Communication network fault analysis method and system based on digital twin

Through digital twin technology, the topology and mirror model of the communication network are built, the node operation data is predicted, and the fault risk level is calculated, which solves the problems of low efficiency and subjectivity of communication network fault detection in the existing technology, and achieves rapid and objective fault detection .

CN117978619BActive Publication Date: 2024-11-26CHINA NAT INST OF STANDARDIZATION
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410184802.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-19
Publication Date
2024-11-26
Estimated Expiration
2044-02-19

AI Technical Summary

Technical Problem

The existing communication network fault detection methods are inefficient and subjective, and cannot effectively monitor and predict faults in real time, affecting network security and communication speed.

Method used

The communication network failure analysis method based on digital twins is adopted, and the topology structure and mirror digital model of the communication network are constructed, and the data prediction is used to predict the node's fault risk level is calculated to achieve rapid detection and detection of faults.

Benefits of technology

It improves the efficiency and objectivity of communication network failure detection, can quickly identify abnormalities, and reduces the risk of information loss and communication paralysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117978619B_ABST
    Figure CN117978619B_ABST
Patent Text Reader

Abstract

The present invention discloses a communication network fault analysis method and system based on digital twins, and relates to the technical field of communication network fault analysis. According to a completely closed test signal parameter processing process, the structural form distribution of the communication network is obtained, the topological structure of the communication network is constructed according to the obtained structural form distribution, the operation data of each node in the topological structure of the communication network is obtained, and a mirror digital model of the communication network is constructed according to the obtained topological structure, and the operation data type of each node is added to the constructed digital model, and the operation data of each node in the topological structure of the communication network in T consecutive cycles are collected and synchronized to the digital model, and the operation data of each node in the T+1th cycle is predicted, and the predicted value and measured value of the operation data of each node are obtained, and the deviation value between the measured value and the predicted value is calculated, and the node fault risk level is determined according to the calculation result of the deviation value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of communication network fault analysis, and in particular to a communication network fault analysis method and system based on digital twins. Background Art

[0002] Communication network failures will not only affect the normal operation of the network and reduce the communication rate, but also affect the network information security, resulting in information loss. In severe cases, the communication network may be paralyzed. Therefore, real-time monitoring of the communication network to detect communication failures and implement communication failure alarms is of great practical significance to communication security.

[0003] Initially, network faults were detected manually. The main method was for technicians to conduct regular safety checks on communication network hardware, rely on test systems to test communication network software, and conduct comprehensive analysis of network status based on network software and hardware conditions to detect network faults. This method not only has low detection efficiency, but also has subjective detection results. With the continuous development of big data technology, related studies have proposed the use of digital twin technology, based on communication data, to build a physical model of the communication network through multidisciplinary, multi-scale, multi-physical quantity and other coupled simulation methods, so as to complete the precise mapping of physical entities in the real world to the mirror digital model of the virtual communication network, forming a scene where the physical world of the physical dimension and the digital world of the information dimension coexist and blend virtual and real, which provides a new research direction for the detection of communication faults, but there is no relevant implementation method in the existing communication fault detection. To this end, we propose a communication network fault analysis method and system based on digital twins. Summary of the invention

[0004] The main purpose of the present invention is to provide a communication network fault analysis method and system based on digital twins, which can effectively solve the problems in the background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] Communication network fault analysis method based on digital twin, including:

[0007] The structure distribution of the communication network is obtained according to the completely closed test signal parameter processing process, and the topological structure of the communication network is constructed according to the obtained structure distribution;

[0008] Obtaining operation data of each node in the topology of the communication network;

[0009] A mirror digital model of the communication network is constructed according to the acquired topological structure, and the operation data type of each node is added to the constructed digital model;

[0010] Collect the operation data of each node in the communication network topology within T consecutive cycles, and synchronously transmit the acquired operation data to the digital model;

[0011] The digital model predicts the operation data of each node in the T+1th cycle to obtain the predicted value of the operation data of each node, wherein the predicted value is calculated by the following formula: ; In the formula, is the predicted value of the jth running data of the i-th node in the topology of the communication network in the T+1th period, is the measured value of the jth operation data of the i-th node in the topological structure of the communication network in the T-th period, and a is a constant coefficient;

[0012] The measured value of the operation data of each node in the T+1th cycle is obtained, the deviation value between the measured value and the predicted value is calculated, and the node failure risk level is determined according to the calculation result of the deviation value, wherein the calculation formula of the deviation value is: ; In the formula, is the deviation between the predicted value and the measured value of the j-th operation data of the i-th node in the topology of the communication network, is the measured value of the jth operation data of the i-th node in the topology of the communication network in the T+1th period;

[0013] When the operating data is a positive indicator, the determination principle of the node failure risk level is:

[0014] when hour;

[0015] If the deviation between the measured value and the predicted value is larger, the node failure risk level is lower;

[0016] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is higher;

[0017] when hour;

[0018] If the deviation between the measured value and the predicted value is larger, the node failure risk level is higher;

[0019] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is lower;

[0020] When the operating data is a negative indicator, the determination principle of the node failure risk level is:

[0021] when hour;

[0022] If the deviation between the measured value and the predicted value is larger, the node failure risk level is higher;

[0023] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is lower;

[0024] when hour;

[0025] If the deviation between the measured value and the predicted value is larger, the node failure risk level is lower;

[0026] The smaller the deviation between the measured value and the predicted value, the higher the node failure risk level.

[0027] The positive indicator is an indicator type in which the operating data is positively correlated with the operating status of the communication network; the negative indicator is an indicator type in which the operating data is negatively correlated with the operating status of the communication network.

[0028] The communication network fault analysis system based on digital twins includes a topology structure construction module, an operation data acquisition module, a digital model construction module, a data synchronization module, an operation data prediction module, and a node fault risk degree determination module;

[0029] The topology structure building module is used to obtain the structure form distribution of the communication network according to the completely closed test signal parameter processing process, and build the topology structure of the communication network according to the obtained structure form distribution;

[0030] The operation data acquisition module is used to obtain the operation data of each node in the topological structure of the communication network;

[0031] The digital model construction module is used to construct a mirror digital model of the communication network according to the acquired topological structure, and add the operation data type of each node to the constructed digital model;

[0032] The data synchronization module is connected to the operation data acquisition module and the digital model construction module, and is used to synchronously transmit the collected operation data of each node in the communication network topology structure within T consecutive cycles to the digital model;

[0033] The operation data prediction module is used to predict the operation data of each node in the T+1th cycle according to the synchronized operation data, wherein the prediction value is calculated by the following formula:

[0034] ; In the formula, The jth operation data of the i-th node in the topology of the communication network is The predicted value within a period, is the measured value of the jth operation data of the i-th node in the topological structure of the communication network in the T-th period, and a is a constant coefficient. The value range of the constant coefficient a is ,in, The specific value of is determined according to the following steps:

[0035] Step s01, obtaining the Tth period front of the node to be evaluated in the communication network topology structure Operation data of each cycle;

[0036] Step s02, set the initial value of the constant coefficient a to The final value is , the step length is ,in, , n is an integer greater than 1;

[0037] Step s03, based on the previous T period The operating data of each cycle is used as the input value, and the initial value is a constant coefficient, and the running data of the Tth period is calculated by the calculation formula of the running data prediction value. ;

[0038] Step s04, increase the initial value constant coefficient One step length , the running data of the Tth cycle is calculated by the calculation formula of the running data prediction value ;

[0039] Step s05, repeat step s04, and calculate the constant coefficient a when each step length increases To final value When , the operation data of the Tth cycle are as follows: , ,,,,, ;

[0040] Step s06, compare operation data , , ,,,,, The difference between the actual value of the operation data of the Tth period and the coefficient with the smallest difference is taken as the constant coefficient a of the calculation formula for the predicted value of this type of operation data of the node;

[0041] in, The value range is , step length The value range is ;

[0042] The node failure risk level determination module is used to calculate the deviation between the measured value and the predicted value, and determine the node failure risk level according to the calculation result of the deviation value;

[0043] The system also includes a memory, a processor, and a computer program stored on the memory and executable on the processor.

[0044] The present invention has the following beneficial effects:

[0045] Compared with the prior art, the technical solution of the present invention obtains the structural form distribution of the communication network according to a completely closed test signal parameter processing process, constructs the topological structure of the communication network according to the obtained structural form distribution, obtains the operating data of each node in the topological structure of the communication network, constructs a mirror digital model of the communication network according to the obtained topological structure, adds the operating data type of each node to the constructed digital model, collects the operating data of each node in the topological structure of the communication network within T consecutive cycles, and synchronously transmits the acquired operating data to the digital model. In the digital model, the operating data of each node in the T+1th cycle is predicted, the predicted value of the operating data of each node is obtained, the measured value of the operating data of each node in the T+1th cycle is obtained, the deviation value between the measured value and the predicted value is calculated, and the node fault risk level is determined according to the calculation result of the deviation value. This solution uses digital twin technology to construct a mirror digital model of the communication network based on communication data, and uses the change of communication data as the detection abnormality judgment standard, which can realize the rapid detection of communication network faults and improve the detection efficiency and objectivity of communication network data faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the communication network fault analysis method based on digital twin of the present invention;

[0047] Figure 2 It is a structural block diagram of the communication network fault analysis system based on digital twin of the present invention;

[0048] Figure 3 This is a logic block diagram of a method for determining the constant coefficient a. DETAILED DESCRIPTION

[0049] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product. Example 1

[0050] The specific implementation process of the technical solution of the present invention includes the following steps:

[0051] Step 1), obtaining the structural form distribution of the communication network according to the completely closed test signal parameter processing process through the topology construction module, and constructing the topology structure of the communication network according to the obtained structural form distribution;

[0052] Step 2), obtaining the operation data of each node in the topological structure of the communication network by running the data acquisition module;

[0053] Step 3), constructing a mirror digital model of the communication network according to the acquired topological structure through a digital model construction module, and adding the running data type of each node to the constructed digital model;

[0054] Step 4), synchronously transmitting the collected operation data of each node in the communication network topology structure within T consecutive cycles to the digital model through the data synchronization module;

[0055] Step 5), the operation data prediction module predicts the operation data of each node in the T+1th cycle according to the synchronized operation data, wherein the prediction value is calculated by the following formula:

[0056] ;

[0057] In the formula, is the predicted value of the jth running data of the i-th node in the topology of the communication network in the T+1th period, is the measured value of the jth operation data of the i-th node in the topological structure of the communication network in the T-th period, a is a constant coefficient, and its value range is The specific value is determined according to the following steps:

[0058] Step s51, obtaining the Tth period front of the node to be evaluated in the communication network topology structure Operation data of each cycle;

[0059] Step s52, set the initial value of the constant coefficient a to The final value is , the step length is ,in, , n is an integer greater than 1, and the range of step length is ;

[0060] Step s53, based on the previous T period The operating data of a cycle is used as input value. The value range is , initial value is a constant coefficient, and the running data of the Tth period is calculated by the calculation formula of the running data prediction value. ;

[0061] Step s54, increase the initial value constant coefficient One step length , the running data of the Tth cycle is calculated by the calculation formula of the running data prediction value ;

[0062] Step s55, repeat step s04, and calculate the constant coefficient a when each step length increases To final value When , the operation data of the Tth cycle are as follows: , ,,,,, ;

[0063] Step s56, compare operation data , , ,,,,, The difference between the actual value of the operation data of the Tth period and the coefficient with the smallest difference is taken as the constant coefficient a of the calculation formula for the predicted value of this type of operation data of the node;

[0064] Step 6), the node failure risk level determination module is used to calculate the deviation between the measured value and the predicted value. The calculation formula is:

[0065] ;

[0066] In the formula, is the deviation between the predicted value and the measured value of the j-th operation data of the i-th node in the topology of the communication network, is the measured value of the jth operation data of the i-th node in the topological structure of the communication network in the T+1th cycle. The node failure risk level is determined according to the calculation result of the deviation value. The determination basis is:

[0067] When the operating data is a positive indicator, the principle for determining the node failure risk level is:

[0068] when hour;

[0069] If the deviation between the measured value and the predicted value is larger, the node failure risk level is lower;

[0070] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is higher;

[0071] when hour;

[0072] If the deviation between the measured value and the predicted value is larger, the node failure risk level is higher;

[0073] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is lower;

[0074] When the operating data is a negative indicator, the principle for determining the node failure risk level is:

[0075] when hour;

[0076] If the deviation between the measured value and the predicted value is larger, the node failure risk level is higher;

[0077] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is lower;

[0078] when hour;

[0079] If the deviation between the measured value and the predicted value is larger, the node failure risk level is lower;

[0080] If the deviation between the measured value and the predicted value is smaller, the node failure risk level is higher;

[0081] It should be noted that a positive indicator is an indicator type in which the operating data is positively correlated with the operating status of the communication network; a negative indicator is an indicator type in which the operating data is negatively correlated with the operating status of the communication network.

[0082] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A communication network fault analysis method based on digital twins, characterized in that: include, The structure distribution of the communication network is obtained according to the completely closed test signal parameter processing process, and the topological structure of the communication network is constructed according to the obtained structure distribution; Obtaining operation data of each node in the topology of the communication network; A mirror digital model of the communication network is constructed according to the acquired topological structure, and the operation data type of each node is added to the constructed digital model; Collect the operation data of each node in the communication network topology within T consecutive cycles, and synchronously transmit the acquired operation data to the digital model; The digital model predicts the operation data of each node in the T+1th cycle to obtain the predicted value of the operation data of each node, wherein the predicted value is calculated by the following formula: ; In the formula, is the predicted value of the jth running data of the i-th node in the topology of the communication network in the T+1th period, is the measured value of the jth operation data of the i-th node in the topology of the communication network in the T-th period, is a constant coefficient; Obtain the measured value of the operation data of each node in the T+1th cycle, calculate the deviation between the measured value and the predicted value, and determine the node failure risk level based on the calculation result of the deviation value; Constant coefficient The value range is ,in, The specific value of is determined according to the following steps: Step s01, obtaining the Tth period front of the node to be evaluated in the communication network topology structure Operation data of each cycle; Step s02, set constant coefficient The initial value is The final value is , the step length is ,in, , n is an integer greater than 1; Step s03, based on the previous T period The operating data of a cycle is used as the input value, and the initial value is a constant coefficient, and the running data of the Tth period is calculated by the calculation formula of the running data prediction value. ; Step s04, increase the initial value constant coefficient One step length , the running data of the Tth cycle is calculated by the calculation formula of the running data prediction value ; Step s05, repeat step s04, and calculate the constant coefficients Each additional step To final value When , the operation data of the Tth cycle are as follows: , ,,,,, ; Step s06, compare operation data , , ,,,,, The difference between the actual value of the running data of the Tth period and the coefficient with the smallest difference is taken as the constant coefficient of the calculation formula of the predicted value of the running data of this type for this node ; The value range is , step length The value range is .

2. The communication network fault analysis method based on digital twin according to claim 1 is characterized in that: The calculation formula of the deviation value is: ; In the formula, is the deviation between the predicted value and the measured value of the j-th operation data of the i-th node in the topology of the communication network, It is the measured value of the j-th operating data of the i-th node in the topology of the communication network in the T+1-th cycle.

3. The communication network fault analysis method based on digital twin according to claim 1 is characterized in that: When the operating data is a positive indicator, the determination principle of the node failure risk level is: when hour; If the deviation between the measured value and the predicted value is larger, the node failure risk level is lower; If the deviation between the measured value and the predicted value is smaller, the node failure risk level is higher; when hour; If the deviation between the measured value and the predicted value is larger, the node failure risk level is higher; If the deviation between the measured value and the predicted value is smaller, the node failure risk level is lower; When the operating data is a negative indicator, the determination principle of the node failure risk level is: when hour; If the deviation between the measured value and the predicted value is larger, the node failure risk level is higher; If the deviation between the measured value and the predicted value is smaller, the node failure risk level is lower; when hour; If the deviation between the measured value and the predicted value is larger, the node failure risk level is lower; The smaller the deviation between the measured value and the predicted value, the higher the node failure risk level.

4. The communication network fault analysis method based on digital twin according to claim 3 is characterized in that: The positive indicator is an indicator type in which the operating data is positively correlated with the operating status of the communication network; the negative indicator is an indicator type in which the operating data is negatively correlated with the operating status of the communication network.

5. The communication network fault analysis system based on digital twin is characterized by: The system is used to implement the communication network fault analysis method based on digital twins as described in any one of claims 1 to 4, including a topology structure construction module, an operation data acquisition module, a digital model construction module, a data synchronization module, an operation data prediction module, and a node fault risk degree determination module; The topology structure building module is used to obtain the structure form distribution of the communication network according to the completely closed test signal parameter processing process, and build the topology structure of the communication network according to the obtained structure form distribution; The operation data acquisition module is used to obtain the operation data of each node in the topological structure of the communication network; The digital model construction module is used to construct a mirror digital model of the communication network according to the acquired topological structure, and add the operation data type of each node to the constructed digital model; The data synchronization module is connected to the operation data acquisition module and the digital model construction module, and is used to synchronously transmit the collected operation data of each node in the communication network topology structure within T consecutive cycles to the digital model; The operation data prediction module is used to predict the operation data of each node in the T+1th cycle according to the synchronized operation data, wherein the prediction value is calculated by the following formula: ; In the formula, is the predicted value of the jth running data of the i-th node in the topology of the communication network in the T+1th period, is the measured value of the jth operation data of the i-th node in the topology of the communication network in the T-th period, is a constant coefficient; The node failure risk level determination module is used to calculate the deviation value between the measured value and the predicted value, and determine the node failure risk level according to the calculation result of the deviation value.

6. Communication network fault analysis system based on digital twin, characterized by: The system further comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 4 when executing the program.