CN108063676A - Communication network failure method for early warning and device - Google Patents
Communication network failure method for early warning and device Download PDFInfo
- Publication number
- CN108063676A CN108063676A CN201610983540.5A CN201610983540A CN108063676A CN 108063676 A CN108063676 A CN 108063676A CN 201610983540 A CN201610983540 A CN 201610983540A CN 108063676 A CN108063676 A CN 108063676A
- Authority
- CN
- China
- Prior art keywords
- communication network
- data
- performance index
- early warning
- network performance
- 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
- 238000004891 communication Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000009467 reduction Effects 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000000513 principal component analysis Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 37
- 238000010219 correlation analysis Methods 0.000 claims description 18
- 238000012847 principal component analysis method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 10
- 230000014509 gene expression Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 16
- 239000011159 matrix material Substances 0.000 description 15
- 238000012423 maintenance Methods 0.000 description 9
- 238000012098 association analyses Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005520 cutting process Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 6
- 238000010295 mobile communication Methods 0.000 description 6
- 230000007774 longterm Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000011541 reaction mixture Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention provides a kind of communication network failure method for early warning.This method, including：Collect the network performance index data and fault condition data of communication network end access device；Dimensionality reduction is carried out to network performance index data by Principal Component Analysis；Network performance index data after dimensionality reduction and fault condition data are associated by analysis by NB Algorithm and obtain communication network failure Early-warning Model；And the Parameters variation indication signal of communication network end access device is received, judge whether to need to collect the network performance index data of communication network end access device again according to Parameters variation indication signal and fault condition data are iterated update to the communication network failure Early-warning Model of acquisition.The present invention also provides a kind of communication network failure prior-warning devices.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a communication network fault early warning method and device.
Background
At present, the communication industry is rapidly developing towards a high-speed mobile communication system, and the operation state of the wireless base station as the terminal access equipment of the mobile communication network not only affects the service capability of the information communication network, but also is directly related to the customer service quality and the customer satisfaction. The failure of the wireless base station to quit service, which is a serious failure affecting the quality of network service, is always a technical difficulty in monitoring the focus of the network and in operation and maintenance of the network, and the failure will directly cause the communication signal within the coverage area of the base station to be seriously weakened or interrupted, thereby seriously affecting the normal communication service of the user.
Disclosure of Invention
The embodiment of the invention provides a communication network fault early warning method and device, which can enable the fault early warning result to be higher in accuracy, reliability and real-time performance.
In one aspect, a method for early warning of communication network faults is provided, which includes: collecting network performance index data and fault condition data of the communication network terminal access equipment; performing dimensionality reduction on the network performance index data by a principal component analysis method; performing correlation analysis on the network performance index data subjected to dimensionality reduction and fault condition data through a naive Bayesian algorithm to obtain a communication network fault early warning model; and receiving a parameter change indication signal of the communication network terminal access equipment, and judging whether network performance index data and fault condition data of the communication network terminal access equipment need to be collected again according to the parameter change indication signal to iteratively update the obtained communication network fault early warning model.
In another aspect, a communication network fault early warning apparatus is provided, including: the device comprises a data collection module, a dimension reduction module, an association analysis module and an iteration updating module. The data collection module is configured to collect network performance indicator data and fault condition data for an end access device of a communication network. The dimensionality reduction module is configured to reduce the dimensionality of the network performance indicator data through a principal component analysis method. The correlation analysis module is configured to perform correlation analysis on the network performance index data subjected to dimensionality reduction and fault condition data through a naive Bayesian algorithm to obtain a communication network fault early warning model. The iteration updating module is configured to receive a parameter change indication signal of the communication network terminal access device, and judge whether to collect network performance index data and fault condition data of the communication network terminal access device again according to the parameter change indication signal to perform iteration updating on the obtained communication network fault early warning model.
In still another aspect, a communication network fault early warning device is provided, including: memory, processor, input device, output device, I/O interface, and bus. The memory is for storing computer executable instructions; the processor is used for executing the program stored in the memory, and the program enables the processor to execute the communication network fault early warning method; a bus for passing information between the processor, memory, input devices, output devices, and I/O interfaces.
The communication network fault early warning method and the communication network fault early warning device provided by the embodiment of the invention adopt a mode of combining naive Bayes and a principal component analysis method on the method of associating fault data and performance indexes, have the advantages of higher tolerance to missing data and being more suitable for application scenes with low data quality in the field of mobile communication maintenance, and can automatically trigger the early warning system to re-analyze when the parameters of base station equipment change due to the fact that whether the data needs to be re-collected for iterative updating processing is judged according to the parameter change indication signal, so that the accuracy, reliability and real-time performance of the fault early warning result are higher.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are schematic and should not be construed as limiting the invention in any way, and in which:
fig. 1 shows a flow diagram of a communication network fault early warning method according to an embodiment;
fig. 2 is a schematic diagram illustrating an application scenario of a communication network fault early warning method according to an embodiment of the present invention;
FIG. 3 illustrates a flow diagram of a communication network fault warning method for testing according to an embodiment of the present invention;
fig. 4 is a block diagram illustrating a communication network failure warning apparatus according to an embodiment of the present invention;
fig. 5 is a block diagram illustrating an exemplary hardware architecture of a computing device capable of implementing at least a portion of a communication network fault early warning apparatus and a communication network fault early warning method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
Features and exemplary embodiments of various aspects of the present invention will be described in detail below. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention. The present invention is in no way limited to any specific configuration and algorithm set forth below, but rather covers any modification, replacement or improvement of elements, components or algorithms without departing from the spirit of the invention. In the drawings and the following description, well-known structures and techniques are not shown in order to avoid unnecessarily obscuring the present invention.
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. In the drawings, the thickness of regions and layers may be exaggerated for clarity. The same reference numerals denote the same or similar structures in the drawings, and thus detailed descriptions thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring the main technical ideas of the present invention, it is noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Some existing early warning methods for communication network fault early warning models established by adopting a moving average method sequentially calculate an average value containing a certain number of items according to the gradual transition of a time sequence, so that the long-term early warning trend is reflected, but the early warning methods are single and cannot eliminate the influence of special conditions on early warning, and the accuracy is reduced because the method sequentially calculates the average value containing the certain number of items according to the time sequence and cannot accurately early warn information of working days and non-working days respectively.
Some linear regression classification methods are used as data analysis methods, but the method has low tolerance to missing data, is not suitable for fault early warning with relatively low data quality in the field of mobile communication maintenance, and also can cause the problem of low accuracy.
In view of the above, the embodiments of the present invention provide a novel communication network fault early warning method and apparatus. The following describes a communication network fault early warning method and apparatus according to an embodiment of the present invention in detail with reference to the accompanying drawings.
Fig. 1 shows a flowchart of a communication network fault early warning method according to an embodiment, the communication network fault early warning method includes: s110, collecting network performance index data and fault condition data of the communication network terminal access equipment; s120, performing dimensionality reduction on the network performance index data through a principal component analysis method; s130, performing correlation analysis on the network performance index data subjected to dimensionality reduction and fault condition data through a naive Bayes algorithm to obtain a communication network fault early warning model; and S140, receiving a parameter change indication signal of the communication network terminal access equipment, and judging whether to collect network performance index data and fault condition data of the communication network terminal access equipment again according to the parameter change indication signal to iteratively update the obtained communication network fault early warning model.
The communication network end access device described in any of steps S110 to S140 may be a base station, and it should be understood that the base station device is a radio transceiver station for information transfer between a mobile telephone terminal and a mobile communication switching center in a certain radio coverage area. The network performance index data can be data representing the performance of the base station, such as the number of received paging records, the number of lost downlink packets of a cell, the number of times of switching-out cancellation of S1 between eNBs and the like, wherein the fault condition data can be understood as fault condition data at the moment corresponding to the network performance index data, and the data can be used as a data basis associated with the corresponding performance index data when a communication network fault early warning model is obtained by performing association analysis on the reduced network performance index data and the fault condition data through a naive Bayesian algorithm; the Principal Component Analysis (PCA) is a statistical method that can convert a group of variables that may have correlation into a group of linearly uncorrelated variables by orthogonal transformation, and the group of transformed variables is called the Principal component. The communication network fault early warning method adopts a mode of combining naive Bayes and a principal component analysis method on the basis of a method for correlating fault data and performance indexes, has higher tolerance on missing data, is more suitable for application scenes with low data quality in the field of mobile communication maintenance, and can be used for automatically triggering an early warning system to reanalyze when parameters of base station equipment are updated and changed because whether data needs to be recollected for iterative updating processing is judged according to the set change condition, so that the accuracy, reliability and real-time performance of a fault early warning result are higher.
In one example, S120 may include: s121, constructing an index vector for the network performance index data of the network terminal access equipment to form a full sample matrix; s122, carrying out standardized transformation on the sample array elements to obtain a standardized matrix, and calculating a correlation coefficient matrix; s123, solving a characteristic equation of the sample correlation matrix to obtain a characteristic root, and determining a principal component expression; and S124, converting the standardized network performance index data variable of the network terminal access equipment into a principal component expression.
In one example, the principal component expressions may be further weighted and summed to obtain a value combination of the network performance index data of the final network end access device, so that the value combination of the network performance index data of the final network end access device provides a data base for performing correlation analysis on the dimensionality-reduced network performance index data and the fault condition data through a naive bayes algorithm in S130.
Fig. 2 is a schematic view of an application scenario of a communication network fault early warning method according to an embodiment of the present invention. The Operation and Maintenance Center (abbreviated as OMC) may be understood as an Operation and Maintenance Center of a wireless subsystem, and a software operating system used by an equipment manufacturer or a Maintenance worker to manage, configure, and the like the base station equipment. The network optimization performance management system can be understood as a unified real-time acquisition management system for performance indexes of base station equipment. The centralized fault management system is understood to receive status data information (e.g., device performance data, device alarm message, etc.) generated by the base station device through the OMC, and the system further has functions of alarm management, dispatching of fault work orders, etc. The engineering reservation system can be understood as that when the engineering is cut and connected, for example, the operations such as upgrading software and hardware of equipment, processing faults and the like, a large number of equipment alarm messages are generated, the alarm messages form a large number of fault work orders through the OMC and the centralized fault management system and are distributed to maintenance personnel, the work orders are not required to be distributed actually due to the equipment maintenance, and the engineering reservation system is a limiting link existing in the process of converting the alarm to the work orders, namely: and if the base station equipment already performs reservation operation in the project reservation system, not dispatching the fault work order until the project cutting reservation time is finished. The communication network fault early warning device is configured to perform communication fault early warning by using the communication fault early warning method in fig. 1. In one embodiment, in the method for early warning a communication network fault, S140 receives a parameter change indication signal of a communication network end access device, and determines whether it is necessary to collect network performance index data and fault condition data of the communication network end access device again according to the parameter change indication signal to iteratively update an obtained communication network fault early warning model. The parameter change indication signal may include at least one of an operation state change indication signal of the device, an alarm indication signal of the device, and a configuration parameter adjustment indication signal of the device. The equipment operation state change can be understood as a change process of a normal operation state, an engineering cutting state and a normal operation state, when a base station equipment maintenance worker sets a certain normally operated base station equipment state in an engineering reservation system as an engineering cutting state, and configures the engineering cutting time from A to B, the base station equipment state is automatically converted from the engineering cutting state to the normal operation state when the time exceeds B (namely, the base station equipment state realizes the process of the normal operation state, the engineering cutting state and the normal operation state), an operation state change indication signal of the equipment generated by the engineering reservation system is sent to a communication network fault early warning device, and the communication network fault early warning device can acquire performance index data after the normal operation state again for long-term early warning of the base station fault. The alarm condition of the equipment can be understood as the process of 'out-of-service alarm generation-out-of-service alarm elimination', when the base station equipment generates out-of-service alarm due to fault in the operation process (the message is transmitted to the centralized fault management system through the OMC), the equipment is indicated to be in a down state, when the base station equipment is recovered to be normal, the out-of-service alarm is automatically eliminated (namely, the equipment alarm 'out-of-service alarm generation-out-of-service alarm elimination'), when the process is generated and finished, the centralized fault management system transmits an alarm indication signal of the equipment to the communication network fault early warning device, and the communication network fault early warning device can re-collect performance index data in the normal operation state for long-term early warning of the out-of-service of the base station. The configuration parameter adjustment condition of the equipment comprises the condition that the configuration parameters of the equipment are manually and/or systematically adjusted and changed, when a base station equipment maintenance worker operates the equipment through an OMC, the equipment state is converted from a normal operation state into an engineering test state, when the operation state of the equipment is converted or the equipment parameters are adjusted in an OMC operation log record, the OMC sends an equipment configuration parameter change message to a centralized fault management system, the centralized fault management system sends a configuration parameter adjustment indication signal of the equipment to a communication network fault early warning device, and the communication network fault early warning device can reacquire performance index data in the normal operation state for long-term early warning of the service quit of the base station. And acquiring the network performance index data and the fault condition data of the equipment again by acquiring the parameter change of the equipment under the condition or directly receiving the indication given by the equipment or manpower when the condition occurs, wherein the historical network performance index data and the fault condition data of the equipment are still used as reference data sources, and the obtained communication network fault early warning model is subjected to iterative updating so as to ensure the reliability and the real-time performance of the data of each link in the fallback fault early warning analysis.
In an embodiment, the communication network fault early warning method may further include cleaning and/or averaging the network performance index data before performing dimension reduction on the network performance index data through a principal component analysis method in S120. The data cleaning can be to remove abnormal data, such as data with zero or null value; the averaging processing can be understood as that, for example, averaging calculation is performed on the same dimension index of the same base station according to working days and non-working days, so that information of working days and non-working days can be accurately pre-warned respectively, and accuracy of pre-warning results is improved. In an example, before performing the dimensionality reduction on the network performance indicator data by the principal component analysis method, the method may further include performing cluster analysis on the network performance indicator data, so as to perform network element classification on the communication network terminal access device, and further obtain a cluster group of the network performance indicator data. The cluster analysis is a process of classifying data into different classes or clusters, so that objects in the same cluster have great similarity, and objects in different clusters have great dissimilarity. Data are collected for classification on the basis of similarity, the distance of the intra-cluster network element performance index is small, and the distance of the inter-cluster network element performance index is large. In the network element classification process, the network equipment classification based on the equipment performance index self-characteristics avoids analysis interference caused by the difference between service division of the communication network terminal access equipment and actual operation performance indexes of the communication network terminal access equipment, and realizes differential classification based on the network element performance index characteristics. In an example, before performing dimension reduction on the network performance index data through a principal component analysis method, normalization processing may be performed on the network performance index data, and by performing normalization processing on the performance index data of each communication network terminal access device, the index data are in the same order of magnitude, so that network device performance index data indexes of different name types have comparability. The data processing methods further included before the dimensionality reduction of the network performance index data by the principal component analysis method can be used alone or in combination, and are not listed here.
In an embodiment, the step S130 of performing association analysis on the dimensionality-reduced network performance index data and the fault condition data through a naive bayes algorithm to obtain the communication network fault early warning model by the communication network fault early warning method may further include: and obtaining the key performance index type and the threshold value for representing the equipment failure according to the correlation analysis.
Fig. 3 shows a flowchart of a method for communication network fault warning testing according to an embodiment of the present invention. In S310 in this experiment, network element classification is performed on the collected data. In S320, the sorted data is subjected to dimensionality reduction. In S330, the network quality performance index selected after the dimensionality reduction and the number of device failures are subjected to correlation analysis. In step S340, key performance indicators are selected and threshold analysis is performed on the performance indicators. Specifically, the network performance index data and the fault condition data of the adopted communication network terminal access equipment are 76 ten thousand equipment performance index data resources which are acquired by 5119 4G base stations according to 560 equipment performance index data dimensions within 5 months of a certain city. Here, a 4G base station is selected as the communication network end access device. Data processing actions can be performed on the acquired data, for example, network performance index data and fault condition data resources of 76 ten thousand pieces of base station equipment with 560 equipment performance data dimensions are cleaned, and abnormal data are eliminated. And carrying out mean calculation on the same dimension indexes of the same base station according to working days and non-working days. The average value calculation is to perform correlation matrix calculation on 560 base station equipment performance data sets, select 77 performance indexes with correlation coefficients larger than 0.5, further remove indexes with weak numerical fluctuation, reduce the base station equipment performance index sets to 39, and take the 39 equipment performance index sets as network optimization indexes. The correlation matrix is also called correlation coefficient matrix and is formed by correlation coefficients among columns of the matrix. The screening limit for the correlation coefficient here deals with 0.5 in this experiment and can also be a value between 0.3 and 0.7 depending on the requirements. The 39-dimensional performance index set of the 4G base station equipment can be subjected to clustering analysis, for example, a K-means clustering algorithm is adopted, specifically, the 39-dimensional performance index of each 4G base station equipment after data processing is distributed to the nearest cluster center to obtain K clusters; and respectively calculating the average values of the obtained clusters, and taking the average values as the new cluster centers of the clusters. Taking three groups of performance indexes of the paging record receiving number, the cell downlink packet loss number and the cancellation times of S1 switching among eNBs as examples, the performance index clustering center points of the 4G base station equipment are distributed in Table 1:
TABLE 1, 4G base station equipment performance index clustering center point distribution
The intra-cluster and inter-cluster distances of each cluster can be calculated through Euclidean distances, and the clustering parameters can be optimized through the ratio of the sum of squared errors of the clusters, and the calculation method comprises the following steps:
in the formula (1), m is the number of clustering clusters, and n is the number of distance relationships among the clusters. The smaller the value of the ratio of the squared cluster errors is, the smaller the distance of the intra-cluster network element performance index is, and the larger the distance of the inter-cluster network element performance index is, thus indicating that the clustering effect is better, otherwise, the clustering effect is worse.
Here, 4G base station devices can also be clustered into 5 clusters by "cluster square error sum ratio" clustering calculation, and the specific number and proportion distribution of the 4G base station devices in each cluster are given in table 2:
table 2, number of 4G base station devices in each cluster and ratio distribution
| Cluster number | Cluster 0 | Cluster 1 | Cluster 2 | Cluster 3 | Group 4 |
| Number of network elements (devices) | 1 858 | 1 576 | 485 | 103 | 1 097 |
| Ratio distribution | 36％ | 31％ | 9％ | 2％ | 21％ |
In the network element classification process, the network equipment classification based on the equipment performance index features avoids analysis interference caused by the difference between the 4G base station equipment service classification and the 4G base station equipment actual operation performance index, and realizes the differential classification based on the network element performance index features.
The maximum value x of the index data can be selected for the performance index data of the statistical historical base station equipmentmaxAnd the minimum value xminThen, data normalization processing is carried out, dimensions are removed, so that the index data are in the same order of magnitude, and the performance index data indexes of the network equipment with different name types are comparable, wherein the calculation method comprises the following steps:
xi＝(xi-xmin)/(xmax-xmin)
in an embodiment of an experiment performed according to the communication fault early warning method, a principal component analysis method may be used to perform group dimensionality reduction on clustered network elements, and the method may be used to perform group dimensionality reduction on clustered network elementsTo construct 560-dimensional index vector x ═ (x) of equipment performance index data1，x2，x3，...x560)TThen 5119 4G base stations will form a full sample matrix, i.e.: x is the number ofi＝(xi1，xi2，xi3，...xi560)T1, 2, 3.., 5119, a normalized transformation is performed on the sample array elements to obtain a normalized matrix Z:
in the formula (2), the reaction mixture is,calculating a correlation coefficient matrix by normalizing the matrix Z, wherein the correlation coefficient matrix is calculated as follows:
wherein,i, j ═ 1, 2, 3. Solving eigen equation | R- λ I of sample correlation matrix RpGet p characteristic roots and then determine principal component, where IpIs a unit main diagonal matrix.
Can be as followsDetermining m value, i.e. the cumulative contribution of information up to 85%, for each lambdaj1, 2, 3, m, solving equation detail Rb λjb obtaining unit vectorsConverting the standardized 4G base station equipment performance index variable into a principal componentj ═ 1, 2, 3.., m, where U is1Is a first main component, U2Is the second principal component, and so on, UpIs the pth principal component. And carrying out weighted summation on the m main components to obtain the final index value combination.
Performing dimensionality reduction analysis on the performance index data through principal component analysis to find that: the cumulative contribution rate of 89 principal component expressions is 100%, for convenient calculation, 45 principal component expressions can be selected according to the cumulative information utilization rate of 85%, and the 8 th principal component U is used821 st principal component U2122 nd principal component U22For example, the 8 th principal component U821 st principal component U21And 22 nd principal component U22The main performance indicators and their weights are given in tables 3 to 5:
TABLE 3, 8 th principal component U8And their weights
| Weight of | Performance index | Weight of | Performance index |
| -0.171 | Number of successes in CSFB initial context establishment | 0.137 | Number of inter-eNB handover preparation failures |
| -0.171 | CSFB initializationNumber of context establishment requests | 0.137 | Average utilization rate of downlink PRB |
| -0.163 | CSFB triggered RRC connection Release count | 0.136 | Average rate of downlink users |
| 0.143 | Downlink traffic information PRB occupancy rate | 0.135 | Maximum number of active E-RAB downlink |
TABLE 4, 21 st principal component U21And their weights
TABLE 5, 22 nd principal component U22And their weights
The obtained principal component expression and the base station failure times can be subjected to correlation analysis by using a naive Bayes algorithm, and a reference performance index is selected, wherein the specific method comprises the following steps:
and (4) performing correlation analysis on the 45 principal component expressions subjected to the index dimension reduction and the base station failure times by calculating a correlation coefficient, wherein the base station fallback times can be used as failure standards for the correlation analysis. For example, the principal component expression with the absolute value of the correlation coefficient greater than 0.1 may be selected as the key principal component expression, including: principal component expression 8, principal component expression 16, principal component expression 21, and principal component expression 22, where the above key principal component expression is given in table 6 with respect to the base station apparatus backoff number:
TABLE 6 correlation coefficient of key principal component expression and base station equipment out-of-service times
Table 6 can show that the principal component expressions have a certain correlation with the base station backoff times, and can classify 45 principal component expressions and the base station backoff times by a naive bayes tree method. The binning operation may be performed on each principal component expression value, the kth principal component being formed (F)k1、Fk2、...Fkn) The feature set, here, the binning operation refers to a method of smoothly storing values of data by considering surrounding values. And the service returning times of the base station can be subjected to box separation to form a base station service returning category set: (C)1、C2、...Cn). Solving for P (C) according to a naive Bayes tree methodk|Fk1Fk2...Fkn) The maximum value of the k-th principal component is the classification result.
Requiring only P (F)k1Fk2...Fkn|Ck)P(Ck) The principal component analysis method can ensure that all characteristic values are independent of each other, then
P(Fk1Fk2...Fkn|Ck)P(Ck)＝P(Fk1|Ck)P(Fk2|Ck)...P(Fkn|Ck)P(Ck) (4)
P(Fkn|Ck) Can be calculated by counting on the training setAnd collecting the distribution of each characteristic value corresponding to each box value in each base station service quitting warning time category. And obtaining a naive Bayes classification model and constructing a classification tree. By adopting the classification model, the class of the out-of-service alarm times of the base station can be judged under the condition of giving a set of principal component characteristic values, and the importance degree of the principal component index can be evaluated.
In determining the threshold range of the base station performance index for determining the failure condition of the base station equipment, the 8 th principal component U may be processed in the above embodiment821 st principal component U2122 nd main component U22The 22 main performance indexes are subjected to correlation analysis, and the performance indexes larger than a preset value, such as 0.75, are grouped into one group. Because the same group of network optimization indexes with correlation have the same or similar distribution characteristics and change rules, the characteristic rules of the group of index data can be represented by analyzing the relation between a typical network optimization index and the number of times of the quit service fault in each group.
Taking cluster 2 as an example, first, the 8 th principal component U is processed821 st principal component U2122 nd main component U22The 22 main performance indexes are numbered 1-19 in sequence, the 22 main performance indexes are divided into 9 groups through correlation analysis, the absolute value of a correlation coefficient generally representing strong correlation needs to be between 0.5 and 1.0, the correlation coefficient of the selectable performance indexes is larger than 0.75, and 4 types of fluctuation characteristics are obtained by analyzing the numerical values of the 9 groups of main performance indexes and the change of the service quitting times of 4G base station equipment as follows:
(1) middle axle fluctuation type performance index (performance index numbers 1, 2, 3, 4)
When the 4G base station equipment has fewer times of service quitting, the performance index value is relatively stable; when the service quitting times of the 4G base station equipment are between 5 and 10, the performance index value is increased by small-amplitude fluctuation; when the service quitting times of the 4G base station equipment is more than 10, the performance index value gradually has large central axial fluctuation. Therefore, the indexes belong to middle axis fluctuation type performance indexes, and bilateral threshold value grading early warning can be established according to the tolerance of engineering practice.
(2) Reduced performance index (performance index number 5 ~ 16)
When the 4G base station equipment has fewer times of service quitting, the performance index value is relatively stable; when the service quitting times of the 4G base station equipment are gradually increased, the performance index value has an overall descending trend and has no obvious inverse proportion linear relation. Therefore, the indexes belong to reduced performance indexes, and upper-limit threshold grading early warning can be established according to engineering practice tolerance.
(3) Elevated Performance level (Performance level number 17)
When the 4G base station equipment has fewer times of service quitting, the performance index value is relatively constant; when the service quitting times of the 4G base station equipment are gradually increased, the performance index value has an overall ascending trend and has no obvious proportional linear relation. Therefore, the indexes belong to elevated performance indexes, and a lower-limit threshold grading early warning can be established according to engineering practice tolerance.
(4) Constant shape performance index of center shaft (performance index numbers 18, 19)
Along with the increase of the service quitting times of the 4G base station equipment, the performance index value fluctuates around the central axis, but the obvious change characteristic is not presented, so that the performance index value is not included in a reference index system of a service quitting fault early warning model of the 4G base station equipment.
Through analysis of the change rule of the service quitting failure times and the performance indexes of the 4G base station equipment, the 1 st type (the 1 st group, 6 performance indexes in total), the 2 nd type (the 2 nd to 7 th groups, 12 performance indexes in total) and the 3 rd type (the 8 th group, 1 performance index in total) are finally selected to form a 4G base station equipment communication network failure early warning model consisting of 19 reference performance indexes, and the reference indexes of the 4G base station equipment communication network failure early warning model are selected and the threshold value is given in a table 7:
TABLE 7, selection of reference index and threshold value of fault early warning model of 4G base station equipment communication network
In an embodiment, after the communication network fault early warning model is established, network performance index data and fault condition data of the device are collected again by collecting parameter changes of base station equipment or directly receiving instructions given by the device or workers when the condition occurs, but historical network performance index data and fault condition data of the device are still used as reference data sources, and the obtained communication network fault early warning model is updated iteratively to ensure reliability and real-time performance of data of each link in fallback fault early warning analysis. According to the communication network fault early warning method of the embodiment, 4G base station equipment performance index data (daily granularity) of 5 months in a certain city is adopted, early warning analysis can be performed on the service quitting fault of the 4G base station equipment in the next month in the previous month, and 27.8% (mean value) of the service quitting fault events of the base station equipment can be accurately performed through testing.
Fig. 4 is a block diagram illustrating a communication network failure early warning apparatus according to an embodiment of the present invention. This communication network trouble early warning device includes: a data collection module 401, a dimension reduction module 402, an association analysis module 403, and an iterative update module 404. The data collection module 401 is configured to collect network performance indicator data and fault condition data for an end access device of a communication network. The dimensionality reduction module 402 is configured to reduce the dimensionality of the network performance indicator data via principal component analysis. The association analysis module 403 is configured to perform association analysis on the dimensionality-reduced network performance index data and the fault condition data through a naive bayes algorithm to obtain a communication network fault early warning model. The iterative update module 404 is configured to receive a parameter change indication signal of the communication network end access device, and determine whether to collect network performance index data and fault condition data of the communication network end access device again according to the parameter change indication signal to perform iterative update on the obtained communication network fault early warning model. In one example, the parameter change indication signal includes at least one of an operational state change indication signal of the device, an alarm indication signal of the device, and a configuration parameter adjustment indication signal of the device. In one example, the apparatus further includes a first data pre-processing module configured to perform a washing and/or averaging process on the network performance indicator data. In one example, the apparatus further includes a second data preprocessing module configured to perform cluster analysis on the network performance indicator data, so as to perform network element classification on the communication network end access device, thereby obtaining a cluster grouping of the network performance indicator data. In one example, the apparatus further includes a third data pre-processing module configured to normalize the network performance indicator data. It should be understood that the data processing modules in the above examples can be used alone or in combination. In one example, the association analysis module 403 of the apparatus is further configured to obtain a category of key performance indicators and a threshold value characterizing the failure of the device according to the association analysis. It should be noted that, the apparatus and the method correspond to each other, and both have similar functions, which can solve similar technical problems, and therefore, the same or similar parts of the apparatus and the method are not repeated.
At least a part of the communication network failure early warning apparatus and the communication network failure early warning method described in conjunction with fig. 1 and 4 may be implemented by a computing device. Fig. 5 is a block diagram illustrating an exemplary hardware architecture of a computing device capable of implementing at least a portion of a communication network fault early warning apparatus and a communication network fault early warning method according to embodiments of the present invention. As shown in fig. 5, computing device 500 includes an input device 501, an input port 502, a processor 503, a memory 504, an output port 505, and an output device 506. The input port 502, the processor 503, the memory 504, and the output port 505 are connected to each other via a bus 510, and the input device 501 and the output device 506 are connected to the bus 510 via the input port 502 and the output port 505, respectively, and further connected to other components of the computing device 500. It should be noted that the output interface and the input interface can also be represented by I/O interfaces. Specifically, the input device 501 receives input information from the outside and transmits the input information to the processor 503 through the input port 502; the processor 503 processes the input information based on computer-executable instructions stored in the memory 504 to generate output information, stores the output information in the memory 504 temporarily or permanently, and then transmits the output information to the output device 506 through the output port 505; output device 506 outputs the output information to an exterior of computing device 500.
When the communication network fault early warning apparatus described in conjunction with fig. 1 and 4 is implemented by the computing device 500 shown in fig. 5, the input device 501 collects network performance index data and fault condition data of the communication network end access device, receives a parameter change indication signal of the communication network end access device, and determines whether to collect network performance index data and fault condition data of the communication network end access device again according to the parameter change indication signal; the processor 503 processes the collected network performance indicator data and fault condition data for the communication network end access device based on computer executable instructions stored in the memory 504. The communication network fault pre-warning result is then directly output via the output port 505 and the output device 506 as needed.
That is, the stock right data processing apparatus according to the embodiment of the present invention may also be implemented to include a memory storing computer-executable instructions; and a processor, which when executing the computer executable instructions, may implement the communication network failure early warning apparatus and the communication network failure early warning method described in conjunction with fig. 1 and 4.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. Also, a detailed description of known process techniques is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present invention.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. 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.
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 several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some ports, devices or units, and may also be an electrical, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (13)
1. A communication network fault early warning method comprises the following steps:
collecting network performance index data and fault condition data of the communication network terminal access equipment;
performing dimensionality reduction on the network performance index data through a principal component analysis method;
performing correlation analysis on the network performance index data subjected to dimensionality reduction and the fault condition data through a naive Bayesian algorithm to obtain a communication network fault early warning model; and
and receiving a parameter change indication signal of the communication network terminal access equipment, and judging whether to collect network performance index data and fault condition data of the communication network terminal access equipment again according to the parameter change indication signal to iteratively update the obtained communication network fault early warning model.
2. The method of claim 1, wherein the parameter change indication signal comprises at least one of an operational state change indication signal of the device, an alarm indication signal of the device, and a configuration parameter adjustment indication signal of the device.
3. The method of claim 1, wherein the dimensionality reduction of the network performance indicator data by principal component analysis further comprises:
and cleaning and/or equalizing the network performance index data.
4. The method of claim 1 or 3, wherein the dimensionality reduction of the network performance indicator data by principal component analysis further comprises:
and performing cluster analysis on the network performance index data, thereby performing network element classification on the communication network terminal access equipment and further obtaining cluster grouping of the network performance index data.
5. The method of claim 1, 3 or 4, wherein the reducing the dimensions of the network performance indicator data by principal component analysis further comprises:
and carrying out normalization processing on the network performance index data.
6. The method of claim 1, wherein the step of obtaining a communication network fault pre-warning model by correlating the dimensionality reduced network performance indicator data with the fault condition data through a naive bayes algorithm further comprises: and obtaining the key performance index type and the threshold value representing the equipment fault according to the correlation analysis.
7. A communication network fault early warning device, comprising:
a data collection module configured to collect network performance indicator data and fault condition data of a communication network end access device;
the dimensionality reduction module is configured to reduce the dimensionality of the network performance index data through a principal component analysis method;
the correlation analysis module is configured to perform correlation analysis on the dimensionality-reduced network performance index data and the fault condition data through a naive Bayesian algorithm to obtain a communication network fault early warning model; and
and the iteration updating module is configured to receive a parameter change indicating signal of the communication network terminal access equipment, and judge whether to collect network performance index data and fault condition data of the communication network terminal access equipment again according to the parameter change indicating signal to perform iteration updating on the obtained communication network fault early warning model.
8. The apparatus of claim 7, wherein the parameter change indication signal comprises at least one of an operational state change indication signal of the device, an alarm indication signal of the device, and a configuration parameter adjustment indication signal of the device.
9. The apparatus of claim 7, further comprising:
a first data preprocessing module configured to perform cleaning and/or averaging on the network performance indicator data.
10. The apparatus of claim 7 or 9, further comprising:
and the second data preprocessing module is configured to perform cluster analysis on the network performance index data so as to perform network element classification on the communication network terminal access equipment and further obtain cluster grouping of the network performance index data.
11. The apparatus of claim 7, 9 or 10, further comprising:
a third data preprocessing module configured to normalize the network performance indicator data.
12. The apparatus of claim 7, wherein the correlation analysis module is further configured to obtain key performance indicator types and thresholds characterizing the device failure according to the correlation analysis.
13. A communication network fault early warning device, comprising:
a memory storing computer-executable instructions;
a processor for executing the memory-stored program, the program causing the processor to perform any one of the communication network failure warning methods of claims 1-6;
an input device;
an output device;
an I/O interface; and
a bus for passing information between the processor, memory, input devices, output devices, and I/O interfaces.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610983540.5A CN108063676A (en) | 2016-11-08 | 2016-11-08 | Communication network failure method for early warning and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610983540.5A CN108063676A (en) | 2016-11-08 | 2016-11-08 | Communication network failure method for early warning and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108063676A true CN108063676A (en) | 2018-05-22 |
Family
ID=62136762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610983540.5A Pending CN108063676A (en) | 2016-11-08 | 2016-11-08 | Communication network failure method for early warning and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108063676A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409411A (en) * | 2018-09-28 | 2019-03-01 | 东软集团股份有限公司 | The problem of based on operation management localization method, device and storage medium |
| CN109548057A (en) * | 2018-12-18 | 2019-03-29 | 广州旭隆通信科技有限公司 | A kind of method and system of base station monitoring and maintenance |
| CN110740061A (en) * | 2019-10-18 | 2020-01-31 | 北京三快在线科技有限公司 | Fault early warning method and device and computer storage medium |
| CN110808864A (en) * | 2019-11-12 | 2020-02-18 | 国家电网有限公司 | Communication early warning method, device and system |
| CN111082956A (en) * | 2018-10-22 | 2020-04-28 | 中兴通讯股份有限公司 | Event stream processing method, electronic device and readable storage medium |
| CN111680727A (en) * | 2020-05-29 | 2020-09-18 | 深圳市英维克信息技术有限公司 | Naive Bayes-based fault diagnosis method, diagnosis device, and storage medium |
| CN111813643A (en) * | 2020-07-08 | 2020-10-23 | 上海燕汐软件信息科技有限公司 | Data processing method, device and system for fault management system |
| CN111934895A (en) * | 2019-05-13 | 2020-11-13 | 中国移动通信集团湖北有限公司 | Intelligent early warning method and device for network management system and computing equipment |
| CN112152868A (en) * | 2019-06-28 | 2020-12-29 | 北京金山云网络技术有限公司 | Network fault detection method and device, electronic equipment 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 |
| CN112383421A (en) * | 2020-11-03 | 2021-02-19 | 中国联合网络通信集团有限公司 | Fault positioning method and device |
| CN112714458A (en) * | 2019-10-24 | 2021-04-27 | 大唐移动通信设备有限公司 | Base station parameter updating method and base station |
| CN112836843A (en) * | 2019-11-25 | 2021-05-25 | 中国移动通信集团设计院有限公司 | Method and device for predicting base station out-of-service alarm |
| CN114827951A (en) * | 2022-04-24 | 2022-07-29 | 重庆长安汽车股份有限公司 | Vehicle network quality analysis method and system based on vehicle terminal and storage medium |
| CN115426244A (en) * | 2022-08-09 | 2022-12-02 | 武汉虹信技术服务有限责任公司 | Network equipment fault detection method based on big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917297A (en) * | 2010-08-30 | 2010-12-15 | 烽火通信科技股份有限公司 | Method and system for diagnosing faults of core network based on Bayesian network |
| WO2015091784A1 (en) * | 2013-12-19 | 2015-06-25 | Bae Systems Plc | Data communications performance monitoring |
| CN105721194A (en) * | 2016-01-13 | 2016-06-29 | 广州衡昊数据科技有限公司 | Intelligent positioning system of faults and hidden dangers of mobile network |
-
2016
- 2016-11-08 CN CN201610983540.5A patent/CN108063676A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917297A (en) * | 2010-08-30 | 2010-12-15 | 烽火通信科技股份有限公司 | Method and system for diagnosing faults of core network based on Bayesian network |
| WO2015091784A1 (en) * | 2013-12-19 | 2015-06-25 | Bae Systems Plc | Data communications performance monitoring |
| CN105721194A (en) * | 2016-01-13 | 2016-06-29 | 广州衡昊数据科技有限公司 | Intelligent positioning system of faults and hidden dangers of mobile network |
Non-Patent Citations (1)
| Title |
|---|
| 王洋: "基于集中监控数据资源的4G基站退服故障预警模型", 《电信科学》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109409411B (en) * | 2018-09-28 | 2020-11-03 | 东软集团股份有限公司 | Problem positioning method and device based on operation and maintenance management and storage medium |
| CN109409411A (en) * | 2018-09-28 | 2019-03-01 | 东软集团股份有限公司 | The problem of based on operation management localization method, device and storage medium |
| CN111082956B (en) * | 2018-10-22 | 2022-06-07 | 中兴通讯股份有限公司 | Event stream processing method, electronic device and readable storage medium |
| CN111082956A (en) * | 2018-10-22 | 2020-04-28 | 中兴通讯股份有限公司 | Event stream processing method, electronic device and readable storage medium |
| WO2020083023A1 (en) * | 2018-10-22 | 2020-04-30 | 中兴通讯股份有限公司 | Event flow processing method, electronic device, and readable storage medium |
| CN109548057A (en) * | 2018-12-18 | 2019-03-29 | 广州旭隆通信科技有限公司 | A kind of method and system of base station monitoring and maintenance |
| CN111934895B (en) * | 2019-05-13 | 2022-11-15 | 中国移动通信集团湖北有限公司 | Intelligent early warning method and device for network management system and computing equipment |
| CN111934895A (en) * | 2019-05-13 | 2020-11-13 | 中国移动通信集团湖北有限公司 | Intelligent early warning method and device for network management system and computing equipment |
| CN112152868A (en) * | 2019-06-28 | 2020-12-29 | 北京金山云网络技术有限公司 | Network fault detection method and device, electronic equipment 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 |
| 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 |
| CN110740061B (en) * | 2019-10-18 | 2020-09-29 | 北京三快在线科技有限公司 | Fault early warning method and device and computer storage medium |
| CN110740061A (en) * | 2019-10-18 | 2020-01-31 | 北京三快在线科技有限公司 | Fault early warning method and device and computer storage medium |
| CN112714458A (en) * | 2019-10-24 | 2021-04-27 | 大唐移动通信设备有限公司 | Base station parameter updating method and base station |
| CN112714458B (en) * | 2019-10-24 | 2022-06-21 | 大唐移动通信设备有限公司 | Base station parameter updating method and base station |
| CN110808864A (en) * | 2019-11-12 | 2020-02-18 | 国家电网有限公司 | Communication early warning method, device and system |
| CN112836843B (en) * | 2019-11-25 | 2024-04-09 | 中国移动通信集团设计院有限公司 | Base station out-of-service alarm prediction method and device |
| CN112836843A (en) * | 2019-11-25 | 2021-05-25 | 中国移动通信集团设计院有限公司 | Method and device for predicting base station out-of-service alarm |
| CN111680727A (en) * | 2020-05-29 | 2020-09-18 | 深圳市英维克信息技术有限公司 | Naive Bayes-based fault diagnosis method, diagnosis device, and storage medium |
| CN111680727B (en) * | 2020-05-29 | 2023-12-26 | 深圳市英维克信息技术有限公司 | Naive Bayes-based fault diagnosis method, diagnosis device and storage medium |
| CN111813643A (en) * | 2020-07-08 | 2020-10-23 | 上海燕汐软件信息科技有限公司 | Data processing method, device and system for fault management system |
| CN112383421B (en) * | 2020-11-03 | 2023-03-24 | 中国联合网络通信集团有限公司 | Fault positioning method and device |
| CN112383421A (en) * | 2020-11-03 | 2021-02-19 | 中国联合网络通信集团有限公司 | Fault positioning method and device |
| CN114827951A (en) * | 2022-04-24 | 2022-07-29 | 重庆长安汽车股份有限公司 | Vehicle network quality analysis method and system based on vehicle terminal and storage medium |
| CN115426244A (en) * | 2022-08-09 | 2022-12-02 | 武汉虹信技术服务有限责任公司 | Network equipment fault detection method based on big data |
| CN115426244B (en) * | 2022-08-09 | 2024-03-15 | 武汉虹信技术服务有限责任公司 | Network equipment fault detection method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108063676A (en) | Communication network failure method for early warning and device | |
| US11277420B2 (en) | Systems and methods to detect abnormal behavior in networks | |
| CN112398680B (en) | Fault delimiting method and equipment | |
| CN101997709B (en) | Root alarm data analysis method and system | |
| US12063528B2 (en) | Anomaly detection method and device, terminal and storage medium | |
| US9015312B2 (en) | Network management system and method for identifying and accessing quality of service issues within a communications network | |
| US10225165B2 (en) | Apparatus and method for processing data streams in a communication network | |
| EP1834444B1 (en) | Binary class based analysis and monitoring | |
| CN112243249B (en) | LTE new access anchor point cell parameter configuration method and device under 5G NSA networking | |
| CN109347688A (en) | A kind of method and apparatus of positioning failure in a wireless local area network | |
| CN110443037A (en) | A kind of power monitoring network security postures cognitive method based on modified AHP | |
| CN108880706A (en) | A kind of fast diagnosis method of satellite channel link failure | |
| CN110428191B (en) | Method for identifying fragile nodes of power distribution network | |
| WO2023216457A1 (en) | Method for predicting and positioning abnormity of transmission network between core network and base station | |
| CN109525455B (en) | Hydrological real-time monitoring network state comprehensive evaluation method | |
| CN117156484B (en) | Communication base station energy consumption analysis system and method based on 5G technology | |
| CN115130578A (en) | Incremental rough clustering-based online evaluation method for state of power distribution equipment | |
| CN114553671A (en) | Diagnosis method for power communication network fault alarm | |
| CN109960839B (en) | Service link discovery method and system of service support system based on machine learning | |
| CN111263389A (en) | Method and device for automatically positioning Volte voice quality problem | |
| CN114676157B (en) | Internet access quality monitoring and analyzing method, system, medium and program | |
| CN116522213A (en) | Service state level classification and classification model training method and electronic equipment | |
| CN110225540A (en) | A kind of fault detection method towards centralization access net | |
| CN117376084A (en) | Fault detection method, electronic equipment and medium thereof | |
| CN109034538A (en) | A kind of evaluation analysis method towards automation of transformation substations equipment running quality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| 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: 20180522 |