CN113642624A - Intelligent diagnosis method and device for mobile communication network fault - Google Patents
Intelligent diagnosis method and device for mobile communication network fault Download PDFInfo
- Publication number
- CN113642624A CN113642624A CN202110898063.3A CN202110898063A CN113642624A CN 113642624 A CN113642624 A CN 113642624A CN 202110898063 A CN202110898063 A CN 202110898063A CN 113642624 A CN113642624 A CN 113642624A
- Authority
- CN
- China
- Prior art keywords
- neural network
- mobile communication
- communication network
- particle
- network model
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 78
- 238000010295 mobile communication Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003062 neural network model Methods 0.000 claims abstract description 76
- 239000002245 particle Substances 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 67
- 238000013528 artificial neural network Methods 0.000 claims abstract description 37
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 210000002569 neuron Anatomy 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 210000004027 cell Anatomy 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000007257 malfunction Effects 0.000 claims 2
- 238000010276 construction Methods 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 12
- 208000018910 keratinopathic ichthyosis Diseases 0.000 description 7
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 230000004075 alteration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an intelligent diagnosis method, medium, equipment and device for mobile communication network faults, wherein the method comprises the following steps: acquiring key performance index data of a mobile communication network, and preprocessing the key performance index data to generate a training sample and a test sample; acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; inputting the training sample into a series neural network model, and optimizing an initial weight and a node threshold of the series neural network by adopting a particle swarm algorithm to complete the training of the series neural network model; inputting the test sample into the trained series neural network model so as to carry out fault diagnosis on the mobile communication network through the series neural network model; the generation cost of the training sample can be effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
Description
Technical Field
The present invention relates to the field of mobile communications technologies, and in particular, to an intelligent diagnosis method for a mobile communications network fault, a computer-readable storage medium, a computer device, and an intelligent diagnosis apparatus for a mobile communications network fault.
Background
If a fault occurs in the use process of the mobile communication network, the corresponding key performance index is deteriorated. In the related art, the problem is solved by adopting a supervised learning mode. That is, a classifier model is trained through a data set formed by KPIs recorded by a base station side and corresponding fault causes, and fault diagnosis is completed through the classifier model; common fault diagnosis models include a fault diagnosis model based on a support vector machine or a fault diagnosis model based on a random forest. However, in actual fault diagnosis, KPI data that marks the cause of a fault is difficult to obtain, so that the process of constructing a fault diagnosis model using supervised learning is difficult to implement, and the finally obtained diagnosis model is not good in effect.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, one objective of the present invention is to provide an intelligent diagnosis method for mobile communication network faults, which can effectively reduce the generation cost of training samples and reduce the construction period of a neural network model; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
A second object of the invention is to propose a computer-readable storage medium.
A third object of the invention is to propose a computer device.
The fourth purpose of the invention is to provide an intelligent diagnosis device for mobile communication network faults.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides an intelligent diagnosis method for a mobile communication network fault, including the following steps: acquiring key performance index data of a mobile communication network, and preprocessing the key performance index data to generate a training sample and a test sample; acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; inputting the training sample into the series neural network model, and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm to finish the training of the series neural network model; inputting the test sample into a trained series neural network model so as to carry out fault diagnosis on the mobile communication network through the series neural network model; therefore, the generation cost of the training sample is effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
According to the intelligent diagnosis method for the mobile communication network fault, firstly, key performance index data of the mobile communication network are obtained, and the key performance index data are preprocessed to generate a training sample and a test sample; then, acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; then, inputting the training sample into the series neural network model, and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm to finish the training of the series neural network model; then, inputting the test sample into a trained series neural network model to perform fault diagnosis on the mobile communication network through the series neural network model; therefore, the generation cost of the training sample is effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In addition, the intelligent diagnosis method for the mobile communication network fault according to the above embodiment of the present invention may further have the following additional technical features:
optionally, the primary network is an SOM neural network, and the secondary network is a BP neural network.
Optionally, the key performance indicator data includes a connection establishment success rate, a reference signal received power, a ratio of number to total number of successful handovers, a reference signal received quality, a signal to interference plus noise ratio, an average throughput of all users in a cell, and a distance from a user in the cell to a base station.
Optionally, the tandem neural network model includes an input layer, a competition layer, a hidden layer, and an output layer, where the number of neuron nodes of the input layer is equal to the dimension of the key performance indicator data, and the competition layer is a hexagonal honeycomb structure.
Optionally, optimizing the initial weight and the node threshold of the series neural network by using a particle swarm algorithm, including:
s1, determining the topological structure of the series neural network;
s2, encoding the network connection weight and the node threshold of the series neural network to initialize a particle swarm;
s3, taking the mean square error of the training of the series neural network as the fitness function of the particles;
s4, calculating the fitness function value of each particle in the particle swarm, and comparing the fitness function values of the particles;
s5, updating the particle speed and updating the particle position according to the comparison result of the fitness function value of each particle;
and S6, iterating the steps S4-S5 until the fitness function value of each particle converges.
Optionally, the mean square error is expressed by the following formula:
wherein E isk(l) Representing the mean square error, S representing the number of samples of the training samples, k representing the sample number of the training samples, M representing the number of nodes of the output layer, djk(l) Represents the expected output, y, of the training sample k at output node j at the ith iterationjk(l) Representing the actual output of the output node j of the training sample k at the ith iteration.
Optionally, the particle velocity is calculated by the following formula:
vmn(g+1)＝wvmn(g)+c1r1[pmn(g)-xmn(g)]+c2r2[phn(g)-xmn(g)]
where v represents the velocity of the particles, m represents the number of particles, n represents a dimension of the search space, g represents the number of iterations, w represents the inertia weight, c represents the number of iterations, and1、c2is the acceleration coefficient of the particle, r1、r2Two value ranges [0,1 ]]X denotes the position of the particle, p denotes the optimal position of the particle, vmn(g)、xmn(g) Respectively representing the speed and position of the mth particle of the g generation in the nth dimension, phn(g) Represents the optimal position of the particle group of the g generation on the n dimension.
In order to achieve the above object, a second embodiment of the present invention provides a computer-readable storage medium, on which an intelligent diagnosis program for a mobile communication network fault is stored, and when the intelligent diagnosis program for a mobile communication network fault is executed by a processor, the intelligent diagnosis method for a mobile communication network fault as described above is implemented.
According to the computer-readable storage medium of the embodiment of the invention, the intelligent diagnosis program of the mobile communication network fault is stored, so that the processor can realize the intelligent diagnosis method of the mobile communication network fault when executing the intelligent diagnosis program of the mobile communication network fault, thereby effectively reducing the generation cost of the training sample and reducing the construction period of the neural network model; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In order to achieve the above object, a third embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the intelligent diagnosis method for mobile communication network failure as described above is implemented.
According to the computer equipment provided by the embodiment of the invention, the intelligent diagnosis program of the mobile communication network fault is stored through the memory, so that the processor can realize the intelligent diagnosis method of the mobile communication network fault when executing the intelligent diagnosis program of the mobile communication network fault, thereby effectively reducing the generation cost of a training sample and reducing the construction period of a neural network model; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In order to achieve the above object, a fourth aspect of the present invention provides an intelligent diagnosis apparatus for mobile communication network faults, including an obtaining module, configured to obtain key performance index data of a mobile communication network; the data processing module is used for preprocessing the key performance index data to generate a training sample and a testing sample; the building module is used for obtaining a primary network and a secondary network and building a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; the building module is also used for inputting the training samples into the series neural network model and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm so as to complete the training of the series neural network model; and the diagnosis module is used for inputting the test sample to the trained serial neural network model so as to carry out fault diagnosis on the mobile communication network through the serial neural network model.
According to the intelligent diagnosis device for the mobile communication network fault, the acquisition module is arranged for acquiring key performance index data of the mobile communication network; the data processing module is used for preprocessing the key performance index data to generate a training sample and a testing sample; the building module is used for obtaining a primary network and a secondary network and building a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; the building module is also used for inputting the training samples into the series neural network model and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm so as to complete the training of the series neural network model; the diagnosis module is used for inputting the test sample into a trained series neural network model so as to carry out fault diagnosis on the mobile communication network through the series neural network model; therefore, the generation cost of the training sample is effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
Drawings
Fig. 1 is a flow chart illustrating an intelligent diagnosis method for mobile communication network faults according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a tandem neural network model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for optimizing initial weights and node thresholds according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a procedure for performing optimization on initial weights and node thresholds according to another embodiment of the present invention;
fig. 5 is a block diagram of an intelligent diagnosis apparatus for mobile communication network failure according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
In the related technology, a supervised learning mode is mostly adopted to solve the problem that if a fault occurs in the use process of a mobile communication network, the corresponding key performance index is deteriorated; however, in actual fault diagnosis, KPI data for marking a fault cause is difficult to obtain, so that the process of constructing a fault diagnosis model by using supervised learning is difficult to implement, and the finally obtained diagnosis model has poor effect; according to the intelligent diagnosis method for the mobile communication network fault, firstly, key performance index data of the mobile communication network are obtained, and the key performance index data are preprocessed to generate a training sample and a test sample; then, acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; then, inputting the training sample into the series neural network model, and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm to finish the training of the series neural network model; then, inputting the test sample into a trained series neural network model to perform fault diagnosis on the mobile communication network through the series neural network model; therefore, the generation cost of the training sample is effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be 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 scope of the invention to those skilled in the art.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Fig. 1 is a schematic flowchart of an intelligent diagnosis method for a mobile communication network fault according to an embodiment of the present invention, and as shown in fig. 1, the intelligent diagnosis method for a mobile communication network fault includes the following steps:
s101, key performance index data of the mobile communication network are obtained, and the key performance index data are preprocessed to generate a training sample and a testing sample.
That is, key performance indicator KPI data of the mobile communication network is obtained, and the key performance indicator data is preprocessed to obtain standardized data; further, the normalized data is divided to obtain training samples and test samples.
The key performance index data may be selected in various ways.
As an example, in an LTE network, the key performance indicator data includes:
(1) RRCSSR: RRC connection establishment success rate, i.e. the ratio of successfully completed connections to the total number of completed connections;
(2) RSRP: reference signal received power, a key parameter in LTE network that can represent radio signal strength, is the average of the received signal power over all REs (resource elements) that carry reference signals within a certain symbol;
(3) HOSR: the ratio of the number of successful handovers to the total number;
(4) RSRQ: the reference signal received quality, which is defined as the ratio of the RSRP and the RSSI, determines the actual coverage condition of the system;
(5) SINR: signal to interference plus noise ratio, defined as the ratio of the received desired signal to the received interference signal (noise plus interference) power;
(6) thrp: average throughput of all users in a cell;
(7) dist: the distance of the users in the cell to the base station.
As an example, preprocessing the key performance indicator data includes: first, KPI data collected over a period of time is saved as a data set S ═ X1,X2,...,XmIn the form of (a) } or (b),wherein Xi ═ RRCSSR, RSRP, HOSR, RSRQ, SINR, Thrp, Dist }; then, the data set is normalized, and the value is not in [0,1 ]]KPIs in between, normalized in the form:
further, a normalized data set can be obtained
Wherein the content of the first and second substances,
s102, acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network.
In some embodiments, the primary network is a SOM neural network and the secondary network is a BP neural network; namely, the SOM neural network is used as a primary network, and the BP neural network is used as a secondary network; then, the winning neuron positions of the SOM neural network are used as the input of the BP neural network to construct the SOM-BP series neural model.
In some embodiments, as shown in fig. 2, the tandem neural network model includes an input layer, a competition layer, a hidden layer, and an output layer, wherein the number of neuron nodes of the input layer is equal to the dimension of the key performance indicator data, and the competition layer is a hexagonal honeycomb structure.
As an example, the number of input layer neuron nodes of the SOM-BP tandem neural network is equal to the KPI dimension, and preferably, the number of input layer neuron nodes is 7; the competition layer adopts a 10 x 10 hexagonal honeycomb structure; in the selection of the neuron nodes of the hidden layer, training errors under different node numbers are set and compared, and the number of the training errors is preferably 14 hidden layer nodes; the number of output layer nodes is preferably 7, and is the same as the number of SOM preliminary clusters to represent 7 different types of network states
S103, inputting the training samples into the series neural network model, and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm to finish the training of the series neural network model.
In some embodiments, as shown in fig. 3, the optimizing the initial weights and node thresholds of the serial neural network by using the particle swarm optimization includes:
and S1, determining the topological structure of the series neural network.
And S2, encoding the network connection weight and the node threshold of the series neural network to initialize the particle swarm.
And S3, taking the mean square error of the training of the series neural network as the fitness function of the particles.
And S4, calculating the fitness function value of each particle in the particle swarm, and comparing the fitness function values of the particles.
And S5, updating the particle speed and updating the particle position according to the comparison result of the fitness function value of each particle.
And S6, iterating the steps S4-S5 until the fitness function value of each particle converges.
As an example, as shown in fig. 4, the optimizing the initial full-time and node thresholds of the serial neural network using the particle swarm optimization comprises: firstly, determining a topological structure of an SOM-BP (sequence-based Back propagation) series neural network; then, encoding the network weight and the node threshold value to initialize the particle swarm; then, the mean square error of the network training is used as a fitness function; then, randomly initializing the speed and the position of the particles; then, calculating a fitness function value of each particle; then, updating the individual extreme value and the global extreme value according to the fitness function value of the particle; then, updating the speed and the position of the particles; then, judging whether the current termination condition is met; if not, returning to the step of calculating the fitness function value of each particle; if yes, decoding to obtain a connection weight value and a node threshold value, and calculating an error; then, updating the connection weight and the node threshold according to the calculation result; and then, judging whether the termination condition is met currently or not, and outputting the current connection weight and the node threshold when the judgment result is yes.
In some embodiments, the mean square error is expressed by the following equation:
wherein E isk(l) Representing the mean square error, S representing the number of samples of the training samples, k representing the sample number of the training samples, M representing the number of nodes of the output layer, djk(l) Represents the expected output, y, of the training sample k at output node j at the ith iterationjk(l) Representing the actual output of the output node j of the training sample k at the ith iteration.
In some embodiments, the particle velocity is calculated by the following equation:
vmn(g+1)＝wvmn(g)+c1r1[pmn(g)-xmn(g)]+c2r2[phn(g)-xmn(g)]
where v represents the velocity of the particles, m represents the number of particles, n represents a dimension of the search space, g represents the number of iterations, w represents the inertia weight, c represents the number of iterations, and1、c2is the acceleration coefficient of the particle, r1、r2Two value ranges [0,1 ]]X denotes the position of the particle, p denotes the optimal position of the particle, vmn(g)、xmn(g) Respectively representing the speed and position of the mth particle of the g generation in the nth dimension, phn(g) Represents the optimal position of the particle group of the g generation on the n dimension.
And S104, inputting the test sample into the trained serial neural network model so as to carry out fault diagnosis on the mobile communication network through the serial neural network model.
In summary, according to the intelligent diagnosis method for mobile communication network faults in the embodiment of the present invention, first, key performance index data of a mobile communication network is obtained, and the key performance index data is preprocessed to generate a training sample and a test sample; then, acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; then, inputting the training sample into the series neural network model, and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm to finish the training of the series neural network model; then, inputting the test sample into a trained series neural network model to perform fault diagnosis on the mobile communication network through the series neural network model; therefore, the generation cost of the training sample is effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In order to implement the above embodiments, an embodiment of the present invention proposes a computer-readable storage medium on which an intelligent diagnosis program for a mobile communication network fault is stored, which, when executed by a processor, implements the intelligent diagnosis method for a mobile communication network fault as described above.
According to the computer-readable storage medium of the embodiment of the invention, the intelligent diagnosis program of the mobile communication network fault is stored, so that the processor can realize the intelligent diagnosis method of the mobile communication network fault when executing the intelligent diagnosis program of the mobile communication network fault, thereby effectively reducing the generation cost of the training sample and reducing the construction period of the neural network model; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In order to implement the above embodiments, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the intelligent diagnosis method for a mobile communication network fault as described above is implemented.
According to the computer equipment provided by the embodiment of the invention, the intelligent diagnosis program of the mobile communication network fault is stored through the memory, so that the processor can realize the intelligent diagnosis method of the mobile communication network fault when executing the intelligent diagnosis program of the mobile communication network fault, thereby effectively reducing the generation cost of a training sample and reducing the construction period of a neural network model; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
In order to implement the above embodiments, the embodiments of the present invention provide an intelligent diagnosis apparatus for mobile communication network faults; as shown in fig. 5, the intelligent diagnosis apparatus for mobile communication network failure includes: the system comprises an acquisition module 201, a data processing module 202, a construction module 203 and a diagnosis module 204.
The obtaining module 201 is configured to obtain key performance index data of the mobile communication network;
the data processing module 202 is configured to pre-process the key performance indicator data to generate a training sample and a test sample;
the building module 203 is used for obtaining a primary network and a secondary network, and building a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network;
the building module 203 is further configured to input the training samples into the serial neural network model, and optimize the initial weight and the node threshold of the serial neural network by using a particle swarm algorithm, so as to complete training of the serial neural network model;
the diagnosis module 204 is configured to input the test sample to the trained serial neural network model, so as to perform fault diagnosis on the mobile communication network through the serial neural network model.
It should be noted that the above description about the intelligent diagnosis method for mobile communication network faults in fig. 1 is also applicable to the intelligent diagnosis device for mobile communication network faults, and is not repeated herein.
In summary, according to the intelligent diagnosis device for mobile communication network faults in the embodiments of the present invention, the obtaining module is configured to obtain key performance index data of the mobile communication network; the data processing module is used for preprocessing the key performance index data to generate a training sample and a testing sample; the building module is used for obtaining a primary network and a secondary network and building a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network; the building module is also used for inputting the training samples into the series neural network model and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm so as to complete the training of the series neural network model; the diagnosis module is used for inputting the test sample into a trained series neural network model so as to carry out fault diagnosis on the mobile communication network through the series neural network model; therefore, the generation cost of the training sample is effectively reduced, and the construction period of the neural network model is reduced; meanwhile, the real-time performance and accuracy of fault diagnosis are improved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above should not be understood to necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. An intelligent diagnosis method for mobile communication network faults is characterized by comprising the following steps:
acquiring key performance index data of a mobile communication network, and preprocessing the key performance index data to generate a training sample and a test sample;
acquiring a primary network and a secondary network, and constructing a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network;
inputting the training sample into the series neural network model, and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm to finish the training of the series neural network model;
inputting the test sample into a trained series neural network model so as to carry out fault diagnosis on the mobile communication network through the series neural network model.
2. The method of claim 1, wherein the primary network is a SOM (Self-Organizing Map) neural network, and the secondary network is a bp (back propagation) neural network.
3. The method of claim 1, wherein the key performance indicator data comprises a connection establishment success rate, a reference signal received power, a ratio of number to total number of successful handovers, a reference signal received quality, a signal to interference plus noise ratio, an average throughput of all users in a cell, and a distance of a user in a cell to a base station.
4. The method according to claim 1, wherein the tandem neural network model comprises an input layer, a competition layer, a hidden layer and an output layer, wherein the number of neuron nodes of the input layer is equal to the dimension of the key performance indicator data, and the competition layer is a hexagonal honeycomb structure.
5. The intelligent diagnosis method for mobile communication network fault according to claim 1, wherein the optimizing of the initial weight and node threshold of the series neural network by using the particle swarm optimization comprises:
s1, determining the topological structure of the series neural network;
s2, encoding the network connection weight and the node threshold of the series neural network to initialize a particle swarm;
s3, taking the mean square error of the training of the series neural network as the fitness function of the particles;
s4, calculating the fitness function value of each particle in the particle swarm, and comparing the fitness function values of the particles;
s5, updating the particle speed and updating the particle position according to the comparison result of the fitness function value of each particle;
and S6, iterating the steps S4-S5 until the fitness function value of each particle converges.
6. The intelligent diagnosis method for mobile communication network failure according to claim 5, wherein the mean square error is expressed by the following formula:
wherein E isk(l) Representing the mean square error, S representing the number of samples of the training samples, k representing the sequence of samples of the training samplesNumber, M denotes the number of nodes of the output layer, djk(l) Represents the expected output, y, of the training sample k at output node j at the ith iterationjk(l) Representing the actual output of the output node j of the training sample k at the ith iteration.
7. The intelligent diagnosis method for mobile communication network failure according to claim 5, wherein the particle velocity is calculated by the following formula:
vmn(g+1)＝wvmn(g)+c1r1[pmn(g)-xmn(g)]+c2r2[phn(g)-xmn(g)]
where v represents the velocity of the particles, m represents the number of particles, n represents a dimension of the search space, g represents the number of iterations, w represents the inertia weight, c represents the number of iterations, and1、c2is the acceleration coefficient of the particle, r1、r2Two value ranges [0,1 ]]X denotes the position of the particle, p denotes the optimal position of the particle, vmn(g)、xmn(g) Respectively representing the speed and position of the mth particle of the g generation in the nth dimension, phn(g) Represents the optimal position of the particle group of the g generation on the n dimension.
8. A computer-readable storage medium, having stored thereon a mobile communication network malfunction intelligent diagnosis program, which when executed by a processor, implements the mobile communication network malfunction intelligent diagnosis method according to any one of claims 1 to 7.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements the intelligent diagnosis method of mobile communication network failure according to any one of claims 1 to 7.
10. An intelligent diagnosis device for mobile communication network faults, which is characterized by comprising:
an acquisition module for acquiring key performance index data of a mobile communication network;
the data processing module is used for preprocessing the key performance index data to generate a training sample and a testing sample;
the building module is used for obtaining a primary network and a secondary network and building a series neural network model by taking the position of a winning neuron of the primary network as the input of the secondary network;
the building module is also used for inputting the training samples into the series neural network model and optimizing the initial weight and the node threshold of the series neural network by adopting a particle swarm algorithm so as to complete the training of the series neural network model;
and the diagnosis module is used for inputting the test sample to the trained serial neural network model so as to carry out fault diagnosis on the mobile communication network through the serial neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898063.3A CN113642624A (en) | 2021-08-05 | 2021-08-05 | Intelligent diagnosis method and device for mobile communication network fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898063.3A CN113642624A (en) | 2021-08-05 | 2021-08-05 | Intelligent diagnosis method and device for mobile communication network fault |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642624A true CN113642624A (en) | 2021-11-12 |
Family
ID=78419888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110898063.3A Pending CN113642624A (en) | 2021-08-05 | 2021-08-05 | Intelligent diagnosis method and device for mobile communication network fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642624A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117741429A (en) * | 2023-12-15 | 2024-03-22 | 广东海洋大学 | Method, device, medium and equipment for determining health index of ship alternating current motor |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105334436A (en) * | 2015-10-30 | 2016-02-17 | 山东电力研究院 | Cross-linked cable partial discharge mode identification method based on SOM-BP combined neural network |
| CN108919059A (en) * | 2018-08-23 | 2018-11-30 | 广东电网有限责任公司 | A kind of electric network failure diagnosis method, apparatus, equipment and readable storage medium storing program for executing |
| CN111199252A (en) * | 2019-12-30 | 2020-05-26 | 广东电网有限责任公司 | Fault diagnosis method for intelligent operation and maintenance system of power communication network |
| CN112634019A (en) * | 2020-12-23 | 2021-04-09 | 百维金科(上海)信息科技有限公司 | Default probability prediction method for optimizing grey neural network based on bacterial foraging algorithm |
-
2021
- 2021-08-05 CN CN202110898063.3A patent/CN113642624A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105334436A (en) * | 2015-10-30 | 2016-02-17 | 山东电力研究院 | Cross-linked cable partial discharge mode identification method based on SOM-BP combined neural network |
| CN108919059A (en) * | 2018-08-23 | 2018-11-30 | 广东电网有限责任公司 | A kind of electric network failure diagnosis method, apparatus, equipment and readable storage medium storing program for executing |
| CN111199252A (en) * | 2019-12-30 | 2020-05-26 | 广东电网有限责任公司 | Fault diagnosis method for intelligent operation and maintenance system of power communication network |
| CN112634019A (en) * | 2020-12-23 | 2021-04-09 | 百维金科(上海)信息科技有限公司 | Default probability prediction method for optimizing grey neural network based on bacterial foraging algorithm |
Non-Patent Citations (4)
| Title |
|---|
| 唐建华: "基于神经网络的TD-LTE网络故障诊断技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 03, 15 March 2015 (2015-03-15), pages 242 - 245 * |
| 杨燕玲等: "《5G移动通信技术》", 北京：北京邮电大学出版社, pages: 242 - 245 * |
| 范子豪: "数据驱动的LTE-R网络故障诊断与预测研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 03, 15 March 2021 (2021-03-15) * |
| 邹兰: "基于SOM-BP神经网络的盾构机故障诊断方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 12, pages 25 - 68 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117741429A (en) * | 2023-12-15 | 2024-03-22 | 广东海洋大学 | Method, device, medium and equipment for determining health index of ship alternating current motor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110770761B (en) | Deep learning system and method and wireless network optimization using deep learning | |
| US10375585B2 (en) | System and method for deep learning and wireless network optimization using deep learning | |
| JP5733166B2 (en) | Parameter setting apparatus, computer program, and parameter setting method | |
| CN107113764B (en) | Method and device for improving positioning performance of artificial neural network | |
| CN112512069B (en) | Network intelligent optimization method and device based on channel beam pattern | |
| CN110110862A (en) | A kind of hyperparameter optimization method based on adaptability model | |
| CN110521234A (en) | The method and system of network self-organization is carried out using deep learning | |
| CN108900333A (en) | A kind of appraisal procedure and assessment device of quality of wireless network | |
| CN109120435B (en) | Network link quality prediction method, device and readable storage medium | |
| CN106982436A (en) | The detection method of adjustment and device of a kind of indoor and outdoor network coverage | |
| CN112039687A (en) | Small sample feature-oriented fault diagnosis method based on improved generation countermeasure network | |
| EP3979685A1 (en) | Network optimization method, device, and storage medium | |
| CN114268981A (en) | Network fault detection and diagnosis method and system | |
| CN112243249A (en) | LTE new access anchor point cell parameter configuration method and device under 5G NSA networking | |
| CN113642624A (en) | Intelligent diagnosis method and device for mobile communication network fault | |
| Chagas et al. | Genetic algorithms and simulated annealing optimization methods in wireless sensor networks localization using artificial neural networks | |
| Bouzid et al. | Wireless sensor network deployment optimisation based on coverage, connectivity and cost metrics | |
| CN111935761B (en) | Automatic positioning method and system for quality difference root cause of mobile communication network | |
| CN110968075B (en) | Fault diagnosis method and system based on active learning self-organizing cellular network | |
| CN105228158A (en) | Based on the cognition wireless network cooperative node selection method of intensified learning | |
| CN107197519B (en) | Underwater target positioning method based on improved least square support vector machine | |
| CN113068247B (en) | Wireless access point power estimation method based on multilayer perceptron | |
| Barreto et al. | Competitive neural networks for fault detection and diagnosis in 3G cellular systems | |
| CN114390582B (en) | Base station site prediction method and device | |
| CN113395709A (en) | Service coverage analysis method facing user base station poisson distribution |
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 |