CN109787846A - A kind of 5G network service quality exception monitoring and prediction technique and system - Google Patents
A kind of 5G network service quality exception monitoring and prediction technique and system Download PDFInfo
- Publication number
- CN109787846A CN109787846A CN201910235520.3A CN201910235520A CN109787846A CN 109787846 A CN109787846 A CN 109787846A CN 201910235520 A CN201910235520 A CN 201910235520A CN 109787846 A CN109787846 A CN 109787846A
- Authority
- CN
- China
- Prior art keywords
- data
- qos
- network
- service quality
- network service
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000003066 decision tree Methods 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000011664 signaling Effects 0.000 claims description 13
- 238000013500 data storage Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 2
- 238000012806 monitoring device Methods 0.000 abstract 2
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention proposes a kind of 5G network service quality exception monitoring and prediction technique and system, belongs to technical field of communication network.The system comprises: data acquisition module: for acquiring 5G network service quality data and network KPI performance monitoring data；Data processing module: for the network service quality data to be pre-processed and are marked；Qos data memory module: for storing the network service quality data after the label；Model training module: establishing Supervised machine learning model, and training obtains QoS exception monitoring device and QoS predicting abnormality device；QoS exception monitoring device: current 5G network service quality data are monitored；QoS predicting abnormality device: prediction future 5G network service quality data exception；Qos policy decision-making module: for marking and storing abnormal data, abnormal results are reported.The present invention can be the quality of service guarantee of the 5G network user, improve service quality.
Description
Technical Field
The invention belongs to the technical field of communication networks, and particularly relates to a method and a system for monitoring and predicting 5G network service quality abnormity based on a decision tree.
Background
The Quality of Service (QoS) of a network is a necessary support for guaranteeing the performance of the network, and the traditional QoS guarantees adopt a differentiated services Diffserv model or an integrated services Interserv model. The Diffserv cannot guarantee the global optimization, and the Interserv model involves complex signaling control, so that the existing network can only provide best-effort service quality but cannot provide the guarantee of the service quality.
Under the scenes of mass equipment connection, ultrahigh flow density, ultrahigh connection number density and ultrahigh mobility, a 5G network has great challenge on how to meet user service, and the traditional network service quality architecture cannot adapt to complex and dynamic 5G network application scenes.
Disclosure of Invention
In view of this, the invention provides a method and a system for monitoring and predicting the quality of service abnormality of a 5G network, which are used for monitoring the network service abnormality and improving the quality of the network service.
In a first aspect of the present invention, a method for monitoring and predicting abnormal quality of service of a 5G network is provided, where the method includes:
s1, collecting 5G network service quality data and network KPI performance monitoring data, wherein the network service quality data comprises user terminal data, access network data and core network data;
s2, preprocessing the network service quality data and marking;
s3, storing the marked network service quality data to a QoS database;
s4, constructing a supervised machine learning model by taking the marked network service quality data in the QoS database as a data set, and training the supervised machine learning model by using the data set to obtain a QoS anomaly monitor and a QoS anomaly predictor;
s5, monitoring the current 5G network service quality data in real time by adopting the QoS anomaly monitor, and sending the monitored anomaly data to a QoS strategy decision module;
s6, predicting the future 5G network service quality data abnormity by adopting the QoS abnormity predictor, and sending the predicted abnormal data to a QoS strategy decision module;
and S7, the QoS strategy decision module marks and stores the abnormal data, updates a QoS database, reports an abnormal result, makes a decision according to the abnormal data and drives the decision to be executed.
Optionally, in step S1: the user terminal data includes: hardware data and software model version of the user terminal, installed application, terminal position, moving direction, speed, consumed CPU, memory resource and alarm log; the access network data includes: base station distribution, antenna channel mode, frequency spectrum usage, physical resource virtual resource usage, air interface signaling and alarm logs; the core network data includes: user service quality agreement, network slice resource usage, core network signaling, and alarm log; the network KPI performance monitoring data comprises: network bandwidth, delay, jitter.
Optionally, the specific process of step S2 is: and cleaning and unifying the format of the collected network service quality data, and marking the network service quality data by combining the network KPI performance monitoring data, wherein the marking comprises normal and abnormal.
Optionally, in step S4, the supervised machine learning model adopts a decision tree algorithm.
Optionally, in step S6, the QoS anomaly predictor predicts future 5G network QoS data anomalies according to current 5G network QoS data and historical 5G network QoS data, where the historical 5G network QoS data is a historical network QoS data record stored in the QoS database.
Optionally, in the step S7, the marking and storing the abnormal data by the QoS policy decision module specifically includes: and automatically marking the results of the QoS anomaly monitor and the QoS anomaly predictor, storing new marking data into the QoS database, and updating network service quality data in the QoS database.
In a second aspect of the present invention, a system for monitoring and predicting quality of service anomaly in a 5G network is provided, the system comprising:
a data acquisition module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring 5G network service quality data and network KPI performance monitoring data, and the network service quality data comprises user terminal QoS data, access network QoS data and core network QoS data;
a data processing module: the system is used for preprocessing the network service quality data and marking the network service quality data;
a Qos data storage module: the system is used for storing the marked network service quality data;
a model training module: the system is used for constructing a supervised machine learning model by taking the marked network service quality data in the QoS database as a data set of the supervised machine learning model, and training the supervised machine learning model to obtain a QoS anomaly monitor and a QoS anomaly predictor
QoS anomaly monitor: the system is used for monitoring the current 5G network service quality data in real time and sending the monitored abnormal data to the QoS strategy decision module;
QoS anomaly predictor: the QoS policy decision module is used for predicting the future 5G network service quality data abnormity according to the current 5G network service quality data and the historical 5G network service quality data in the Qos data storage module and sending the predicted abnormal data to the QoS policy decision module;
a QoS policy decision module: the system is used for marking and storing the abnormal data, reporting an abnormal result, making a decision according to the abnormal data and driving the decision to execute.
Optionally, the data acquisition module specifically includes:
a user terminal data acquisition unit: the system comprises a Central Processing Unit (CPU), a memory resource and an alarm log, wherein the CPU, the memory resource and the alarm log are used for acquiring hardware data and software model versions of a user terminal, installed applications, terminal position, moving direction and speed, and consumed CPU, memory resource and alarm log;
an access network data acquisition unit: the method comprises the steps of acquiring base station distribution data, an antenna channel mode, frequency spectrum usage, physical resource virtual resource usage, air interface signaling and alarm log data;
a core network data acquisition unit: the system is used for acquiring user service quality agreement, network slice resource use, core network signaling and alarm log data;
the network KPI performance monitoring data acquisition unit: the method is used for acquiring network bandwidth, time delay and jitter data.
Optionally, the model training module constructs the supervised machine learning model by using a decision tree algorithm, the training result is a tree structure composed of nodes and branches, each non-leaf node represents an attribute in the data set, a branch of the non-leaf node is a certain value or value interval of the attribute, and each leaf node is a category in the data set and represents that the network service quality is abnormal or normal.
Optionally, the QoS policy decision module marks the abnormal results of the QoS abnormal monitor and the QoS abnormal predictor, stores new marked data into the QoS database, and updates network quality of service data in the QoS database.
The invention provides a method for monitoring and predicting the abnormal service quality of a 5G network, which comprises the following steps of collecting, storing, marking and analyzing mass QoS service quality data of a network terminal, a wireless access network and a core network:
1) the incidence relation between the historical network event and the network service quality can be reconstructed;
2) the method can monitor the current network service quality abnormity in real time, further form a network QoS management strategy, and realize the automatic scheduling of network resources through a software, virtualization and slicing network programming interface, thereby ensuring the service quality of 5G network users and improving the service quality;
3) the method can predict the possible network service quality abnormity in the future, and provides basis for network planning and service quality optimization.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the technical description of the present invention will be briefly introduced below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor.
FIG. 1 is a schematic flow chart of a method for monitoring and predicting abnormal quality of network service provided by the present invention;
fig. 2 shows the label formats of the user terminal data, the access network data, and the core network data provided by the present invention;
FIG. 3 is a schematic diagram of a network QoS anomaly monitoring and prediction decision tree according to the present invention;
fig. 4 is a schematic structural diagram of a network service quality anomaly monitoring and predicting system provided by the present invention.
Detailed Description
The invention provides a method and a system for monitoring and predicting 5G network service quality abnormity based on a decision tree.
From the machine learning model, machine learning is classified into supervised learning, unsupervised learning, and semi-supervised learning.
Under supervised learning, input data is called as 'training data', each group of training data has a definite identification or result, for example, 'junk mail' and 'non-junk mail' in a spam prevention system, a learning process is established in the supervised learning, a prediction result is compared with an actual result of the 'training data', the prediction model is continuously adjusted for dining and staying until the prediction result of the model reaches an expected accuracy, and a supervised learning algorithm comprises linear regression, a decision tree, a support vector machine and the like.
In unsupervised learning, data is not specifically labeled, and the learning model is to infer some of the internal structure of the data. Common application scenarios include association rule learning, clustering and the like, and unsupervised learning algorithms include K-means, hierarchical clustering and the like.
In the semi-supervised learning mode, where the input data is partially identified and partially not identified, such a learning model may be used to make predictions, but the model first needs to learn the intrinsic structure of the data in order to reasonably organize the data to make predictions.
The machine learning mainly depends on an algorithm, computing power and data, the training and the computing can be performed in an online mode or an offline mode after the data are obtained, the offline mode is not high in real-time performance, and the online learning and training mode is adopted in the invention in consideration of the real-time performance requirement of network service quality guarantee.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a method for monitoring and predicting quality of service anomaly of a 5G network, the method comprising:
s1, collecting 5G network service quality data and network KPI performance monitoring data, wherein the network service quality data comprises user terminal data, access network data and core network data;
the user terminal data includes: hardware data and software model version of the user terminal, installed application, terminal position, moving direction, speed, consumed CPU, memory resource and alarm log;
the access network data includes: base station distribution, antenna channel mode, frequency spectrum usage, physical resource virtual resource usage, air interface signaling and alarm logs;
the core network data includes: user service quality agreement, network slice resource usage, core network signaling, and alarm log;
the network KPI (Key Performance indication) Performance monitoring data comprises: network bandwidth, delay, jitter.
S2, preprocessing the network service quality data and marking;
and cleaning and unifying the format of the collected network service quality data, and marking the network service quality data by combining the network KPI performance monitoring data, wherein the marking comprises normal and abnormal.
Specifically, the preprocessing is to eliminate noise and correct errors of irrelevant data, process invalid values and missing values, standardize the collected data uniformly, and convert the data into a formatted format which is easy for subsequent processing. And marking the preprocessed user terminal data, access network data and core network data as normal or abnormal respectively through network KPI performance monitoring data such as network bandwidth, time delay, jitter and the like. Some KPI performance data of the network may be monitored, such as rate, delay, etc., and the collected user data, access network data, and core network data corresponding to the KPI performance data may be directly marked according to the monitored KPI performance data.
Referring to fig. 2, fig. 2 lists label formats of user terminal data, access network data, and core network data. In fig. 2, Feature1, Feature2, etc. are attributes or features of a data set, corresponding columns are attribute values or value intervals of each item, and labeled category labels have two types, Normal and abnormal. After marking, the marked network service quality data can be used for learning the marking rule and training the prediction model, and finally, the current network service quality is automatically monitored and classified according to the learned rule so as to predict the result.
S3, storing the marked network service quality data to a QoS database;
in particular, a relational database or NoSQL database or file system can be used for storage,
S4, constructing a supervised machine learning model by taking the marked network service quality data in the QoS database as a data set, and training the supervised machine learning model by using the data set to obtain a QoS anomaly monitor and a QoS anomaly predictor;
in step S4, the supervised machine learning model employs a decision tree algorithm. Algorithms that may be used also include neural networks or support vector machine algorithms, etc.
The decision tree algorithm is a supervised learning method for classification, and can deduce decision rules from the characteristics of training set data and predict the result of input data by creating a tree structure. The marked network service quality data in the QoS database is used as a data set, the data set is generally divided into a training data set and a testing data set, a decision tree is generated through the training data set, how to predict and output is learned from input data, then the generated decision tree is checked, corrected and repaired by using a testing sample set, branches influencing accuracy are cut out through preliminary rules generated in the process of generating the decision tree by data verification in the testing data set, a more accurate tree structure is generated, and finally the classification result (normal or abnormal) of a leaf node is used as a monitoring result of newly input network service quality data.
Taking C4.5 decision tree algorithm as an example, the specific process of step S4 is described:
1) and calculating the information gain rate of each attribute in the training data set, and constructing a decision tree model.
Specifically, the classification algorithm is based on the information entropy, the larger the information entropy is, the more new information carried by the representative information is, and the two data have large difference, so that the two data belong to different classes; the smaller the entropy of information, the less new information that is carried by the representative information, and the more likely the two data fall into one category. If the attribute value is continuous, the continuous attribute is discretized, and after discretization, if the attribute value of the attribute A has m discrete value intervals, the training data set S is divided into C through the attribute value of the attribute A1，C2，…，CmTotal m sub-datasets, | Cp| represents the number of samples in the p-th sub-dataset, | S | represents the total number of samples in the dataset before partitioning,
note P (C)p) As a classification subset CpThe frequency of occurrence in the sample set S, P (C)p)＝|Cpi/S, p 1,2, …, m, entropy of the sample set before splitting:
for any attribute A thereiniSuppose there are t different values of aqQ is 1,2, …, t according to AiCan divide S into S1，S2，…，StT subsets, while C can be1，C2，…，CmDividing into m x t subsets, each subset CpqIs shown in Ai＝aqA set of samples belonging to the p-th class under the condition of (1), over attribute AiEntropy of sample set after splitting:
wherein,the smaller the entropy, the higher the purity of the subset partitioning. By attribute AiThe information gain of the sample set after splitting is:
InfoGain(S,Ai)＝H(S)-H(S,Ai)
information gain InfoGain (S, A)i) Indicating the degree of uncertainty degradation after partitioning.
Attribute AiSplit information amount of (2):
continue splitting to create new nodes, via attribute AiThe information gain ratio of the sample set S after splitting is:
and C4.5, selecting the attribute of the maximum information gain rate by the decision tree algorithm to establish an initial decision tree from top to bottom, pruning the initial decision tree by using the test data set, removing abnormal branches, improving classification accuracy and obtaining a final decision tree model.
Referring to fig. 3, a schematic diagram of an anomaly detection and prediction decision tree is shown, wherein the decision tree is a tree structure of class flow chart composed of nodes and branches, and the nodes are divided into leaf nodes and non-leaf nodes. The top level of the tree is the first non-leaf node, the root node, which is the starting position of the decision tree. Each non-leaf node represents a certain attribute in the dataset, whose branches are a certain value or interval of values of said attribute. Each leaf node is a category in the data set, i.e. indicating that the network service quality is abnormal or normal.
2) The constructed decision tree module can be used as a QoS abnormity monitor, and QoS abnormity can be monitored by inputting the current 5G network service quality into the decision tree model; and further training to obtain a QoS anomaly predictor according to the current 5G network service quality data and the historical 5G network service quality data in the Qos data storage module, and predicting the anomaly of the future 5G network service quality data.
S5, monitoring the current 5G network service quality data in real time by adopting the QoS anomaly monitor, and sending the monitored anomaly data to a QoS strategy decision module;
s6, predicting the future 5G network service quality data abnormity by adopting the QoS abnormity predictor, and sending the predicted abnormal data to a QoS strategy decision module;
in step S6, the QoS anomaly predictor predicts future 5G network QoS data anomalies according to current 5G network QoS data and historical 5G network QoS data, where the historical 5G network QoS data is a historical network QoS data record stored in the QoS database.
And S7, the QoS strategy decision module marks and stores the abnormal data, updates a QoS database, reports an abnormal result, makes a decision according to the abnormal data and drives the decision to be executed.
In step S7, the marking and storing of the abnormal data by the QoS policy decision module specifically includes:
and automatically marking the results of the QoS anomaly monitor and the QoS anomaly predictor, storing new marked data into the QoS database, storing the new marked data as historical 5G network service quality data, and updating the network service quality data in the QoS database. Therefore, the incidence relation between the historical network events and the network service quality is established, and a training basis is provided for the next training and prediction. And when new network service quality data is input after the QoS database is updated, taking the updated QoS database as a new data set, and training and predicting the abnormity in the input data.
The QoS policy decision module also makes a decision according to the monitored or predicted abnormal result, for example, if the bandwidth is not sufficient, the bandwidth is increased, the time delay is too long, the queue queuing processing is accelerated, and the decision execution is driven.
Referring to fig. 4, the present invention further provides a system for monitoring and predicting quality of service anomaly of a 5G network, where the system includes:
the data acquisition module 410: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring 5G network service quality data and network KPI performance monitoring data, and the network service quality data comprises user terminal QoS data, access network QoS data and core network QoS data;
the data processing module 420: the system is used for preprocessing the network service quality data and marking the network service quality data;
qos data storage module 430: the system is used for storing the marked network service quality data;
the model training module 440: the system is used for constructing a supervised machine learning model by taking the marked network service quality data in the QoS database as a data set of the supervised machine learning model, and training the supervised machine learning model to obtain a QoS anomaly monitor and a QoS anomaly predictor
QoS anomaly monitor 450: the system is used for monitoring the current 5G network service quality data in real time and sending the monitored abnormal data to the QoS strategy decision module;
QoS anomaly predictor 460: the QoS policy decision module is used for predicting the future 5G network service quality data abnormity according to the current 5G network service quality data and the historical 5G network service quality data in the Qos data storage module and sending the predicted abnormal data to the QoS policy decision module;
QoS policy decision module 470: the system is used for marking and storing the abnormal data, reporting an abnormal result, making a decision according to the abnormal data and driving the decision to execute.
The data acquisition module 410 specifically includes:
a user terminal data acquisition unit: the system comprises a Central Processing Unit (CPU), a memory resource and an alarm log, wherein the CPU, the memory resource and the alarm log are used for acquiring hardware data and software model versions of a user terminal, installed applications, terminal position, moving direction and speed, and consumed CPU, memory resource and alarm log;
an access network data acquisition unit: the method comprises the steps of acquiring base station distribution data, an antenna channel mode, frequency spectrum usage, physical resource virtual resource usage, air interface signaling and alarm log data;
a core network data acquisition unit: the system is used for acquiring user service quality agreement, network slice resource use, core network signaling and alarm log data;
the network KPI performance monitoring data acquisition unit: the method comprises the steps of obtaining network bandwidth, time delay and jitter data;
the model training module 440 adopts a decision tree algorithm to construct the supervised machine learning model, the training result is a tree structure composed of nodes and branches, each non-leaf node represents an attribute in the data set, the branch is a certain value or value interval of the attribute, and each leaf node represents a category in the data set, which represents that the network service quality is abnormal or normal.
The QoS policy decision module 470 marks the abnormal results of the QoS abnormal monitor and the QoS abnormal predictor, stores the new marked data into the QoS database, and updates the network quality of service data in the QoS database.
The data acquisition module 410, the data processing module 420, the model training module 440, the QoS anomaly monitor 450, the QoS anomaly predictor 460, and the QoS policy decision module 470 together form a 5G network QoS machine learning engine, and according to the acquired user terminal QoS data, access network QoS data, core network QoS data, and network KPI performance monitoring data, the 5G network QoS machine learning engine is used to automatically detect and predict network QoS anomalies, so as to further form a network QoS management policy, which provides a basis for the quality of service guarantee of 5G network users, as well as for network planning and network quality of service optimization.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art would appreciate that the modules, elements, and/or method steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for monitoring and predicting abnormal service quality of a 5G network is characterized by comprising the following steps:
s1, collecting 5G network service quality data and network KPI performance monitoring data, wherein the network service quality data comprises user terminal data, access network data and core network data;
s2, preprocessing the network service quality data and marking;
s3, storing the marked network service quality data to a QoS database;
s4, constructing a supervised machine learning model by taking the marked network service quality data in the QoS database as a data set, and training the supervised machine learning model by using the data set to obtain a QoS anomaly monitor and a QoS anomaly predictor;
s5, monitoring the current 5G network service quality data in real time by adopting the QoS anomaly monitor, and sending the monitored anomaly data to a QoS strategy decision module;
s6, predicting the future 5G network service quality data abnormity by adopting the QoS abnormity predictor, and sending the predicted abnormal data to a QoS strategy decision module;
and S7, the QoS strategy decision module marks and stores the abnormal data, updates a QoS database, reports an abnormal result, makes a decision according to the abnormal data and drives the decision to be executed.
2. The method for monitoring and predicting quality of service anomaly in 5G networks according to claim 1, wherein in step S1:
the user terminal data includes: hardware data and software model version of the user terminal, installed application, terminal position, moving direction, speed, consumed CPU, memory resource and alarm log;
the access network data includes: base station distribution, antenna channel mode, frequency spectrum usage, physical resource virtual resource usage, air interface signaling and alarm logs;
the core network data includes: user service quality agreement, network slice resource usage, core network signaling, and alarm log;
the network KPI performance monitoring data comprises: network bandwidth, delay, jitter.
3. The method for monitoring and predicting abnormal quality of service of 5G network according to claim 1, wherein the specific process of the step S2 is as follows:
and cleaning and unifying the format of the collected network service quality data, and marking the network service quality data by combining the network KPI performance monitoring data, wherein the marking comprises normal and abnormal.
4. The method for monitoring and predicting quality of service anomalies of a 5G network as claimed in claim 1 wherein, in said step S4, said supervised machine learning model employs a decision tree algorithm.
5. The method for monitoring and predicting quality of service anomaly of 5G network according to claim 1, wherein in step S6, the QoS anomaly predictor predicts future 5G network quality of service data anomaly according to current 5G network quality of service data and historical 5G network quality of service data, wherein the historical 5G network quality of service data is a historical network quality of service data record stored in the QoS database.
6. The method for monitoring and predicting quality of service (QoS) anomalies in a 5G network according to claim 1, wherein in the step S7, the QoS policy decision module marks and stores the anomaly data specifically as follows:
and automatically marking the results of the QoS anomaly monitor and the QoS anomaly predictor, storing new marking data into the QoS database, and updating network service quality data in the QoS database.
7. A 5G network quality of service anomaly monitoring and prediction system, the system comprising:
a data acquisition module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring 5G network service quality data and network KPI performance monitoring data, and the network service quality data comprises user terminal QoS data, access network QoS data and core network QoS data;
a data processing module: the system is used for preprocessing the network service quality data and marking the network service quality data;
a Qos data storage module: the system is used for storing the marked network service quality data;
a model training module: the system is used for constructing a supervised machine learning model by taking the marked network service quality data in the QoS database as a data set of the supervised machine learning model, and training the supervised machine learning model to obtain a QoS anomaly monitor and a QoS anomaly predictor
QoS anomaly monitor: the system is used for monitoring the current 5G network service quality data in real time and sending the monitored abnormal data to the QoS strategy decision module;
QoS anomaly predictor: the QoS policy decision module is used for predicting the future 5G network service quality data abnormity according to the current 5G network service quality data and the historical 5G network service quality data in the Qos data storage module and sending the predicted abnormal data to the QoS policy decision module;
a QoS policy decision module: the system is used for marking and storing the abnormal data, reporting an abnormal result, making a decision according to the abnormal data and driving the decision to execute.
8. The system for monitoring and predicting quality of service anomalies of a 5G network according to claim 7, wherein the data acquisition module specifically includes:
a user terminal data acquisition unit: the system comprises a Central Processing Unit (CPU), a memory resource and an alarm log, wherein the CPU, the memory resource and the alarm log are used for acquiring hardware data and software model versions of a user terminal, installed applications, terminal position, moving direction and speed, and consumed CPU, memory resource and alarm log;
an access network data acquisition unit: the method comprises the steps of acquiring base station distribution data, an antenna channel mode, frequency spectrum usage, physical resource virtual resource usage, air interface signaling and alarm log data;
a core network data acquisition unit: the system is used for acquiring user service quality agreement, network slice resource use, core network signaling and alarm log data;
the network KPI performance monitoring data acquisition unit: the method is used for acquiring network bandwidth, time delay and jitter data.
9. The system of claim 7, wherein the model training module employs a decision tree algorithm to construct the supervised machine learning model, the result of the training is a tree structure consisting of nodes and branches, each non-leaf node represents an attribute in the data set, a branch is a value or a range of values of the attribute, and each leaf node represents a category in the data set, and represents network quality of service anomaly or normality.
10. The system of claim 7, wherein the QoS policy decision module marks the QoS anomaly monitor and the QoS anomaly predictor, stores the new marked data in the QoS database, and updates the QoS data in the QoS database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235520.3A CN109787846A (en) | 2019-03-27 | 2019-03-27 | A kind of 5G network service quality exception monitoring and prediction technique and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235520.3A CN109787846A (en) | 2019-03-27 | 2019-03-27 | A kind of 5G network service quality exception monitoring and prediction technique and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109787846A true CN109787846A (en) | 2019-05-21 |
Family
ID=66491317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235520.3A Pending CN109787846A (en) | 2019-03-27 | 2019-03-27 | A kind of 5G network service quality exception monitoring and prediction technique and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109787846A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111581045A (en) * | 2020-03-18 | 2020-08-25 | 平安科技（深圳）有限公司 | Database anomaly monitoring method and device, computer device and storage medium |
| CN112312427A (en) * | 2019-07-31 | 2021-02-02 | 中国移动通信集团广东有限公司 | Method for optimizing network quality and electronic equipment |
| CN113472590A (en) * | 2021-07-14 | 2021-10-01 | 南京邮电大学 | QoS configuration method based on machine learning in DDS |
| CN113541984A (en) * | 2020-04-14 | 2021-10-22 | 中国移动通信集团浙江有限公司 | Method, device and equipment for predicting experience of network slicing service |
| WO2021213247A1 (en) * | 2020-04-24 | 2021-10-28 | 华为技术有限公司 | Anomaly detection method and device |
| CN113747480A (en) * | 2020-05-28 | 2021-12-03 | 中国移动通信集团浙江有限公司 | Processing method and device for 5G slice fault and computing equipment |
| CN113825161A (en) * | 2020-06-18 | 2021-12-21 | 中国移动通信集团浙江有限公司 | 5G slice abnormity detection method and device based on deep self-coding neural network |
| CN114143163A (en) * | 2020-08-14 | 2022-03-04 | 中国移动通信集团浙江有限公司 | Slice false alarm identification method and device based on graph attention network |
| CN114424601A (en) * | 2019-10-28 | 2022-04-29 | 谷歌有限责任公司 | End-to-end machine learning for wireless networks |
| CN114615051A (en) * | 2022-03-09 | 2022-06-10 | 黄河水利职业技术学院 | Network security detection method and system |
| CN114757249A (en) * | 2020-12-28 | 2022-07-15 | 北京神州泰岳软件股份有限公司 | Quality evaluation method and device, training method and device and electronic equipment |
| CN115996168A (en) * | 2021-10-20 | 2023-04-21 | 慧与发展有限责任合伙企业 | Supervised quality of service change derivation |
| CN116233871A (en) * | 2023-01-17 | 2023-06-06 | 广州爱浦路网络技术有限公司 | XR service enhancement method, computer device and storage medium |
| CN116302009A (en) * | 2023-05-19 | 2023-06-23 | 微网优联科技(成都)有限公司 | Software updating method and device based on wireless router |
| CN116528274A (en) * | 2023-07-05 | 2023-08-01 | 腾讯科技（深圳）有限公司 | Network quality regulation and control method and related equipment |
| CN118509527A (en) * | 2024-07-18 | 2024-08-16 | 中国科学院信息工程研究所 | Abnormality detection method and system for multi-dimensional KPI (key performance indicator) time sequence of 5G core network |
| CN118524413A (en) * | 2024-07-23 | 2024-08-20 | 北京华迅通信技术有限公司 | Big data-based 5G communication network operation and maintenance platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8615575B2 (en) * | 2008-10-16 | 2013-12-24 | At&T Intellectual Property I, L.P. | Devices, methods, and computer-readable media for providing quality of service optimization via policy-based rearrangements |
| CN105119734A (en) * | 2015-07-15 | 2015-12-02 | 中国人民解放军防空兵学院 | Full network anomaly detection positioning method based on robust multivariate probability calibration model |
| CN106027288A (en) * | 2016-05-10 | 2016-10-12 | 华北电力大学 | Communication traffic prediction method for distribution line information monitoring service |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN109343995A (en) * | 2018-10-25 | 2019-02-15 | 金税信息技术服务股份有限公司 | Intelligent O&M analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robot |
-
2019
- 2019-03-27 CN CN201910235520.3A patent/CN109787846A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8615575B2 (en) * | 2008-10-16 | 2013-12-24 | At&T Intellectual Property I, L.P. | Devices, methods, and computer-readable media for providing quality of service optimization via policy-based rearrangements |
| CN105119734A (en) * | 2015-07-15 | 2015-12-02 | 中国人民解放军防空兵学院 | Full network anomaly detection positioning method based on robust multivariate probability calibration model |
| CN106027288A (en) * | 2016-05-10 | 2016-10-12 | 华北电力大学 | Communication traffic prediction method for distribution line information monitoring service |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN109343995A (en) * | 2018-10-25 | 2019-02-15 | 金税信息技术服务股份有限公司 | Intelligent O&M analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robot |
Non-Patent Citations (2)
| Title |
|---|
| GUOSHENG ZHU，JUN ZANZ, YANG YANG，AND XIAOYUN QI: "A Supervised Learning Based QoS Assurance Architecture for 5G Networks", 《IEEE ACCESS》 * |
| 陈胜等: "基于C5.0决策树的NAT设备检测方法", 《计算机科学》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112312427A (en) * | 2019-07-31 | 2021-02-02 | 中国移动通信集团广东有限公司 | Method for optimizing network quality and electronic equipment |
| CN112312427B (en) * | 2019-07-31 | 2023-09-05 | 中国移动通信集团广东有限公司 | Method for optimizing network quality and electronic equipment |
| CN114424601A (en) * | 2019-10-28 | 2022-04-29 | 谷歌有限责任公司 | End-to-end machine learning for wireless networks |
| CN111581045A (en) * | 2020-03-18 | 2020-08-25 | 平安科技（深圳）有限公司 | Database anomaly monitoring method and device, computer device and storage medium |
| CN111581045B (en) * | 2020-03-18 | 2024-05-28 | 平安科技（深圳）有限公司 | Database anomaly monitoring method, device, computer device and storage medium |
| CN113541984A (en) * | 2020-04-14 | 2021-10-22 | 中国移动通信集团浙江有限公司 | Method, device and equipment for predicting experience of network slicing service |
| WO2021213247A1 (en) * | 2020-04-24 | 2021-10-28 | 华为技术有限公司 | Anomaly detection method and device |
| CN113747480A (en) * | 2020-05-28 | 2021-12-03 | 中国移动通信集团浙江有限公司 | Processing method and device for 5G slice fault and computing equipment |
| CN113747480B (en) * | 2020-05-28 | 2024-05-07 | 中国移动通信集团浙江有限公司 | Processing method and device for 5G slice faults and computing equipment |
| CN113825161A (en) * | 2020-06-18 | 2021-12-21 | 中国移动通信集团浙江有限公司 | 5G slice abnormity detection method and device based on deep self-coding neural network |
| CN113825161B (en) * | 2020-06-18 | 2023-08-04 | 中国移动通信集团浙江有限公司 | 5G slice anomaly detection method and device based on depth self-coding neural network |
| CN114143163A (en) * | 2020-08-14 | 2022-03-04 | 中国移动通信集团浙江有限公司 | Slice false alarm identification method and device based on graph attention network |
| CN114143163B (en) * | 2020-08-14 | 2023-11-14 | 中国移动通信集团浙江有限公司 | Slice false alarm identification method and device based on graph attention network |
| CN114757249A (en) * | 2020-12-28 | 2022-07-15 | 北京神州泰岳软件股份有限公司 | Quality evaluation method and device, training method and device and electronic equipment |
| CN113472590A (en) * | 2021-07-14 | 2021-10-01 | 南京邮电大学 | QoS configuration method based on machine learning in DDS |
| CN115996168A (en) * | 2021-10-20 | 2023-04-21 | 慧与发展有限责任合伙企业 | Supervised quality of service change derivation |
| CN115996168B (en) * | 2021-10-20 | 2024-04-05 | 慧与发展有限责任合伙企业 | Supervised quality of service change derivation |
| CN114615051A (en) * | 2022-03-09 | 2022-06-10 | 黄河水利职业技术学院 | Network security detection method and system |
| CN116233871A (en) * | 2023-01-17 | 2023-06-06 | 广州爱浦路网络技术有限公司 | XR service enhancement method, computer device and storage medium |
| CN116233871B (en) * | 2023-01-17 | 2023-12-15 | 广州爱浦路网络技术有限公司 | XR service enhancement method, computer device and storage medium |
| CN116302009B (en) * | 2023-05-19 | 2023-08-08 | 微网优联科技(成都)有限公司 | Software updating method and device based on wireless router |
| CN116302009A (en) * | 2023-05-19 | 2023-06-23 | 微网优联科技(成都)有限公司 | Software updating method and device based on wireless router |
| CN116528274B (en) * | 2023-07-05 | 2023-09-22 | 腾讯科技（深圳）有限公司 | Network quality regulation and control method and related equipment |
| CN116528274A (en) * | 2023-07-05 | 2023-08-01 | 腾讯科技（深圳）有限公司 | Network quality regulation and control method and related equipment |
| CN118509527A (en) * | 2024-07-18 | 2024-08-16 | 中国科学院信息工程研究所 | Abnormality detection method and system for multi-dimensional KPI (key performance indicator) time sequence of 5G core network |
| CN118509527B (en) * | 2024-07-18 | 2024-09-24 | 中国科学院信息工程研究所 | Abnormality detection method and system for multi-dimensional KPI (key performance indicator) time sequence of 5G core network |
| CN118524413A (en) * | 2024-07-23 | 2024-08-20 | 北京华迅通信技术有限公司 | Big data-based 5G communication network operation and maintenance platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109787846A (en) | A kind of 5G network service quality exception monitoring and prediction technique and system | |
| US20220121994A1 (en) | Method and apparatus for implementing model training, and computer storage medium | |
| KR101984730B1 (en) | Automatic predicting system for server failure and automatic predicting method for server failure | |
| WO2021052394A1 (en) | Model training method, apparatus, and system | |
| CN111506478A (en) | Method for realizing alarm management control based on artificial intelligence | |
| CN111242171B (en) | Model training and diagnosis prediction method and device for network faults and electronic equipment | |
| CN110335168B (en) | Method and system for optimizing power utilization information acquisition terminal fault prediction model based on GRU | |
| US20220179884A1 (en) | Label Determining Method, Apparatus, and System | |
| US20220284352A1 (en) | Model update system, model update method, and related device | |
| CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN110297207A (en) | Method for diagnosing faults, system and the electronic device of intelligent electric meter | |
| CN105471647A (en) | Power communication network fault positioning method | |
| CN117041312A (en) | Enterprise-level information technology monitoring system based on Internet of things | |
| US11197175B2 (en) | Forcasting time series data | |
| CN117792864A (en) | Alarm processing method and device, storage medium and electronic device | |
| CN116522213A (en) | Service state level classification and classification model training method and electronic equipment | |
| CN113839799B (en) | Alarm association rule mining method and device | |
| Mijumbi et al. | MAYOR: machine learning and analytics for automated operations and recovery | |
| JP2022037107A (en) | Failure analysis device, failure analysis method, and failure analysis program | |
| Jerome et al. | Anomaly detection and classification using a metric for determining the significance of failures: Case study: mobile network management data from LTE network | |
| CN118820910B (en) | Heterogeneous network security big data management method and system | |
| Hairuman et al. | Evaluation of machine learning techniques for anomaly detection on hourly basis kpi | |
| Nguyen | Anomaly detection in self-organizing network | |
| CN117354251A (en) | Automatic extraction method for electric power Internet of things terminal characteristics | |
| CN114116417A (en) | Training method of capacity prediction model, capacity prediction method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |