的是,上述各个实施例的技术方案可以结合使用,也可以单独使用,本公开实施例对此不作限定。It should be noted that the technical solutions of the foregoing embodiments may be used in combination, or may be used alone, which is not limited in the embodiments of the present disclosure.
以下结合示例性实施例对上述技术方案进行说明,但不用于限定本公开实施例的技术方案。The above technical solutions are described below in conjunction with exemplary embodiments, but are not used to limit the technical solutions of the embodiments of the present disclosure.
示例性实施例的技术方案主要应用于如图5所示的结构场景中,图5以长期演进(Long Term Evolved,简称为LTE)系统为例,OMC表示网管,演进型Node B(Evolved Node B,简称为eNB)表示基站,UE表示用户设备(手机、平板等)。此外,图5还示出了:边缘计算中心(Edge Calculation Unit,简称为ECU),其连接所有eNB,可单独存在也可使用现有eNB单板承担,并且负责场馆内的实时计算处理,例如在线推理、实时计数器收集、音视频辅助信息识别;以及外部数据源采集单元(External Source Unit,简称为ESU),例如摄像头、无人机、温湿度传感器等。这些外部数据若能获取,可改进场馆保障算法性能。ESU单元为可选单元,不影响核心功能。The technical solution of the exemplary embodiment is mainly applied to the structural scenario as shown in FIG. 5, which takes the Long Term Evolved (LTE for short) system as an example, OMC stands for Network Management, and Evolved Node B , Referred to as eNB) means base station, UE means user equipment (mobile phone, tablet, etc.). In addition, Figure 5 also shows: Edge Computing Center (Edge Computing Unit, referred to as ECU), which is connected to all eNBs, can exist alone or can be used by existing eNB boards, and is responsible for real-time calculation processing in the venue, for example Online reasoning, real-time counter collection, audio and video auxiliary information recognition; and external data source collection unit (External Source Unit, referred to as ESU), such as cameras, drones, temperature and humidity sensors, etc. If these external data can be obtained, the performance of the venue security algorithm can be improved. The ESU unit is optional and does not affect the core functions.
图6为根据本公开示例实施例的整体流程图,如图6所示,该流程包括以下步骤S402至S420。FIG. 6 is an overall flowchart according to an exemplary embodiment of the present disclosure. As shown in FIG. 6, the flow includes the following steps S402 to S420.
在步骤S402,历史数据收集与集成,其中的实时数据(来自eNB计数器)的粒度为5~15秒,在本公开的示例实施例中可以为10秒。In step S402, historical data is collected and integrated. The granularity of the real-time data (from the eNB counter) is 5 to 15 seconds, which can be 10 seconds in the exemplary embodiment of the present disclosure.
收集包含负荷、容量指标的数据或数据集,以及相关的系统关 键性能指标用于生成评价准则。数据来源包括:网管性能统计数据,告警数据,基站实时上报的测量、计数器数据,非结构化数据(日志文件、现场监控图片视频等)。本公开中,最终用于量化处理的负荷/容量以及网络关键性能指标(Key Performance Indicator,简称为KPI)、关键服务质量指标(Key Quality Indicator,简称为KQI)、用户行为指示(UBI)属于结构化的数值型数据,需要从非结构化数据中提取出负荷/容量相关的字段并转为结构化形式。其中涉及的独立子步骤(之间没有顺序要求)包括:采集无线侧前台历史数据;以及采集非通信系统数据,例如比赛期间的看台监控视频(用于实时识别观众手机操作密度)。Collect data or data sets containing load and capacity indicators, and related key system performance indicators to generate evaluation criteria. Data sources include: network management performance statistics, alarm data, measurements, counter data reported by the base station in real time, counter data, and unstructured data (log files, on-site monitoring pictures and videos, etc.). In this disclosure, the final load/capacity used for quantization processing and the key performance indicators (Key Performance Indicator, KPI for short), key service quality indicators (Key Quality Indicator, KQI for short), and user behavior indicator (UBI) belong to the structure For numerical data, it is necessary to extract load/capacity related fields from unstructured data and convert them into structured forms. The independent sub-steps involved (there is no sequence requirement between them) include: collecting wireless front-end historical data; and collecting non-communication system data, such as stand monitoring video during the game (for real-time identification of audience mobile phone operation density).
在步骤S404,数据健康度检验与数据规约。In step S404, the data health check and the data protocol.
对历史原始数据字段进行检验、剔除异常、补全、转换、合并、拆分、衍生等操作,生成适合量化挖掘评估体系的“特征(Feature)”字段。本步骤包含系统内部数据与ESU数据两方面,两者可并行没有前后顺序关系。本步骤完成后,输出预处理后的场馆全体小区数据集{CellDataOrigin}。Perform operations on historical raw data fields, remove anomalies, completions, conversions, merges, splits, derivations, and other operations to generate "Feature" fields suitable for quantitative mining evaluation systems. This step includes both the internal data of the system and the data of the ESU. The two can be parallel and have no sequential relationship. After the completion of this step, the pre-processed venue cell data set {CellDataOrigin} is output.
本公开实施例主要使用以下系统内部数据:用户连接数、物理资源块利用率、流量字节数、邻区对切换数、无线侧传输时延、MCS等级指示、核心客户关注KPI。The embodiments of the present disclosure mainly use the following internal data of the system: the number of user connections, the utilization rate of physical resource blocks, the number of traffic bytes, the number of pairs of neighboring cells, the transmission delay on the wireless side, the MCS level indication, and the core customer focus on KPI.
外部数据(可选)用于结合内部数据提高突发负荷或拥塞判定准确率。音视频主要用于提取观众兴奋时刻与高密度手机操作时刻信息。External data (optional) is used in combination with internal data to improve the accuracy of burst load or congestion determination. Audio and video are mainly used to extract information about the moment of excitement of the audience and the moment of high-density mobile phone operation.
在步骤S406,拥塞场景自适应识别与拥塞指示指标确定方法。In step S406, a method for adaptively identifying congestion scenarios and determining a congestion indicator.
输入数据集为步骤S404输出的区域全体小区数据集{CellDataOrigin}。核心思想描述为:用户突发性大量连接/数据业务出现,因系统设备的接纳/切换能力限制,延后一定时间才会出现某些对应网络KPI恶化。因此构成一种因果关系,自变量是负荷类指标(例如连接数、流量字节数、硬件负载率等),因变量是某些系统或网络的KPI。本步骤通过序列对比检测的方式,自变量已知的前提下可确定对应因变量,同时根据历史数据包含的信息确定延后时间的 置信度范围。The input data set is the entire cell data set {CellDataOrigin} output in step S404. The core idea is described as: a sudden large number of user connections/data services appear. Due to the limitation of the acceptance/switching capabilities of the system equipment, certain corresponding network KPIs will deteriorate after a certain delay. Therefore, a causal relationship is formed. The independent variables are load indicators (such as the number of connections, the number of traffic bytes, the hardware load rate, etc.), and the dependent variable is the KPI of some systems or networks. In this step, the sequence dependent detection method is used to determine the corresponding dependent variable under the premise that the independent variable is known. At the same time, the confidence range of the delay time is determined according to the information contained in the historical data.
拥塞体现为,例如,用户无法接入/收发数据,或收发速率很慢。Congestion manifests itself as, for example, users cannot access/receive data or the transmission and reception rate is very slow.
引起客户体验下降的负荷突升才能算突发负荷。可以使用无线侧数据,例如,存在客户投诉或运维人员明确标注存在拥塞时段的场次,或者全体场次中负荷指标均值、标准差都在前20%的数据。此外,还可以使用序列对比检测方法。Sudden load can only be regarded as a sudden load that causes a decrease in customer experience. You can use data on the wireless side, for example, if there are customer complaints or the operation and maintenance personnel clearly mark the sessions where there is a congestion period, or the data of the average and standard deviation of the load index in the entire session are in the top 20%. In addition, sequence comparison detection methods can also be used.
若场馆(相当于上述实施例的指定区域)主要覆盖eNB对应版本的接纳控制、负荷均衡策略算法与门限若存在重大差异,需要分成不同类别处理。If the venue (equivalent to the designated area in the above embodiment) mainly covers the admission control, load balancing strategy algorithm and threshold of the corresponding version of the eNB, if there are significant differences, it needs to be divided into different categories for processing.
负荷类指标作为自变量组,进行归一离散化处理,高于80分位数的记录离散化为1,其余为0。The load index is used as an independent variable group to perform normalized discretization. The discretization of records higher than 80 quantiles is 1, and the rest are 0.
时延、信干噪比类指标作为因变量组,统计均值与标准差,将高于(均值+3*标准差)的记录离散化为1,其余为0。The indicators of time delay and signal-to-interference-noise ratio are used as dependent variable groups. The statistical mean and standard deviation are discretized to 1 (mean + 3*standard deviation), and the rest are 0.
对齐时间轴,对比检测自变量组与因变量组。统计因变量相对自变量延迟1~2个时间粒度、且持续超过2个粒度的次数。Align the time axis and compare the independent variable group with the dependent variable group. Count the number of times the dependent variable is delayed from the independent variable by 1 to 2 time granularities and continues to exceed 2 granularities.
选出对比检测次数最高的两个因变量指标作为无线侧拥塞指示指标。根据4),选出与拥塞指示指标差分关联最高的2个自变量负荷指标作为拥塞负荷指标。Two dependent variable indicators with the highest number of comparison detections are selected as wireless side congestion indicator. According to 4), two independent variable load indexes with the highest differential correlation with the congestion indicator are selected as the congestion load indexes.
统计所有拥塞场次的拥塞指标,将其(均值+2*标准差)定义为拥塞识别门限TH_CONGESTION。Count the congestion indicators of all congestion sessions, and define its (mean+2*standard deviation) as the congestion recognition threshold TH_CONGESTION.
全体历史数据拥塞场景判决。若某个场馆某场比赛小区负荷都很低(例如观众很少),则该场数据需要从训练集中排除。Judgment of all historical data congestion scenarios. If the load of a community in a certain venue and a game is very low (for example, there are few spectators), then the data of that venue needs to be excluded from the training set.
可选地,无线资源控制(Radio Resource Control,简称为RRC)连接数、物理资源块(Physical Resource Block,简称为PRB)利用率、字节流量均值都低于预设门限。不同运营商对此可能有不同要求。Optionally, the number of radio resource control (Radio Resource Control, RRC for short) connections, physical resource block (Physical Resource Block, PRB for short) utilization, and the average value of byte traffic are all lower than a preset threshold. Different operators may have different requirements for this.
根据上述判决出的拥塞指标门限TH_CONGESTION,扫描全场拥塞指标门限,若拥塞总时间不到60秒,判为无拥塞场次,然后从训练数据中剔除。According to the threshold TH_CONGESTION of the congestion indicator determined above, the threshold of the congestion indicator of the entire field is scanned. If the total congestion indicator threshold is less than 60 seconds, it is determined that there are no congestion sessions, and then removed from the training data.
得到并保存所有存在拥塞的场次历史数据 {CellDataCongestion}。Obtain and save historical data of all congested sessions {CellDataCongestion}.
在步骤S408,历史数据自适应标注。使用数据集为{CellDataCongestion}。基站软硬件版本基本一致的场馆分开进行本步骤。In step S408, the historical data is adaptively labeled. The usage data set is {CellDataCongestion}. Perform this step separately for venues where the software and hardware versions of the base station are basically the same.
根据TH_CONGESTION扫描并标注数据集中所有小区的拥塞指示指标。Scan and mark the congestion indicators of all cells in the data set according to TH_CONGESTION.
记录“无线侧前台历史数据的采集”标注出的拥塞时段,对拥塞负荷指标一阶差分序列进行搜索区间个粒度内的区间扫描。只有当负荷指标处于上升趋势时才能判为突发负荷。搜索区间含义参考图8与步骤S406中对延后时间的描述。搜索区间的搜索范围根据历史数据的统计信息判定,例如95%概率落入5~35秒。Record the congestion time period marked by "Collection of historical data on the wireless side foreground", and perform interval scanning within the granularity of the search interval for the first-order difference sequence of the congestion load index. Only when the load index is in an upward trend can it be judged as a sudden load. For the meaning of the search interval, refer to the description of the delay time in FIG. 8 and step S406. The search range of the search interval is determined based on the statistical information of historical data, for example, a 95% probability falls within 5 to 35 seconds.
基于“非通信系统数据的采集”确定拥塞负荷指标开始上升的时刻TA。The time TA at which the congestion load index starts to rise is determined based on "collection of non-communication system data".
对拥塞时段进行分割整理,根据场景、业务意义与历史数据统计特征确定。例如,在图7中,每个格子代表一个时间粒度,其中带“C”深色时段表示拥塞期。当两段拥塞间隔为1个时间粒度,将该粒度标记为拥塞,即只间隔一个时间粒度的两段拥塞认为是同一段;当两段拥塞间隔为2个或以上时间粒度时,认为是两段独立的拥塞。本子步骤可令后续的数据标注阶段更清晰,令拥塞识别率更高。The congestion period is divided and sorted according to the scene, business significance and historical data statistical characteristics. For example, in Figure 7, each grid represents a time granularity, where dark periods with "C" represent congestion periods. When the congestion interval between two segments is 1 time granularity, the granularity is marked as congestion, that is, two segments of congestion separated by only one time granularity are considered to be the same segment; when the congestion interval between two segments is 2 or more time granularities, it is considered to be two Segment independent congestion. This sub-step can make the subsequent data labeling stage clearer and make the congestion recognition rate higher.
在步骤S410,最佳模型参数组合自适应搜索。In step S410, the optimal model parameter combination is adaptively searched.
模型训练的最佳边界条件需要通过自适应搜索来确定,该最佳边界组合用于逼近数据集蕴含的拥塞预测识别率的上限。基本原理为拥塞识别率上限由数据集本身蕴含的信息决定,拥塞识别率=边界条件限制下的模型函数(输入特征矩阵)。The optimal boundary conditions for model training need to be determined by adaptive search. The optimal boundary combination is used to approximate the upper limit of the congestion prediction recognition rate contained in the data set. The basic principle is that the upper limit of the congestion recognition rate is determined by the information contained in the data set itself, and the congestion recognition rate = the model function under the boundary conditions (input feature matrix).
本步骤用简单的近似方法,搜索出拥塞识别率近似上限以及对应的最佳参数组{边界条件1,边界条件2,……,边界条件n}。This step uses a simple approximation method to search for the upper limit of the congestion recognition rate and the corresponding optimal parameter set {boundary condition 1, boundary condition 2, ..., boundary condition n}.
如图8所示,突发负荷预测模型的边界条件有4个:输入数据记录的条数(时间维度边界),突发负荷的提前量,突发负荷宽度,突发负荷等级。As shown in Figure 8, there are four boundary conditions for the burst load prediction model: the number of input data records (time dimension boundary), the amount of burst load advancement, burst load width, and burst load level.
通过对这4个边界参数进行穷搜或寻优,找到最适合当前业务 (该业务的突发负荷或拥塞识别效果最优,等价于拥塞预测准确度最高)的边界参数组合。By performing a poor search or optimization on these four boundary parameters, a combination of boundary parameters that is most suitable for the current service (the optimal effect of the service's burst load or congestion recognition is equivalent to the highest accuracy of congestion prediction) is found.
在步骤S412,实时拥塞识别模型训练。In step S412, the real-time congestion recognition model training.
输入数据为步骤S408得到的<完成标注>数据,边界参数为步骤S410得到的最优参数组合。若没有步骤S406-步骤S410,本步骤面对的情形可以理解为一个超参众多的复杂网络,运算量巨大且很难找到最优/近似最优拥塞识别率。第步骤S406-步骤S410相当于从数据空间中分离出相对独立的超参子空间(第步骤S406-步骤S408),单独寻优求解(步骤S410)。这样,本步骤只需要面对相对简单的数据空间,方便进行求解与模型训练;例如实施例1中,本步骤面对的问题已被分解为可用线性支持向量机(Support Vector Machine,简称为SVM)求解的简单模型。The input data is the <completed label> data obtained in step S408, and the boundary parameter is the optimal parameter combination obtained in step S410. If there is no step S406-step S410, the situation faced in this step can be understood as a complex network with many super-parameters, the calculation amount is huge and it is difficult to find the optimal/approximate optimal congestion recognition rate. Steps S406-S410 are equivalent to separating relatively independent hyperparameter subspaces from the data space (steps S406-step S408), and individually seeking solutions (step S410). In this way, this step only needs to face a relatively simple data space, which is convenient for solution and model training; for example, in Example 1, the problem faced by this step has been decomposed into available linear support vector machines (Support Vector Machine, referred to as SVM for short) ) A simple model for solving.
可选地,以交叉验证方式,分割训练集与验证集,并进行模型评估与最优模型判决。突发负荷预测模型的准则可以包括,例如,结构化风险最小;对应的,模型超参主要考虑收敛条件与惩罚参数,以提高泛化能力。Optionally, in a cross-validation manner, the training set and the verification set are divided, and model evaluation and optimal model decision are performed. The criteria for the sudden load forecasting model may include, for example, the minimum structured risk; correspondingly, the model hyperparameter mainly considers the convergence conditions and penalty parameters to improve the generalization ability.
通过模型评估,从候选模型中选出最适合当前区域、当前业务的突发负荷预测模型,作为实时计算的应用模型。Through model evaluation, the best load prediction model suitable for the current area and current business is selected from the candidate models as the application model for real-time calculation.
在步骤S414,实时拥塞识别模型发布。In step S414, the real-time congestion recognition model is released.
模型训练与模型在线应用可在同一个计算节点进行,也可在不同节点进行。因此模型训练与模型应用在逻辑功能上分开,步骤S412训练得到的模型以通用或专用格式保存,并发布/传递到在线应用的节点(ECU)。Model training and online model application can be performed at the same computing node or at different nodes. Therefore, the model training and the model application are separated in terms of logic functions. The model trained in step S412 is saved in a general or special format, and published/delivered to the online application node (ECU).
在步骤S416,实时拥塞识别模型在线应用。In step S416, the real-time congestion recognition model is applied online.
将得到的模型投入在线实际应用,运行在ECU。Put the obtained model into online practical application and run it in ECU.
在步骤S418,实时拥塞识别在线性能监测评估。In step S418, online performance monitoring and evaluation of real-time congestion recognition.
检测在线模型对突发负荷的错判率、漏判率等,同时综合现场其他指标判断是模型原因、用户行为模式突变还是其他原因。通常,突发负荷预测还会与其他保障措施同时运行,作为网络动态参数配置的参考依据。The misjudgment rate and missed judgment rate of the online model for sudden load are detected, and at the same time, the other on-site indicators are integrated to judge whether the model is the cause, the user behavior pattern is abrupt or other reasons. Generally, the sudden load forecast will also run simultaneously with other safeguards, as a reference basis for network dynamic parameter configuration.
在步骤S420,维持/关闭/重新计算。In step S420, maintain/close/recalculate.
根据步骤S418的评估结果,判决当前预测与预优化策略的维持(良好生效中)或关闭(失败)。突发负荷预测属于实时策略,需要定期纳入最新数据重新训练并评估模型。According to the evaluation result of step S418, it is determined whether the current prediction and the pre-optimization strategy are maintained (good in effect) or closed (failed). Burst load forecasting is a real-time strategy, and it needs to regularly incorporate the latest data to retrain and evaluate the model.
在例如体育比赛、演唱会、大型集会期间,存在小区负荷突然激增并导致用户速率下降甚至连接中断的情形。为保障话务质量,一种解决方案为基于突发负荷预测进行执行节点的参数动态调整,在负荷到来前采取措施避免或减缓。During, for example, sports competitions, concerts, and large-scale gatherings, there is a situation where the cell load suddenly increases and the user rate drops or even the connection is interrupted. To ensure the quality of traffic, a solution is to dynamically adjust the parameters of the execution node based on the sudden load prediction, and take measures to avoid or slow down before the load arrives.
本示例实施例可以理解为是前述示例实施例的进一步的详细技术方案,其包括以下步骤。This exemplary embodiment can be understood as a further detailed technical solution of the foregoing exemplary embodiment, which includes the following steps.
步骤1,区域历史实时数据采集。Step 1. Real-time data collection of regional history.
由网络统一运维管理中心下发采集任务到策略集中控制节点,策略集中控制节点在规定时间收集eNB上报的数据,并以约定方式发送给网络统一运维管理中心。数据包括三大类:负荷类指标、小区服务质量评价指标、基站硬件资源占用率,粒度为5~20秒。本实施例的时间粒度为10秒。The network unified operation and maintenance management center issues the collection task to the strategy centralized control node. The strategy centralized control node collects the data reported by the eNB at a specified time and sends it to the network unified operation and maintenance management center in an agreed manner. The data includes three categories: load indicators, cell service quality evaluation indicators, and base station hardware resource occupancy rate, with a granularity of 5 to 20 seconds. The time granularity of this embodiment is 10 seconds.
步骤2,数据健康度检验与数据规约。该步骤根据规则(可结合专家接口)自动执行。Step 2. Data health check and data specification. This step is performed automatically according to rules (which can be combined with expert interfaces).
在网络统一运维管理中心进行。由于可能出现有关模块临时失效,数据传递链路拥塞、通讯失灵、解码错误等事件,所以采集到的小区级数据可能出现若干健康度问题需要根据规则库进行检验和预处理。之后根据特征生成规则,从原始数据字段产生用于后续计算的特征。In the network unified operation and maintenance management center. Due to events such as temporary failure of the module, congestion of the data transmission link, communication failure, and decoding error, the collected cell-level data may have several health problems that need to be checked and preprocessed according to the rule base. Then, according to the feature generation rules, the features used for subsequent calculations are generated from the original data fields.
步骤3,发掘定义突发负荷的原则。Step 3. Discover the principles that define sudden loads.
本实施例中,在网络统一运维管理中心进行。业务目标定义为解决或缓解用户数据业务严重卡顿。表示节点负荷的数据字段有多个,而卡顿现象也与多个网络KPI/KQI有关。因此,需要找出与业务目标关系最密切的负荷指标与网络KPI/KQI。In this embodiment, it is performed in the network unified operation and maintenance management center. The business objective is defined as solving or alleviating the severe stuck of user data business. There are multiple data fields representing node load, and the stuttering phenomenon is also related to multiple network KPI/KQI. Therefore, it is necessary to find the load index and network KPI/KQI that are most closely related to the business objectives.
结合现场维护优化人员的经验,生成最可能体现卡顿/下载低的等效评价指标,与每种负荷指标时序对齐后,可以利用,例如,关联 算法检测负荷指标突增与等效评价指标变化的一致性。例如,连接数、PRB利用率、流量字节数的变化趋势与趋势起止时刻对齐,可以都归为自变量。Combined with the experience of on-site maintenance and optimization personnel, the equivalent evaluation index that most likely reflects the low stall/download is generated. After being aligned with the timing of each load index, you can use, for example, the correlation algorithm to detect the sudden increase in load index and the change in equivalent evaluation index Consistency. For example, the change trends of the number of connections, PRB utilization rate, and the number of flow bytes are aligned with the beginning and end of the trend, and they can all be classified as independent variables.
去除业务体现不显著的负荷指标后,对剩余负荷类指标进行共线性分析,例如分层聚类、相关系数。若业务体现一般且与强业务体现负荷指标共线性,则去除这些负荷指标。本实施例中,负荷类的指标包括(但不限于):总流量数、数据字节数、最大RRC连接数、平均RRC连接数、单板CPU占用率、单板内存占用率、PRB占用率等。最终分析比较后,只需要使用RRC最大连接数、下行PRB利用率作为自变量,即主成分只有2个。After removing the load indicators that are not significant in the business, perform collinear analysis on the remaining load indicators, such as hierarchical clustering and correlation coefficients. If the business manifestation is general and collinear with the strong business manifestation load index, these load indexes are removed. In this embodiment, the load type indicators include (but are not limited to): total traffic, data bytes, maximum RRC connections, average RRC connections, board CPU usage, board memory usage, PRB usage Wait. After the final analysis and comparison, only the RRC maximum number of connections and the downstream PRB utilization rate need to be used as independent variables, that is, there are only two principal components.
在主要负荷指标突然增高或持续高峰时段,检验等效评价指标的变化一致性。如图9所示,等效卡顿/下载速率低的恶化指标作为因变量,上升尖峰需要比负荷类的自变量上升尖峰有所延迟。During the sudden increase of the main load index or the continuous peak period, the consistency of the change of the equivalent evaluation index is checked. As shown in Figure 9, the deterioration index with a low equivalent stuttering/download rate is used as the dependent variable, and the rising spike needs to be delayed from the independent variable rising spike of the load type.
本实施例中,在运营商需求区域内,经过数据分析最终用于定义突发负荷的负荷指标为:以下行PRB利用率为主,并且以RRC连接数为辅(仅当RRC连接数很高),对应的小区等效评价指标包括:下行PDCP包平均归一化时延,下行QPSK编码比例。In this embodiment, in the operator's demand area, the load index that is finally used to define the burst load after data analysis is as follows: the following line PRB utilization is mainly used, and the number of RRC connections is supplemented (only when the number of RRC connections is high ), the corresponding cell equivalent evaluation indicators include: downlink PDCP packet average normalized delay, downlink QPSK coding ratio.
步骤4,对历史数据进行突发负荷自动标注。Step 4: Automatically label the historical data with sudden load.
在网络统一运维管理中心进行。在步骤3阶段,有部分可确认为导致小区用户感觉卡顿的“突发负荷”数据得到了标注,并分为突发等级1和突发等级2。本实施例中,结合现有门限、现有保障策略流程与人工经验,使用,例如,GBDT的方式来逐步确定图10中的各门限。图10中,DDR表示下行PDCP平均时延相对比值,DPR表示下行Prb利用率,RUR表示RRC连接用户数占比。DDR对应指示拥塞的因变量,DPR与RUR对应负荷类自变量。In the network unified operation and maintenance management center. In step 3, some of the "burst load" data that can be identified as causing cell users to feel stuck are marked and divided into burst level 1 and burst level 2. In this embodiment, the thresholds in FIG. 10 are gradually determined using, for example, the GBDT method in combination with the existing threshold, the existing guarantee strategy process, and human experience. In Figure 10, DDR represents the relative ratio of downlink PDCP average delay, DPR represents the utilization rate of downlink Prb, and RUR represents the proportion of RRC connected users. DDR corresponds to the dependent variable indicating congestion, and DPR and RUR correspond to the load type independent variables.
最终得到的不可分数据部分为:用户数过低的小区,CA策略不合理的小区,以及eNB单板超负荷的小区。The finally obtained indivisible data parts are: cells with too low number of users, cells with unreasonable CA policies, and cells with overloaded eNB boards.
步骤5,最佳模型参数组合自适应搜索。Step 5. Adaptive search for optimal model parameter combination.
本实施例中,在网络统一运维管理中心进行。突发负荷预测的有效性由以下时间窗长度的组合决定:输入数据记录的条数(时间长 度);在标注的突发负荷前多久进行预测(提前量);标注的突发负荷持续多久;突发负荷等级已在步骤4中结合业务规范指定,此处不再作为参数。In this embodiment, it is performed in the network unified operation and maintenance management center. The effectiveness of burst load prediction is determined by the combination of the following time window lengths: the number of input data records (time length); how long before the marked burst load is predicted (advance); how long the marked burst load lasts; The burst load level has been specified in step 4 in conjunction with the service specification and is no longer used as a parameter here.
对于历史数据,使用,例如,SVM多分类算法的分类精度评估参数组合效果,可选方法为决策树、神经网络。输入分类器的数据采集粒度为10秒间隔,时间跨度搜索范围10秒~100秒,提前量搜索范围10秒~60秒,突发负荷持续长度搜索范围10秒~200秒,以输入数据的采集粒度为步长(本实施例中为10秒),突发负荷相对等级范围30%~60%。For historical data, use, for example, the classification accuracy of the SVM multi-classification algorithm to evaluate the effect of the combination of parameters. The available methods are decision tree and neural network. The data collection granularity of the input classifier is 10 seconds interval, the time span search range is 10 seconds to 100 seconds, the advance search range is 10 seconds to 60 seconds, and the burst load duration search range is 10 seconds to 200 seconds to collect the input data. The granularity is the step size (10 seconds in this embodiment), and the burst load has a relative grade range of 30% to 60%.
对于当前系统设备、当前区域,得到的最优时间窗组合为:For the current system equipment and current area, the optimal time window combination is:
{输入时间跨度40秒,提前量10秒,突发负荷持续长度60秒zuo}。{The input time span is 40 seconds, the advance is 10 seconds, and the burst load duration is 60 seconds.}
步骤6,突发负荷预测模型离线训练。Step 6. Offline training of the burst load prediction model.
选择某体育馆历史比赛期间的数据,以步骤5得到的参数组合、结构性风险最小原则进行离线模型训练。算法选择支持向量分类器(Support Vector Classifier,简称为SVC),主要考虑现网基站单板运算能力限制,在线模型必须消耗较少资源。使用近一个月的数据,输入数据包括本小区与主要邻区的负荷及等效评价指标数据(来自步骤3)。Select the data during a historical competition in a gymnasium, and use the parameter combination obtained in step 5 and the principle of minimum structural risk for offline model training. The algorithm selects Support Vector Classifier (SVC for short), which mainly considers the limitation of single-board computing capability of the existing network base station, and the online model must consume less resources. Using the data for the past month, the input data includes the load and equivalent evaluation index data of the cell and the main neighboring cell (from step 3).
最终得到的模型,Precision约0.8,Recall约0.7,F1-Measure约0.75。The resulting model has Precision about 0.8, Recall about 0.7, and F1-Measure about 0.75.
步骤7,模型下发。 Step 7. The model is delivered.
在该体育馆下一场比赛开始前,网络统一运维管理中心将步骤6训练出来的模型下发到策略集中控制节点。Before the start of the next game in the stadium, the network unified operation and maintenance management center will deliver the model trained in step 6 to the strategy centralized control node.
步骤8,突发负荷预测与预优化在线执行。Step 8. Online load forecasting and pre-optimization are performed.
本实施例中,在线模型的实时运算,以及预测出突发负荷即将到来时的对应调整策略判决,都在策略集中控制节点进行,避免消耗eNB的计算能力。策略集中控制节点判决出的实时调整策略立刻下发给eNB进行执行,同时监测并记录突发负荷预测错判、漏判的详细信息。In this embodiment, the real-time calculation of the online model and the corresponding adjustment strategy decision when the sudden load is predicted are all performed at the policy centralized control node, to avoid consuming the computing power of the eNB. The real-time adjustment strategy decided by the centralized control node of the strategy is immediately issued to the eNB for execution, and at the same time, the detailed information of the misjudgment and missed judgment of the sudden load prediction is monitored and recorded.
本实施例中,后续的处理措包括,例如,集中式负荷均衡、高话务参数自动调整。In this embodiment, subsequent processing measures include, for example, centralized load balancing and automatic adjustment of high traffic parameters.
步骤9,评估与后续处理。Step 9. Evaluation and subsequent processing.
本实施例中,评估准则包括:区域频谱效率、平均时延、用户投诉率(运营商指标)。根据评估准则,综合判断突发负荷预测及后续配套措施的有效性,并以此调整优化模型训练的超参数。In this embodiment, the evaluation criteria include: regional spectrum efficiency, average delay, and user complaint rate (operator index). According to the evaluation criteria, the effectiveness of the sudden load forecast and the subsequent supporting measures are comprehensively judged, and the hyperparameters of the optimal model training are adjusted accordingly.
综上所述,采用本公开的技术方案,达到的有益效果如下:体系架构部署灵活,资源消耗较少,兼顾现有系统与下一代网络的硬件能力;在数据与业务规则探索过程中得到的中间结果,可用于支持相同系统架构下的其他业务;可作为智能运维的整体框架,方案作为一个实施子集。本公开方案可与其他智能方法共存、共享架构且联合优化。In summary, with the technical solution of the present disclosure, the beneficial effects achieved are as follows: flexible architecture deployment, less resource consumption, taking into account the hardware capabilities of the existing system and the next generation network; the results obtained during the exploration of data and business rules The intermediate result can be used to support other services under the same system architecture; it can be used as an overall framework for intelligent operation and maintenance, and the program can be used as an implementation subset. The disclosed solution can coexist with other intelligent methods, share architecture, and be jointly optimized.
本公开的实施例还提供了一种存储介质,该存储介质存储有计算机程序,该计算机程序被处理器运行时,使得处理器执行根据本公开各实施例的突发负荷的预测方法。An embodiment of the present disclosure also provides a storage medium that stores a computer program, which when executed by the processor, causes the processor to execute the burst load prediction method according to various embodiments of the present disclosure.
可选地,在本实施例中,该计算机程序被处理器运行时,可以使得处理器执行步骤:采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;以及使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。Optionally, in this embodiment, when the computer program is run by the processor, the processor may be caused to perform the step of: collecting load index data of a specified area, where the load index data is used to characterize the load of the specified area Situation; and use the burst load model to analyze the load index data and predict the occurrence of burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
可选地,在本实施例中,上述存储介质可以包括但不限于:U盘、只读存储器(Read-Only Memory,简称为ROM)、随机存取存储器(Random Access Memory,简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。Optionally, in this embodiment, the above storage medium may include, but is not limited to: a USB flash drive, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), Various media that can store program codes, such as removable hard disks, magnetic disks, or optical disks.
可选地,本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例,本实施例在此不再赘述。Optionally, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementation manners, and details are not repeated in this embodiment.
显然,本领域的技术人员应该明白,上述的本公开的各模块或各步骤可以用通用的计算装置来实现,它们可以集中在单个的计算装置上,或者分布在多个计算装置所组成的网络上,可选地,它们可以用计算装置可执行的程序代码来实现,从而,可以将它们存储在存储 装置中由计算装置来执行,并且在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤,或者将它们分别制作成各个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样,本公开不限制于任何特定的硬件和软件结合。Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present disclosure can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed in a network composed of multiple computing devices Above, optionally, they can be implemented with program code executable by the computing device, so that they can be stored in the storage device to be executed by the computing device, and in some cases, can be in a different order than here The steps shown or described are performed, or they are made into individual integrated circuit modules respectively, or multiple modules or steps among them are made into a single integrated circuit module to achieve. In this way, the present disclosure is not limited to any specific combination of hardware and software.
以上所述仅为本公开的优选实施例而已,并不用于限制本公开,对于本领域的技术人员来说,本公开可以有各种更改和变化。凡在本公开的原则之内,所作的任何修改、等同替换、改进等,均应包含在本公开的保护范围之内。The above are only preferred embodiments of the present disclosure, and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the principles of this disclosure shall be included in the protection scope of this disclosure.

Claims (11)

  1. 一种突发负荷的预测方法,包括:A sudden load forecasting method, including:
    采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;以及Collecting load index data of a specified area, wherein the load index data is used to characterize the load of the specified area; and
    使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。The load index data is analyzed using a burst load model to predict the occurrence of burst load, wherein the burst load model is trained through machine learning using multiple sets of data.
  2. 根据权利要求1所述的方法,其中,在使用突发负荷模型对所述负载指标数据进行分析的步骤之前,所述方法还包括:The method according to claim 1, wherein before the step of analyzing the load index data using the burst load model, the method further comprises:
    从多个突发负荷模型中选择适合所述指定区域的突发负荷模型。Select a burst load model suitable for the designated area from a plurality of burst load models.
  3. 根据权利要求2所述的方法,其中,在从多个突发负荷模型中选择适合所述指定区域的突发负荷模型的步骤之前,所述方法还包括:The method according to claim 2, wherein before the step of selecting a burst load model suitable for the designated area from a plurality of burst load models, the method further comprises:
    获取基站处采集的历史数据;Obtain historical data collected at the base station;
    对所述历史数据进行预处理,得到区域全体小区数据集;Pre-process the historical data to obtain a data set of all cells in the area;
    从所述区域全体小区数据集中按照指定规则选择出拥塞数据集;以及Selecting a congestion data set from all cell data sets in the area according to a specified rule; and
    对所述拥塞数据集进行标注,得到多个所述突发负荷模型。Annotate the congestion data set to obtain multiple burst load models.
  4. 根据权利要求3所述的方法,其中,所述历史数据至少包括以下之一:负载指标数据,网络关键性能指标数据,关键服务质量指标数据,用户行为指示数据。The method according to claim 3, wherein the historical data includes at least one of the following: load indicator data, network key performance indicator data, key service quality indicator data, and user behavior indicator data.
  5. 根据权利要求3所述的方法,其中,所述区域全体小区数据集包括:自变量数据,因变量数据,并且至少通过以下方式获取所述区域全体小区数据集:The method according to claim 3, wherein the regional total cell data set includes: independent variable data and dependent variable data, and the regional total cell data set is acquired at least in the following manner:
    获取满足预设条件的自变量数据和因变量数据,Obtain independent variable data and dependent variable data that meet preset conditions,
    其中,所述自变量数据包括:负荷类数据,所述因变量数据与所述自变量数据存在指定函数关系。Wherein, the independent variable data includes: load type data, and the dependent variable data and the independent variable data have a specified functional relationship.
  6. 根据权利要求5所述的方法,其中,从所述区域全体小区数据集中按照指定规则选择出拥塞数据集的步骤包括:The method according to claim 5, wherein the step of selecting the congestion data set from the entire cell data set of the area according to a specified rule includes:
    根据对比检测方法对所述因变量数据与所述自变量数据进行分析;Analyze the dependent variable data and the independent variable data according to the comparison detection method;
    将对比检测次数满足预设次数的因变量数据作为拥塞指示指标数据;以及Use the dependent variable data whose comparison detection times meet the preset times as the congestion indicator data; and
    将与所述拥塞指示指标数据的关联度满足预设值的n个自变量指标数据作为所述拥塞数据集,其中,n为正整数。Take n independent variable index data whose degree of association with the congestion indicator data satisfy a preset value as the congestion data set, where n is a positive integer.
  7. 根据权利要求1-6任一项所述的方法,其中,所述突发负荷模型至少包括以下之一信息:输入数据长度,突发负荷提前量,突发负荷宽度,突发负荷等级。The method according to any one of claims 1-6, wherein the burst load model includes at least one of the following information: input data length, burst load advance, burst load width, and burst load level.
  8. 一种突发负荷的预测装置,包括:A sudden load prediction device, including:
    采集模块,用于采集指定区域的负载指标数据,其中,所述负载指标数据用于表征所述指定区域的负载情况;以及A collection module, configured to collect load index data of a specified area, wherein the load index data is used to characterize the load of the specified area; and
    预测模块,用于使用突发负荷模型对所述负载指标数据进行分析,预测突发负荷的发生情况,其中,所述突发负荷模型为使用多组数据通过机器学习训练出的。The prediction module is used to analyze the load index data using a burst load model to predict the occurrence of the burst load, wherein the burst load model is trained by machine learning using multiple sets of data.
  9. 根据权利要求8所述的装置,还包括:The apparatus according to claim 8, further comprising:
    选择模块,用于从多个突发负荷模型中选择适合所述指定区域的突发负荷模型。The selection module is used to select a burst load model suitable for the specified area from a plurality of burst load models.
  10. 一种存储介质,其上存储有计算机程序,其中,所述计算机程序被处理器运行时,使得所述处理器执行所述权利要求1至7任一项中所述的突发负荷的预测方法。A storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is caused to execute the burst load prediction method described in any one of claims 1 to 7. .
  11. 一种电子装置,包括存储器和处理器,其中,所述存储器中存储有计算机程序,所述处理器运行所述计算机程序时,执行所述权利要求1至7任一项中所述的突发负荷的预测方法。An electronic device including a memory and a processor, wherein a computer program is stored in the memory, and when the processor runs the computer program, the burst described in any one of claims 1 to 7 is executed Load forecasting method.
PCT/CN2019/128337 2018-12-29 2019-12-25 Burst load prediction method and device, storage medium and electronic device WO2020135510A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811643589.1A CN111385128B (en) 2018-12-29 2018-12-29 Method and device for predicting burst load, storage medium, and electronic device
CN201811643589.1 2018-12-29

Publications (1)

Publication Number Publication Date
WO2020135510A1 true WO2020135510A1 (en) 2020-07-02

Family

ID=71128714

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/128337 WO2020135510A1 (en) 2018-12-29 2019-12-25 Burst load prediction method and device, storage medium and electronic device

Country Status (2)

Country Link
CN (1) CN111385128B (en)
WO (1) WO2020135510A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112202845A (en) * 2020-09-10 2021-01-08 广东电网有限责任公司 Edge computing gateway load system facing distribution and utilization service, analysis method and distribution system thereof
CN113762387A (en) * 2021-09-08 2021-12-07 东北大学 Data center station multi-load prediction method based on hybrid model prediction
CN114155038A (en) * 2021-12-09 2022-03-08 国网河北省电力有限公司营销服务中心 Method for identifying user affected by epidemic situation
CN115515171A (en) * 2021-06-21 2022-12-23 中国移动通信集团湖南有限公司 Load prediction method and device of SA network and electronic equipment
CN116090388A (en) * 2022-12-21 2023-05-09 海光信息技术股份有限公司 Method for generating prediction model of internal voltage of chip, prediction method and related device
US20240171491A1 (en) * 2022-11-18 2024-05-23 Dell Products L.P. Unified Performance Metric for Identifying Data Center Utilization

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12058547B2 (en) 2020-12-30 2024-08-06 Samsung Electronics Co., Ltd. System and method for artificial intelligence (AI) driven voice over long-term evolution (VoLTE) analytics
CN113434377A (en) * 2021-06-30 2021-09-24 中国工商银行股份有限公司 Method and device for allocating graded performance capacity

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102801792A (en) * 2012-07-26 2012-11-28 华南理工大学 Statistical-prediction-based automatic cloud CDN (Content Delivery Network) resource automatic deployment method
CN104376412A (en) * 2014-11-11 2015-02-25 国家电网公司 High energy-consuming enterprise peak regulation control method used in new energy power generation mode
CN106961351A (en) * 2017-03-03 2017-07-18 南京邮电大学 Intelligent elastic telescopic method based on Docker container clusters
US20170371989A1 (en) * 2016-06-24 2017-12-28 The Boeing Company Modeling and analysis of leading edge ribs of an aircraft wing

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106912071B (en) * 2015-12-22 2020-08-04 中国移动通信集团广东有限公司 Method and device for triggering load balancing based on L TE relative load difference
TWI638579B (en) * 2017-05-08 2018-10-11 國立交通大學 Data driven management method and apparatus for base stations
CN107277844A (en) * 2017-07-25 2017-10-20 山东浪潮商用系统有限公司 A kind of communication network high load capacity cell method for early warning based on time series
CN107517481B (en) * 2017-09-21 2021-06-04 台州市吉吉知识产权运营有限公司 Base station load balancing management method and system
CN108989092B (en) * 2018-06-26 2023-01-17 广东南方通信建设有限公司 Wireless network prediction method, electronic equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102801792A (en) * 2012-07-26 2012-11-28 华南理工大学 Statistical-prediction-based automatic cloud CDN (Content Delivery Network) resource automatic deployment method
CN104376412A (en) * 2014-11-11 2015-02-25 国家电网公司 High energy-consuming enterprise peak regulation control method used in new energy power generation mode
US20170371989A1 (en) * 2016-06-24 2017-12-28 The Boeing Company Modeling and analysis of leading edge ribs of an aircraft wing
CN106961351A (en) * 2017-03-03 2017-07-18 南京邮电大学 Intelligent elastic telescopic method based on Docker container clusters

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112202845A (en) * 2020-09-10 2021-01-08 广东电网有限责任公司 Edge computing gateway load system facing distribution and utilization service, analysis method and distribution system thereof
CN112202845B (en) * 2020-09-10 2024-01-23 广东电网有限责任公司 Distribution electricity service oriented edge computing gateway load system, analysis method and distribution system thereof
CN115515171A (en) * 2021-06-21 2022-12-23 中国移动通信集团湖南有限公司 Load prediction method and device of SA network and electronic equipment
CN115515171B (en) * 2021-06-21 2024-11-08 中国移动通信集团湖南有限公司 Load prediction method and device of SA network and electronic equipment
CN113762387A (en) * 2021-09-08 2021-12-07 东北大学 Data center station multi-load prediction method based on hybrid model prediction
CN113762387B (en) * 2021-09-08 2024-02-02 东北大学 Multi-element load prediction method for data center station based on hybrid model prediction
CN114155038A (en) * 2021-12-09 2022-03-08 国网河北省电力有限公司营销服务中心 Method for identifying user affected by epidemic situation
CN114155038B (en) * 2021-12-09 2024-05-31 国网河北省电力有限公司营销服务中心 Epidemic situation affected user identification method
US20240171491A1 (en) * 2022-11-18 2024-05-23 Dell Products L.P. Unified Performance Metric for Identifying Data Center Utilization
US12132632B2 (en) * 2022-11-18 2024-10-29 Dell Products L.P. Unified performance metric for identifying data center utilization
CN116090388A (en) * 2022-12-21 2023-05-09 海光信息技术股份有限公司 Method for generating prediction model of internal voltage of chip, prediction method and related device
CN116090388B (en) * 2022-12-21 2024-05-17 海光信息技术股份有限公司 Method for generating prediction model of internal voltage of chip, prediction method and related device

Also Published As

Publication number Publication date
CN111385128B (en) 2023-04-07
CN111385128A (en) 2020-07-07

Similar Documents

Publication Publication Date Title
WO2020135510A1 (en) Burst load prediction method and device, storage medium and electronic device
US11575583B2 (en) System and method for improving machine learning model performance in a communications network
US11159363B2 (en) Fault localization method and device
Trinh et al. Detecting mobile traffic anomalies through physical control channel fingerprinting: A deep semi-supervised approach
Wu et al. CellPAD: Detecting performance anomalies in cellular networks via regression analysis
WO2021000958A1 (en) Method and apparatus for realizing model training, and computer storage medium
US9015312B2 (en) Network management system and method for identifying and accessing quality of service issues within a communications network
JP2019521427A (en) Network Advisor Based on Artificial Intelligence
CN114269007A (en) Method, device and method storage medium for determining energy-saving strategy of base station
CN105227369B (en) Based on the mobile Apps of the mass-rent pattern analysis method to the Wi-Fi utilization of resources
WO2019196869A1 (en) Method for determining list of patrolling base stations, and patrolling apparatus
TWI684139B (en) System and method of learning-based prediction for anomalies within a base station
CN113542039A (en) Method for positioning 5G network virtualization cross-layer problem through AI algorithm
CN111163482B (en) Data processing method, device and storage medium
Chernogorov et al. Sequence-based detection of sleeping cell failures in mobile networks
Clemente et al. Traffic forecast in mobile networks: Classification system using machine learning
EP3382938A1 (en) A computer implemented method, a system and computer programs to forecast the performance of a network
Bakri et al. Channel stability prediction to optimize signaling overhead in 5G networks using machine learning
CN110647086B (en) Intelligent operation and maintenance monitoring system based on operation big data analysis
CN116643937A (en) Image analysis of data logs
CN107517474B (en) Network analysis optimization method and device
Nayak 5G Traffic Prediction with Time Series Analysis
CN115941433A (en) Network slice performance optimization guarantee method and system, storage medium and electronic equipment
Le et al. Enhanced handover clustering and forecasting models based on machine learning and big data
CN112867110B (en) Efficiency identification method and device of communication cell and electronic equipment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19906320

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 09/11/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19906320

Country of ref document: EP

Kind code of ref document: A1