Intelligent operation and maintenance fault diagnosis system based on communication network

Abstract

The invention discloses an intelligent operation and maintenance fault diagnosis system based on a communication network, which belongs to the technical field of communication networks and comprises a data acquisition preprocessing module, a network dynamic evolution module, a quantum auxiliary diagnosis module, a fault prediction evaluation module, a fault decision module, a fault operation and maintenance module and a fault feedback module. By integrating the data acquisition and preprocessing module, the network dynamic evolution module and the quantum auxiliary diagnosis module, the system can acquire and process the state information of a communication network in real time, and quickly position and accurately identify a fault scene in combination with the high efficiency of quantum calculation, so that the fault diagnosis time is remarkably shortened, the diagnosis accuracy is improved, and the fault diagnosis efficiency is improved. Through the fault prediction and evaluation module in combination with the results of network dynamic evolution and quantum-assisted diagnosis, prediction of a plurality of future network states can be generated, different fault scenes are simulated for evaluation, potential risks are effectively predicted, and meanwhile, through risk evaluation and sorting, operation and maintenance personnel are helped to preferentially process high-risk scenes, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of communication networks, and specifically refers to an intelligent operation and maintenance fault diagnosis system based on communication networks. Background Art

[0002] With the rapid development of communication technology, the scale of networks is becoming larger and larger, and the structure is becoming more and more complex. Traditional operation and maintenance methods can no longer meet the needs of efficient and accurate fault diagnosis. Existing systems mostly rely on manual inspections and expert experience, and have problems such as slow response speed, high misdiagnosis rate, and high resource consumption.

[0003] However, the intelligent operation and maintenance fault diagnosis of existing communication networks still has certain defects. The existing intelligent operation and maintenance fault diagnosis of communication networks relies on a single algorithm or model. When faced with complex and changeable communication networks, these methods often take a long time to collect enough data and analyze it, resulting in slow response speed of fault handling, affecting the availability and false alarm rate of the network. Only focusing on static data analysis cannot adapt well to changes in network structure and traffic patterns, resulting in inaccurate diagnosis results. Therefore, an intelligent operation and maintenance fault diagnosis system based on communication networks is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent operation and maintenance fault diagnosis system based on a communication network to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent operation and maintenance fault diagnosis system based on a communication network, comprising a data acquisition preprocessing module, a network dynamic evolution module, a quantum-assisted diagnosis module, a fault prediction and evaluation module, a fault decision module, a fault operation and maintenance module, and a fault feedback module;

[0006] The data acquisition preprocessing module is used to obtain the communication network operation status information in real time from various sensors, probes, and log records deployed in the network, and perform preliminary cleaning and preprocessing;

[0007] The network dynamic evolution module is used to construct a dynamic evolution model of the communication network and simulate the behavior mode of the network under normal operation and failure state;

[0008] The quantum-assisted diagnosis module is used to quickly find possible fault scenarios and quickly locate and accurately identify faults in combination with the network dynamic evolution module;

[0009] The fault prediction and evaluation module predicts and evaluates the communication network status based on the results of the network dynamic evolution module and the quantum-assisted diagnosis module;

[0010] The fault decision module generates the optimal fault handling solution and resource allocation plan according to the results of the quantum-assisted diagnosis module and the fault prediction results.

[0011] Among them, the data acquisition preprocessing module obtains the communication network operation status information in real time from various sensors, probes, and log records deployed in the network, performs data cleaning, data formatting, data fusion and data compression on the collected communication network operation status information, and stores the preprocessed data in the cloud database.

[0012] The network dynamic evolution module constructs a dynamic evolution model of the communication network according to the data processed by the data acquisition preprocessing module. The node state in the communication network is s i (t), the edge weight is w ij (t), and construct the weight matrix W(t), the node state is s i (t) is specifically expressed as:

[0013]

[0014] In the formula, s i (t) represents the state of each node i at time t, s i,j (t) represents the value of the jth state variable of node i at time t;

[0015] The network status changes are obtained based on the node status and edge weights, and the implementation formula is:

[0016]

[0017] In the formula, P represents the network state transition matrix, which describes the probability of the network state transferring from one time step to the next time step, p ij represents the probability of transferring to network state j at the next time step t+1 under the condition that the network is in state i at time t, where p ij It is expressed as:

[0018] p ij =Pr(s(t+1)=j|s(t)=i);

[0019] According to the network state transfer matrix, the current network state vector s(t) and the weight matrix W(t), the network state vector of the next time step is evolved. The implementation formula is:

[0020] s(t+1)=P·s(t)+g(W(t),s(t)),

[0021] In the formula, s(t+1) represents the network state vector at time t+1, and g(W(t), s(t)) represents the influence of the weight matrix on the current network state vector.

[0022] The network dynamic evolution module defines the benchmark of the normal operation state of the network according to the mean and variance of historical data. The mean of historical data is μ, which represents the average network state vector of historical data, and the variance is σ. 2 , represents the degree of fluctuation of the network state vector relative to the mean. Assuming the time span of historical data is T, the mean realization formula is:

[0023]

[0024] The variance realization formula is:

[0025]

[0026] When the absolute value of the node state deviation from the mean μ is greater than k times the standard deviation σ, it is judged to be an abnormal state, expressed as IF|s(t)-μ|>kσ, where σ is expressed as

[0027] According to the difference between the predicted value and the actual value of the network status, the implementation formula is:

[0028]

[0029] In the formula, E represents the average value of the square difference between the predicted value and the actual value of the network status, represents the predicted network state vector, Represents the actual network state vector s(t) and the predicted network state vector The square of the difference between them. When the difference is too large, re-evolution training is performed for optimization.

[0030] The quantum-assisted diagnosis module encodes the state of each node in the communication network into a quantum bit state and performs data conversion. The implementation formula is:

[0031]

[0032] In the formula, X represents the network node status dataset, x i (t) represents the state of node i at time t, and N represents the total number of network nodes;

[0033] Assume an energy function H and a quantum random walk operator U to reflect the status of each node and edge in the communication network. The energy function and quantum random walk operator are constructed through the network node status data set X. The most likely fault state is found through the energy function. The implementation formula is:

[0034]

[0035] In the formula, h irepresents the local field of network node i, the stability of network node i in normal state, J ij represents the coupling strength between network node i and network node j, Represents the state of network node i, and the energy minimization state is found through quantum annealing, which is realized as

[0036] According to the optimal state obtained by quantum annealing, the fault propagation path is found in the communication network, and the implementation formula is:

[0037]

[0038] In the formula, exp represents the exponential function, i represents the imaginary unit, and i satisfies 2 =-1, A ij represents the transition probability from network node i to network node j, and updates the network state vector to |Ψt+1>=U|Ψt>;

[0039] According to the updated network status, the fault source node is located, and the implementation formula is:

[0040]

[0041] In the formula, Fs represents the fault source node, |<i|ΨT> >| 2 It represents the square of the probability amplitude of network node i at time T. The fault source information obtained is combined with the network dynamic evolution results for diagnosis.

[0042] The fault prediction and evaluation module predicts and evaluates the communication network status according to the results of the network dynamic evolution module and the quantum-assisted diagnosis module. According to the latest status s(t) of the network dynamic evolution module, the network state vector of the fault prediction module is initialized as According to the network state vector, the network state at the next time point is predicted, and the implementation formula is:

[0043]

[0044] In the formula, represents the predicted state vector of the network at time t+1, f represents the time series prediction function, and s(tk) represents the state vector of the network at time tk;

[0045] Generate multiple future network states based on the prediction results, simulate different fault scenarios and evaluate the network state R under each scenario i =g(S si ,w),S si Represents multiple simulation scenarios, and calculates the risk level based on the assessment results. The implementation formula is:

[0046]

[0047] In the formula, r i represents the risk level of the i-th scenario, f i represents the risk assessment function at time step j, It represents the predicted network state vector of the network at time t+j, n represents the time step of the simulation, and each scenario is sorted according to the risk level and risk assessment is performed.

[0048] Among them, the fault decision module receives fault diagnosis information and prediction results from the quantum-assisted diagnosis module and the fault prediction and evaluation module, sets multiple optimization goals according to business needs and network status, generates multiple feasible fault handling solutions based on the optimization goal results, and comprehensively evaluates each alternative solution.

[0049] The fault operation and maintenance module actually performs fault handling operations according to the solution generated by the fault decision module, coordinates resources during the execution process, and records the specific content and results of each operation.

[0050] Among them, the fault feedback module updates and adjusts the data information of the network dynamic evolution module and the quantum-assisted diagnosis module in real time for optimization according to the real-time feedback of the fault operation and maintenance module and the changes in network status.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. In order to solve the problems of slow fault diagnosis, inaccurate positioning, insufficient prediction ability and low decision-making efficiency, and to improve the accuracy and efficiency of fault prediction and diagnosis, the present invention integrates data acquisition preprocessing, network dynamic evolution and quantum-assisted diagnosis modules. The system can acquire and process the status information of the communication network in real time. Combined with the high efficiency of quantum computing, it can quickly locate and accurately identify fault scenarios, significantly shorten the fault diagnosis time and improve the accuracy of diagnosis.

[0053] 2. The present invention combines the results of network dynamic evolution and quantum-assisted diagnosis through the fault prediction and evaluation module to generate multiple predictions of future network states, simulate different fault scenarios for evaluation, and effectively predict potential risks. At the same time, through risk assessment and sorting, it helps operation and maintenance personnel to prioritize high-risk scenarios and improve fault diagnosis accuracy and operation and maintenance efficiency;

[0054] 3. The present invention constructs a dynamic evolution model of the communication network through the network dynamic evolution module, simulates the behavior mode of the network under normal operation and fault conditions, predicts network state changes according to node states and edge weights, and improves the accuracy and reliability of network state prediction;

[0055] 4. The present invention uses a quantum-assisted diagnosis module to quickly find possible fault scenarios based on the high efficiency of quantum computing, combines the network dynamic evolution model to achieve rapid fault location and accurate identification, and constructs a fault state diagnosis model through energy functions and quantum random walk operators to improve diagnostic efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a structural schematic diagram of an intelligent operation and maintenance fault diagnosis system based on a communication network of the present invention;

[0057] Figure 2 It is an operation flow chart of the network dynamic evolution module of the intelligent operation and maintenance fault diagnosis system based on the communication network of the present invention;

[0058] Figure 3 This is an operation flow chart of the quantum-assisted diagnosis module of the intelligent operation and maintenance fault diagnosis system based on the communication network of the present invention;

[0059] Figure 4 The present invention is a flowchart of the operation of the fault prediction and evaluation module of the intelligent operation and maintenance fault diagnosis system based on the communication network. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Example

[0062] See also Figure 1-Figure 4 As shown, the present invention provides a technical solution: including a data acquisition preprocessing module, a network dynamic evolution module, a quantum-assisted diagnosis module, a fault prediction and evaluation module, a fault decision module, a fault operation and maintenance module, and a fault feedback module;

[0063] The data acquisition preprocessing module is used to obtain the communication network operation status information in real time from various sensors, probes, and log records deployed in the network, and perform preliminary cleaning and preprocessing;

[0064] The network dynamic evolution module is used to construct a dynamic evolution model of the communication network and simulate the behavior mode of the network under normal operation and failure state;

[0065] The quantum-assisted diagnosis module is used to quickly find possible fault scenarios and quickly locate and accurately identify faults in combination with the network dynamic evolution module;

[0066] The fault prediction and evaluation module predicts and evaluates the communication network status based on the results of the network dynamic evolution module and the quantum-assisted diagnosis module;

[0067] The fault decision module generates the optimal fault handling solution and resource allocation plan according to the results of the quantum-assisted diagnosis module and the fault prediction results.

[0068] Among them, the data acquisition preprocessing module obtains the communication network operation status information in real time from various sensors, probes, and log records deployed in the network, performs data cleaning, data formatting, data fusion and data compression on the collected communication network operation status information, and stores the preprocessed data in the cloud database.

[0069] The network dynamic evolution module constructs a dynamic evolution model of the communication network according to the data processed by the data acquisition preprocessing module. The node state in the communication network is s i (t), the edge weight is w ij (t), and construct the weight matrix W(t), the node state is s i (t) is specifically expressed as:

[0070]

[0071] In the formula, s i (t) represents the state of each node i at time t, s i,j (t) represents the value of the jth state variable of node i at time t;

[0072] The network status changes are obtained based on the node status and edge weights, and the implementation formula is:

[0073]

[0074] In the formula, P represents the network state transition matrix, which describes the probability of the network state transferring from one time step to the next time step, p ij represents the probability of transferring to network state j at the next time step t+1 under the condition that the network is in state i at time t, where p ij It is expressed as:

[0075] p ij =Pr(s(t+1)=j|s(t)=i);

[0076] According to the network state transfer matrix, the current network state vector s(t) and the weight matrix W(t), the network state vector of the next time step is evolved. The implementation formula is:

[0077] s(t+1)=P·s(t)+g(W(t),s(t)),

[0078] In the formula, s(t+1) represents the network state vector at time t+1, and g(W(t), s(t)) represents the influence of the weight matrix on the current network state vector.

[0079] The network dynamic evolution module defines the benchmark of the normal operation state of the network according to the mean and variance of historical data. The mean of historical data is μ, which represents the average network state vector of historical data, and the variance is σ. 2 , represents the degree of fluctuation of the network state vector relative to the mean. Assuming the time span of historical data is T, the mean realization formula is:

[0080]

[0081] The variance realization formula is:

[0082]

[0083] When the absolute value of the node state deviation from the mean μ is greater than k times the standard deviation σ, it is judged to be an abnormal state, expressed as IF|s(t)-μ|>kσ, where σ is expressed as

[0084] According to the difference between the predicted value and the actual value of the network status, the implementation formula is:

[0085]

[0086] In the formula, E represents the average value of the square difference between the predicted value and the actual value of the network status, represents the predicted network state vector, Represents the actual network state vector s(t) and the predicted network state vector The square of the difference between them. When the difference is too large, re-evolution training is performed for optimization.

[0087] The quantum-assisted diagnosis module encodes the state of each node in the communication network into a quantum bit state and performs data conversion. The implementation formula is:

[0088]

[0089] In the formula, X represents the network node status dataset, x i (t) represents the state of node i at time t, and N represents the total number of network nodes;

[0090] Assume an energy function H and a quantum random walk operator U to reflect the status of each node and edge in the communication network. The energy function and quantum random walk operator are constructed through the network node status data set X. The most likely fault state is found through the energy function. The implementation formula is:

[0091]

[0092] In the formula, h i represents the local field of network node i, the stability of network node i in normal state, J ij represents the coupling strength between network node i and network node j, Represents the state of network node i, and the energy minimization state is found through quantum annealing, which is realized as

[0093] According to the optimal state obtained by quantum annealing, the fault propagation path is found in the communication network, and the implementation formula is:

[0094]

[0095] In the formula, exp represents the exponential function, i represents the imaginary unit, and i satisfies 2 =-1, A ij represents the transition probability from network node i to network node j, and updates the network state vector to |Ψt+1>=U|Ψt>;

[0096] According to the updated network status, the fault source node is located, and the implementation formula is:

[0097]

[0098] In the formula, Fs represents the fault source node, |<i|ΨT> >| 2 It represents the square of the probability amplitude of network node i at time T. The fault source information obtained is combined with the network dynamic evolution results for diagnosis.

[0099] The fault prediction and evaluation module predicts and evaluates the communication network status according to the results of the network dynamic evolution module and the quantum-assisted diagnosis module. According to the latest status s(t) of the network dynamic evolution module, the network state vector of the fault prediction module is initialized as According to the network state vector, the network state at the next time point is predicted, and the implementation formula is:

[0100]

[0101] In the formula, represents the predicted state vector of the network at time t+1, f represents the time series prediction function, and s(tk) represents the state vector of the network at time tk;

[0102] Generate multiple future network states based on the prediction results, simulate different fault scenarios and evaluate the network state R under each scenario i =g(S si,w),S si Represents multiple simulation scenarios, and calculates the risk level based on the assessment results. The implementation formula is:

[0103]

[0104] In the formula, r i represents the risk level of the i-th scenario, f i represents the risk assessment function at time step j, It represents the predicted network state vector of the network at time t+j, n represents the time step of the simulation, and each scenario is sorted according to the risk level and risk assessment is performed.

[0105] Among them, the fault decision module receives fault diagnosis information and prediction results from the quantum-assisted diagnosis module and the fault prediction and evaluation module, sets multiple optimization goals according to business needs and network status, generates multiple feasible fault handling solutions based on the optimization goal results, and comprehensively evaluates each alternative solution.

[0106] The fault operation and maintenance module actually performs fault handling operations according to the solution generated by the fault decision module, coordinates resources during the execution process, and records the specific content and results of each operation.

[0107] Among them, the fault feedback module updates and adjusts the data information of the network dynamic evolution module and the quantum-assisted diagnosis module in real time for optimization according to the real-time feedback of the fault operation and maintenance module and the changes in network status.

[0108] In this example, specifically: the network dynamic evolution module constructs a dynamic evolution model of the communication network according to the data processed by the data acquisition preprocessing module, assuming that the node state in the communication network is s i (t), the edge weight is w ij (t), and construct the weight matrix W(t), the node state is s i (t) is specifically expressed as:

[0109]

[0110] In the formula, s i (t) represents the state of each node i at time t, s i,j (t) represents the value of the jth state variable of node i at time t;

[0111] The network status changes are obtained based on the node status and edge weights, and the implementation formula is:

[0112]

[0113] In the formula, P represents the network state transition matrix, which describes the probability of the network state transferring from one time step to the next time step, p ij represents the probability of transferring to network state j at the next time step t+1 under the condition that the network is in state i at time t, where p ij It is expressed as:

[0114] p ij =Pr(s(t+1)=j|s(t)=i);

[0115] According to the network state transfer matrix, the current network state vector s(t) and the weight matrix W(t), the network state vector of the next time step is evolved. The implementation formula is:

[0116] s(t+1)=P·s(t)+g(W(t),s(t)),

[0117] In the formula, s(t+1) represents the network state vector at time t+1, and g(W(t), s(t)) represents the influence of the weight matrix on the current network state vector.

[0118] In this example, specifically: the network dynamic evolution module defines the benchmark of the normal operation state of the network according to the mean and variance of historical data, assuming that the mean of historical data is μ, which represents the average network state vector of historical data, and the variance is σ 2 , represents the degree of fluctuation of the network state vector relative to the mean. Assuming the time span of historical data is T, the mean realization formula is:

[0119]

[0120] The variance realization formula is:

[0121]

[0122] When the absolute value of the node state deviation from the mean μ is greater than k times the standard deviation σ, it is judged to be an abnormal state, expressed as IF|s(t)-μ|>kσ, where σ is expressed as

[0123] According to the difference between the predicted value and the actual value of the network status, the implementation formula is:

[0124]

[0125] In the formula, E represents the average value of the square difference between the predicted value and the actual value of the network status, represents the predicted network state vector, Represents the actual network state vector s(t) and the predicted network state vector The square of the difference between them. When the difference is too large, re-evolution training is performed for optimization.

[0126] In this example, specifically: the fault prediction and evaluation module predicts and evaluates the communication network state according to the results of the network dynamic evolution module and the quantum-assisted diagnosis module. According to the latest state s(t) of the network dynamic evolution module, the network state vector of the fault prediction module is initialized as According to the network state vector, the network state at the next time point is predicted, and the implementation formula is:

[0127]

[0128] In the formula, represents the predicted state vector of the network at time t+1, f represents the time series prediction function, and s(tk) represents the state vector of the network at time tk;

[0129] Generate multiple future network states based on the prediction results, simulate different fault scenarios and evaluate the network state R under each scenario i =g(S si ,w),S si Represents multiple simulation scenarios, and calculates the risk level based on the assessment results. The implementation formula is:

[0130]

[0131] In the formula, r i represents the risk level of the i-th scenario, f i represents the risk assessment function at time step j, It represents the predicted network state vector of the network at time t+j, n represents the time step of the simulation, and each scenario is sorted according to the risk level and risk assessment is performed.

[0132] Working principle: By obtaining real-time information on the operation status of the communication network from various sensors, probes, logs, etc. deployed in the network, the collected data is cleaned, integrated and compressed, and then the pre-processed data is stored in the cloud database;

[0133] The network dynamic evolution module builds a dynamic evolution model of the communication network based on the data provided by the data acquisition preprocessing module, defines the node status and edge weights, builds the weight matrix and the network state transfer matrix, defines the benchmark of the normal operation status of the network based on historical data, and predicts and evolves the network state of the next time step based on the network state transfer matrix and the current network state. By comparing the predicted value with the actual value, the model accuracy is evaluated, and the model is retrained and optimized when necessary. The quantum-assisted diagnosis module encodes the network node status into quantum bits, and defines the energy function and quantum random walk operator. The quantum annealing algorithm is used to find the energy minimization state, that is, the most likely fault state. Then, based on the results of quantum calculation, the fault propagation path is found in the communication network and the fault source node is located. The fault prediction and evaluation module is based on the network dynamic evolution module and The results of the quantum-assisted diagnosis module predict the future state of the communication network and generate multiple possible future network state scenarios. For each scenario, risk assessment is performed and the risk level is calculated. The fault decision module receives the diagnostic information and prediction results of the quantum-assisted diagnosis module and the fault prediction and evaluation module, and sets multiple optimization goals based on business needs and network status. Based on these goals, it generates multiple feasible fault handling plans, and conducts a comprehensive evaluation of each plan to select the optimal plan. The fault operation and maintenance module actually performs fault handling operations according to the plan generated by the fault decision module. During the execution process, it coordinates the required resources and records the specific content and results of each operation. The fault feedback module updates and adjusts the data information of the network dynamic evolution module and the quantum-assisted diagnosis module in real time based on the real-time feedback of the fault operation and maintenance module and changes in network status.

[0134] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0135] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An intelligent operation and maintenance fault diagnosis system based on a communication network, characterized by: It includes data acquisition preprocessing module, network dynamic evolution module, quantum-assisted diagnosis module, fault prediction and evaluation module, fault decision module, fault operation and maintenance module and fault feedback module; The data acquisition preprocessing module is used to obtain the communication network operation status information in real time from various sensors, probes, and log records deployed in the network, and perform preliminary cleaning and preprocessing; The network dynamic evolution module is used to construct a dynamic evolution model of the communication network and simulate the behavior mode of the network under normal operation and failure state; The quantum-assisted diagnosis module is used to quickly find suspected fault scenarios and combine with the network dynamic evolution module to quickly locate and accurately identify faults; The fault prediction and evaluation module predicts and evaluates the communication network status based on the results of the network dynamic evolution module and the quantum-assisted diagnosis module; The fault decision module generates the optimal fault handling solution and resource allocation plan according to the results of the quantum-assisted diagnosis module and the fault prediction results.

2. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1 is characterized in that: The data acquisition preprocessing module acquires the communication network operation status information in real time from various sensors, probes, and log records deployed in the network, performs data cleaning, data formatting, data fusion, and data compression on the collected communication network operation status information, and stores the preprocessed data in the cloud database.

3. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1 is characterized in that: The network dynamic evolution module constructs a dynamic evolution model of the communication network based on the data processed by the data acquisition preprocessing module. Suppose the node state in the communication network is s i (t), the edge weight is w ij (t), and construct the weight matrix W(t), the node state is s i (t) is specifically expressed as: In the formula, s i (t) represents the state of each node i at time t, s i,j (t) represents the value of the jth state variable of node i at time t; The network status changes are obtained based on the node status and edge weights, and the implementation formula is: P=[p ij ], In the formula, P represents the network state transition matrix, which describes the probability of the network state transferring from one time step to the next time step, p ij represents the probability of transferring to network state j at the next time step t+1 under the condition that the network is in state i at time t, where p ij It is expressed as: p ij =Pr(s(t+1)=j|s(t)=i); According to the network state transfer matrix, the current network state vector s(t) and the weight matrix W(t), the network state vector of the next time step is evolved. The implementation formula is: s(t+1)=P·s(t)+g(W(t),s(t)), In the formula, s(t+1) represents the network state vector at time t+1, and g(W(t), s(t)) represents the influence of the weight matrix on the current network state vector.

4. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 3 is characterized in that: The network dynamic evolution module defines the benchmark of the normal operation state of the network according to the mean and variance of historical data. The mean of historical data is μ, which represents the average network state vector of historical data, and the variance is σ. 2 , represents the degree of fluctuation of the network state vector relative to the mean. Assuming the time span of historical data is T, the mean realization formula is: The variance realization formula is: When the absolute value of the node state deviation from the mean μ is greater than k times the standard deviation σ, it is judged to be an abnormal state, expressed as IF|s(t)-μ|>kσ, where σ is expressed as According to the difference between the predicted value and the actual value of the network status, the implementation formula is: In the formula, E represents the average value of the square difference between the predicted value and the actual value of the network status, represents the predicted network state vector, Represents the actual network state vector s(t) and the predicted network state vector The square of the difference between them. When the difference is too large, re-evolution training is performed for optimization.

5. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1 is characterized in that: The quantum-assisted diagnosis module encodes the state of each node in the communication network into a quantum bit state and performs data conversion. The implementation formula is: In the formula, X represents the network node status dataset, x i (t) represents the state of node i at time t, and N represents the total number of network nodes; Assume an energy function H and a quantum random walk operator U to reflect the status of each node and edge in the communication network. The energy function and quantum random walk operator are constructed through the network node status data set X. The most likely fault state is found through the energy function. The implementation formula is: In the formula, h i represents the local field of network node i, the stability of network node i in normal state, J ij represents the coupling strength between network node i and network node j, Represents the state of network node i, and the energy minimization state is found through quantum annealing, which is realized as According to the optimal state obtained by quantum annealing, the fault propagation path is found in the communication network, and the implementation formula is: In the formula, exp represents the exponential function, i represents the imaginary unit, and i satisfies 2 =-1, A ij represents the transition probability from network node i to network node j, and updates the network state vector to |Ψt+1>=U|Ψt>; According to the updated network status, the fault source node is located, and the implementation formula is: In the formula, Fs represents the fault source node, |<i|ΨT> >| 2 It represents the square of the probability amplitude of network node i at time T. The fault source information obtained is combined with the network dynamic evolution results for diagnosis.

6. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1, characterized in that: The fault prediction and evaluation module predicts and evaluates the communication network status according to the results of the network dynamic evolution module and the quantum-assisted diagnosis module. According to the latest status s(t) of the network dynamic evolution module, the network state vector of the fault prediction module is initialized as According to the network state vector, the network state at the next time point is predicted, and the implementation formula is: In the formula, represents the predicted state vector of the network at time t+1, f represents the time series prediction function, and s(tk) represents the state vector of the network at time tk; Generate multiple future network states based on the prediction results, simulate different fault scenarios and evaluate the network state R under each scenario i =g(S si ,w),S si Represents multiple simulation scenarios, and calculates the risk level based on the assessment results. The implementation formula is: In the formula, r i represents the risk level of the i-th scenario, f i represents the risk assessment function at time step j, It represents the predicted network state vector of the network at time t+j, n represents the time step of the simulation, and each scenario is sorted according to the risk level and risk assessment is performed.

7. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1, characterized in that: The fault decision module receives fault diagnosis information and prediction results from the quantum-assisted diagnosis module and the fault prediction and evaluation module, sets multiple optimization goals according to business requirements and network status, generates multiple feasible fault handling solutions based on the optimization goal results, and comprehensively evaluates each alternative solution.

8. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1, characterized in that: The fault operation and maintenance module actually performs fault handling operations according to the solution generated by the fault decision module, coordinates resources during the execution process, and records the specific content and results of each operation.

9. The intelligent operation and maintenance fault diagnosis system based on communication network according to claim 1, characterized in that: The fault feedback module updates and adjusts the data information of the network dynamic evolution module and the quantum-assisted diagnosis module in real time for optimization according to the real-time feedback of the fault operation and maintenance module and the change of network status.

Images