Power optical communication network fault perception method, device and equipment and storage medium

Abstract

The application provides a power optical communication network fault perception method, device, equipment and storage medium, the method comprises the following steps: collecting power optical communication network operation state data; selecting corresponding membership function model to calculate index layer score; constructing index layer fuzzy judgment matrix and calculating index layer element weight; calculating criterion layer score based on index layer score and weight; constructing criterion layer fuzzy judgment matrix and calculating criterion layer element weight; calculating power optical communication network fault perception score based on criterion layer score and weight; uploading reliability operation state data to power optical communication digital twin network for training digital twin model to predict future operation data of power optical communication network, and predicting power optical communication network fault perception based on prediction data. The application can perceive and warn power optical communication network fault, and effectively improve the accuracy of power optical communication network fault perception.

Description

Technical Field

[0001] This invention relates to the field of fault detection technology, and in particular to a fault detection method, apparatus, device, and storage medium for power optical communication networks. Background Technology

[0002] As a crucial component of power communication networks, power optical communication networks carry the transmission of various service data, placing higher demands on speed, bandwidth, and reliability. The integration of new power equipment into the power grid significantly increases the difficulty of processing massive amounts of power data, posing a development bottleneck for fault detection and early warning systems. Achieving fault detection in power optical communication networks requires extracting reasonable and effective analytical data based on numerous evaluation indicators, enabling the system's control and decision-making units to accurately understand the operational status of each link in the power grid. However, the performance evaluation indicators for power optical communication networks are diverse, with varying correlations between different indicators. Traditional fault detection based on the analytic hierarchy process (AHP) is highly subjective and cannot objectively reflect the true situation of network faults.

[0003] Existing technologies have the following problems: 1. Existing fault perception methods based on deep neural networks are too complex, especially when new power equipment is connected to the power grid, i.e., when the topology of the power optical communication network changes, the original neural network is no longer applicable and needs to be retrained. Furthermore, they can only perceive faults after they occur, and cannot provide early warnings. 2. Existing fault perception methods based on the analytic hierarchy process (AHP) are highly subjective and cannot objectively reflect the true situation of faults in the power optical communication network. They also cannot select an appropriate number of indicators based on the actual operation of the network, resulting in low accuracy in fault perception. Summary of the Invention

[0004] The present invention aims to provide a method, apparatus, device and storage medium for fault detection in power optical communication networks, so as to solve the above-mentioned technical problems, thereby enabling fault detection and early warning in power optical communication networks and improving the accuracy of fault detection in power optical communication networks.

[0005] To address the aforementioned technical problems, this invention provides a fault detection method for power optical communication networks, comprising:

[0006] Collect operational status data of the power optical communication network; wherein, the multi-level fault perception index system of the power optical communication network includes a target layer, a criterion layer, and an index layer;

[0007] The membership function model corresponding to the type of each element in the indicator layer is selected to calculate the score of each indicator element in the indicator layer;

[0008] A fuzzy judgment matrix for the indicator layer is constructed based on the scores of each indicator element in the indicator layer. The fuzzy judgment matrix for the indicator layer is then subjected to a consistency transformation, and the weights of the indicator layer elements are calculated.

[0009] The scores of each criterion element in the criterion layer are calculated based on the scores of each criterion element in the criterion layer and the weights of the criterion elements in the criterion layer.

[0010] A fuzzy judgment matrix for the criterion layer is constructed based on the scores of each indicator element in the criterion layer. The fuzzy judgment matrix for the criterion layer is then subjected to a consistency transformation, and the weights of the criterion layer elements are calculated.

[0011] The fault perception score of the power optical communication network is calculated based on the scores of each criterion element in the criterion layer and the weights of the criterion layer elements.

[0012] Based on the fault perception score of the power optical communication network, reliability operation status data is selected and uploaded to the power optical communication digital twin network for training the digital twin model to predict the future operation data of the power optical communication network. The multi-level fault perception index system is then used to perform fault perception prediction on the power optical communication network based on the predicted data.

[0013] Furthermore, the target layer represents the power optical communication network body; the criteria layer includes resource usage criteria, network operation level criteria, service support criteria, and communication network operation and maintenance criteria.

[0014] Furthermore, within the aforementioned indicator layer, the indicator elements belonging to resource usage criteria include: packet loss rate, online rate, packet error rate, average transmission rate, response time, and channel redundancy; the indicator elements belonging to network operation level criteria include: end-to-end transmission delay, optical transmission equipment failure duration, optical switch equipment failure duration, communication power supply equipment failure duration, optical cable failure duration, and data acquisition module failure duration; the indicator elements belonging to service support criteria include: service importance, number of service interruptions, average service interruption duration, service recoverability, service transmission stability, and service success rate; and the indicator elements belonging to communication network operation and maintenance criteria include: communication network investment amount, on-duty maintenance personnel, equipment maintenance execution rate, spare parts and spare components configuration quantity, network attack frequency, and security mechanism completeness.

[0015] Furthermore, the index element types of the index layer include positively correlated index elements, negatively correlated index elements, and interval-related index elements. Among them, for positively correlated index elements, the larger the value, the higher the reliability of the power optical communication network and the lower the probability of potential failures. For negatively correlated index elements, the smaller the value, the higher the reliability of the power optical communication network and the lower the probability of potential failures. For interval-related index elements, when the value is within a preset range, the power optical communication network has relatively high reliability and a lower probability of potential failures. When the value deviates further from the preset range, the power optical communication network has lower reliability and a higher probability of potential failures.

[0016] Furthermore, the consistency transformation of the fuzzy judgment matrix of the indicator layer specifically involves:

[0017] If it is determined that the fuzzy judgment matrix of the indicator layer does not meet the preset consistency condition, then the fuzzy judgment matrix of the indicator layer is converted into the consistency judgment matrix of the indicator layer based on the preset conversion formula.

[0018] The consistency transformation of the fuzzy judgment matrix of the criterion layer is specifically as follows:

[0019] If the fuzzy judgment matrix of the criterion layer is determined not to meet the preset consistency condition, then the fuzzy judgment matrix of the criterion layer is converted into a consistent judgment matrix of the criterion layer based on the preset conversion formula.

[0020] Furthermore, the step of selecting the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer specifically includes:

[0021] Based on the type of each element in the indicator layer, select the corresponding membership function model, and calculate the membership degree of each element in the indicator layer to the three fuzzy evaluations of good, medium and poor based on the corresponding membership function model;

[0022] The score of each indicator element in the indicator layer is calculated based on the calculated membership degree of the indicator layer elements.

[0023] The present invention also provides a fault detection device for power optical communication networks, comprising:

[0024] The data acquisition module is used to collect operational status data of the power optical communication network; wherein, the multi-level fault perception index system of the power optical communication network includes a target layer, a criterion layer, and an index layer;

[0025] The indicator layer element scoring module is used to select the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer.

[0026] The indicator layer weight calculation module is used to construct an indicator layer fuzzy judgment matrix based on the scores of each indicator element in the indicator layer, perform consistency transformation on the indicator layer fuzzy judgment matrix, and calculate the weight of the indicator layer elements.

[0027] The criteria layer element scoring module is used to calculate the scores of each criterion element in the criteria layer based on the scores of each indicator element in the indicator layer and the weights of the indicator layer elements.

[0028] The criterion layer weight calculation module is used to construct a criterion layer fuzzy judgment matrix based on the scores of each indicator element in the criterion layer, perform a consistency transformation on the criterion layer fuzzy judgment matrix, and calculate the weights of the criterion layer elements.

[0029] The fault perception scoring module is used to calculate the fault perception score of the power optical communication network based on the scores of each criterion element in the criterion layer and the weights of the criterion layer elements.

[0030] The fault perception and prediction module is used to select reliability operation status data based on the fault perception score of the power optical communication network and upload it to the power optical communication digital twin network. This data is used to train the digital twin model to predict the future operation data of the power optical communication network, and to perform fault perception and prediction of the power optical communication network based on the predicted data through the multi-level fault perception index system.

[0031] The present invention also provides a terminal device, including a processor and a memory storing a computer program, wherein the processor executes the computer program to implement any of the power optical communication network fault detection methods described herein.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fault detection method for power optical communication networks as described in any one of the claims.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] This invention provides a method, apparatus, device, and storage medium for fault perception in power optical communication networks. The method includes: collecting operational status data of the power optical communication network; selecting a corresponding membership function model to calculate an index layer score; constructing an index layer fuzzy judgment matrix and calculating the weights of index layer elements; calculating a criterion layer score based on the index layer score and weights; constructing a criterion layer fuzzy judgment matrix and calculating the weights of criterion layer elements; calculating a power optical communication network fault perception score based on the criterion layer score and weights; uploading the reliability operational status data to a power optical communication digital twin network for training a digital twin model to predict future operational data of the power optical communication network, and performing fault perception prediction of the power optical communication network based on the predicted data. This invention can perform fault perception and early warning of power optical communication networks and effectively improves the accuracy of fault perception in power optical communication networks. Attached Figure Description

[0035] Figure 1 This is a flowchart illustrating the fault detection method for power optical communication networks provided by the present invention.

[0036] Figure 2 This is a schematic diagram of the structure of the power optical communication network based on digital twin provided by the present invention;

[0037] Figure 3 This is a schematic diagram of the multi-level fault perception index system provided by the present invention;

[0038] Figure 4 This is a schematic diagram of the structure of the power optical communication network fault sensing device provided by the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0040] Please see Figure 1 This invention provides a fault detection method for power optical communication networks, which may include the following steps:

[0041] S1. Collect operational status data of the power optical communication network; wherein, the multi-level fault perception index system of the power optical communication network includes a target layer, a criterion layer, and an index layer;

[0042] S2. Select the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer;

[0043] S3. Construct a fuzzy judgment matrix for the indicator layer based on the scores of each indicator element in the indicator layer, perform a consistency transformation on the fuzzy judgment matrix for the indicator layer, and calculate the weights of the indicator layer elements.

[0044] S4. Calculate the scores of each criterion element in the criterion layer based on the scores of each indicator element in the indicator layer and the weights of the indicator elements.

[0045] S5. Construct a fuzzy judgment matrix for the criterion layer based on the scores of each indicator element in the criterion layer, perform a consistency transformation on the fuzzy judgment matrix for the criterion layer, and calculate the weights of the criterion layer elements.

[0046] S6. Calculate the fault perception score of the power optical communication network based on the scores of each criterion element in the criterion layer and the weights of the criterion layer elements.

[0047] S7. Based on the fault perception score of the power optical communication network, select reliability operation status data and upload it to the power optical communication digital twin network for training the digital twin model to predict the future operation data of the power optical communication network, and perform fault perception prediction of the power optical communication network based on the predicted data through the multi-level fault perception index system.

[0048] In this embodiment of the invention, the target layer further represents the power optical communication network body; the criteria layer includes resource usage criteria, network operation level criteria, service support criteria, and communication network operation and maintenance criteria.

[0049] In this embodiment of the invention, further, in the indicator layer, the indicator elements belonging to the resource usage criteria include: packet loss rate, online rate, packet error rate, average transmission rate, response time, and channel redundancy; the indicator elements belonging to the network operation level criteria include: end-to-end transmission delay, optical transmission equipment failure duration, optical switch equipment failure duration, communication power supply equipment failure duration, optical cable failure duration, and data acquisition module failure duration; the indicator elements belonging to the service support criteria include: service importance, number of service interruptions, average service interruption duration, service recoverability, service transmission stability, and service success rate; the indicator elements belonging to the communication network operation and maintenance criteria include: communication network investment amount, number of on-duty maintenance personnel, equipment maintenance execution rate, number of spare parts and components, network attack frequency, and security mechanism completeness.

[0050] In this embodiment of the invention, the index element types of the index layer further include positively correlated index elements, negatively correlated index elements, and interval-related index elements. Specifically, for positively correlated index elements, a larger value indicates higher reliability and lower potential failure probability of the power optical communication network; for negatively correlated index elements, a smaller value indicates higher reliability and lower potential failure probability of the power optical communication network; and for interval-related index elements, a value within a preset interval indicates higher reliability and lower potential failure probability of the power optical communication network, while a value deviating further from the preset interval indicates lower reliability and higher potential failure probability of the power optical communication network.

[0051] In this embodiment of the invention, the consistency transformation of the fuzzy judgment matrix of the index layer is further described as follows:

[0052] If it is determined that the fuzzy judgment matrix of the indicator layer does not meet the preset consistency condition, then the fuzzy judgment matrix of the indicator layer is converted into the consistency judgment matrix of the indicator layer based on the preset conversion formula.

[0053] The consistency transformation of the fuzzy judgment matrix of the criterion layer is specifically as follows:

[0054] If the fuzzy judgment matrix of the criterion layer is determined not to meet the preset consistency condition, then the fuzzy judgment matrix of the criterion layer is converted into a consistent judgment matrix of the criterion layer based on the preset conversion formula.

[0055] In this embodiment of the invention, the step of selecting the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer specifically includes:

[0056] Based on the type of each element in the indicator layer, select the corresponding membership function model, and calculate the membership degree of each element in the indicator layer to the three fuzzy evaluations of good, medium and poor based on the corresponding membership function model;

[0057] The score of each indicator element in the indicator layer is calculated based on the calculated membership degree of the indicator layer elements.

[0058] Based on the above scheme, in order to better understand the fault detection method for power optical communication networks provided in the embodiments of the present invention, the following detailed description is provided:

[0059] It should be noted that digital twins, as an effective means of achieving fault early warning in power optical communication networks, allow power grid information control systems to accurately monitor the health of power equipment and services by constructing a fault perception system based on digital twins. This enables performance evaluation and analysis of the power optical communication network, prompting maintenance personnel to promptly eliminate potential hazards and achieving proactive operation and maintenance of the network. With the help of digital twins, the real-time status of physical entities can be directly understood on the information platform. By exploring the deep connections between various research objects in the physical network, future operational data of the power optical communication network can be predicted, achieving fault early warning. Therefore, there is an urgent need to design a fault perception system for power optical communication networks based on digital twins.

[0060] To address the problems existing in the prior art, the objectives of this invention are: 1. To utilize digital twin technology, combining information such as equipment and environmental status of the power optical communication network to construct a power optical communication digital twin network, and on this basis, to train a digital twin model based on the operating data of a high-reliability power optical communication network to achieve fault prediction of the power optical communication network; 2. To construct a multi-level fault perception index system, and to establish a fuzzy judgment matrix using the exponential scaling method, the relative importance between matrix elements can be dynamically adjusted according to the actual situation, avoiding the influence of personal subjective preferences, and is suitable for accurate assessment of fault perception in power optical communication networks.

[0061] The embodiments of the present invention can be implemented through the following steps:

[0062] Step 1: Constructing a digital twin-based power optical communication network. To meet the technical requirements analysis of power grid operation, a digital twin-based power optical communication network system was designed, such as... Figure 2 As shown. The system includes:

[0063] 1. Power optical communication network;

[0064] 2. Multi-level fault perception index system;

[0065] 3. Power optical communication digital twin network.

[0066] The power optical communication network includes numerous optical communication devices, such as optical switches and optical splitters. On one hand, based on data collected from the power optical communication network containing characteristics of these devices, fault perception assessment can be performed. Simultaneously, data from the highly reliable power optical communication network can be used to train a digital twin network. On the other hand, the digital twin network can predict faults based on the network's operational data. By assessing the network's operational status based on the predicted data, timely warnings of potential faults can be issued, guiding on-site maintenance personnel to perform targeted maintenance and significantly improving the network's operational reliability.

[0067] Step Two: Constructing a Multi-Level Fault Perception Index System for Power Optical Communication Networks. Numerous evaluation indicators exist for measuring fault perception in power optical communication networks. To conduct a more comprehensive and effective fault perception assessment, this invention evaluates fault perception in power optical communication networks from four aspects: resource utilization, network operation level, service support, and communication network operation and maintenance. Based on this, a multi-level fault perception index system is constructed. This system, from top to bottom, includes a target layer, a criterion layer, and an index layer. The logical relationships between each layer and the specific content it contains are as follows: Figure 3 As shown.

[0068] The target layer is the power optical communication network body. This embodiment of the invention aims to evaluate fault detection in power optical communication networks; therefore, the power optical communication network body is selected as the target layer element.

[0069] The criteria layer includes resource usage criteria, network operation level criteria, service support criteria, and communication network operation and maintenance criteria. This embodiment of the invention evaluates fault perception in power optical communication networks based on these four criteria.

[0070] The indicator layer includes various indicators collected from the power optical communication network. Since the corresponding indicators in the network will become abnormal when a fault occurs in the power optical communication network, monitoring and evaluating various indicators in the power optical communication network can achieve fault detection for the entire network. This embodiment of the invention selects 24 indicators, each belonging to one of four categories of criteria in the criterion layer.

[0071] Step 3: Scoring of indicators in the multi-level fault perception indicator system. This embodiment of the invention achieves unified scoring of different indicators by constructing different membership function models. Based on the membership function, it realizes fuzzy evaluation of each indicator, which can effectively reduce the influence of subjective human factors on the scoring of indicators in the multi-level fault perception indicator system.

[0072] Considering the different relationships between various indicators and fault perception in power optical communication networks, these indicators are first categorized into three types: positively correlated indicators, negatively correlated indicators, and interval-related indicators. For positively correlated indicators, a larger value indicates higher reliability and a lower probability of potential faults in the power optical communication network. For negatively correlated indicators, a smaller value indicates higher reliability and a lower probability of potential faults. For interval-related indicators, a value within a certain interval indicates higher reliability and a lower probability of potential faults in the power optical communication network; conversely, a value deviating further from the interval indicates lower reliability and a higher probability of potential faults. For these three types of indicators, this invention proposes three membership function models: a positively correlated membership function model, a negatively correlated membership function model, and an interval-related membership function model.

[0073] Step 4: Scoring of criteria in the criterion layer of the multi-level fault perception index system. First, a fuzzy judgment matrix for the index layer of the multi-level fault perception index system is constructed based on the exponential scaling method. Second, consistency checks and consistency transformations of the fuzzy judgment matrix are performed. Finally, the index weights in the multi-level fault perception index system are calculated, and the scores of each criterion in the criterion layer of the multi-level fault perception index system are calculated based on these weights.

[0074] The fuzzy judgment matrix is ​​a matrix that describes the importance relationship between elements of the indicator layer. The fuzzy judgment matrix of the indicators included in criterion b in the multi-level fault perception indicator system is defined as follows: Right now:

[0075]

[0076] In the formula: K represents the number of indicators included in criterion b in the multi-level fault perception index system; This indicates the importance of index m relative to index n in criterion b within the multi-level fault perception index system, where m, n = 1, 2, ..., K.

[0077] This invention employs a highly accurate exponential scaling method to scale the importance relationships among different indicators included in criterion b in a multi-level fault perception index system.

[0078] In the fault perception process based on digital twins, the calculation of the weights of each indicator in the multi-level fault perception indicator system requires the consistency of the fuzzy judgment matrix at the indicator layer. If the fuzzy judgment matrix... for satisfy:

[0079]

[0080] This fuzzy judgment matrix is ​​called a fuzzy consistency judgment matrix.

[0081] Formula (2) is used to determine whether the fuzzy judgment matrix satisfies the consistency condition. If the consistency condition is met, the weights of each indicator in the multi-level fault perception index system can be calculated; if the consistency condition is not met, formula (3) can be used to adjust the fuzzy judgment matrix R. b Perform a consistency transformation, and then transform the fuzzy judgment matrix R. b Transform into a fuzzy consistency judgment matrix

[0082]

[0083] In the formula: and Representing the fuzzy judgment matrix R respectively b The sum of the elements in the m-th and n-th rows, i.e.

[0084] Fuzzy consistency judgment matrix at the indicator layer of a multi-level fault perception indicator system In the multi-level fault perception index system, the weights of indices m and n included in criterion b are correlated with the fuzzy consistency judgment matrix of the state layer. elements in The relationship between them is:

[0085]

[0086] In the formula: and represents the weights of the m-th and n-th indicators included in criterion b in the multi-level fault perception index system, respectively, and s is a parameter, usually taken as a boundary value.

[0087] Then, using the least squares method, the weights of index m included in criterion b in the multi-level fault perception index system can be calculated. for:

[0088]

[0089] Finally, based on the indicator weights obtained above The scores of each indicator can be used to calculate the score X of criterion b in the multi-level fault perception indicator system. b .

[0090] Step 5: Fault Perception Scoring in Power Optical Communication Networks. Based on the scores of each criterion in the multi-level fault perception index system obtained in Step 4, this invention uses a variable weighting method to construct a fuzzy judgment matrix describing the relationships between the criteria in the multi-level fault perception index system criterion layer. Where J represents the number of criteria included in the criterion layer of the multi-level fault perception index system. (Element) The calculation formula is:

[0091]

[0092] In the formula: X i and X j It is the score of criteria i and j in the criteria layer of the multi-level fault perception index system.

[0093] Next, the consistency of the fuzzy judgment matrix of the criterion layer of the multi-level fault perception index system is checked using formula (2). If R a If the consistency condition is not met, then R will be adjusted according to formula (7). a Convert to fuzzy consistency judgment matrix in, The calculation formula is as follows:

[0094]

[0095] In the formula: and Representing the fuzzy judgment matrix R respectively a The sum of the elements in the i-th and j-th rows, i.e.

[0096] Based on formula (5) and the fuzzy consistency judgment matrix of the multi-level fault perception index system criterion layer Calculate the weights of each criterion in the criterion layer of the multi-level fault perception index system.

[0097] Finally, based on the weights of each criterion obtained above... Scores X for each criterion i The final fault perception score S for the power optical communication network can be calculated as follows:

[0098]

[0099] Among them, X i The score is for criterion i in the multi-level fault perception index system calculated in step four.

[0100] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0101] 1. The fault perception method for power optical communication networks based on digital twins provided in this embodiment of the invention constructs a digital twin model of the power optical communication network, predicts the operation data of the power optical communication network by mining the deep-level connections between various research objects in the physical network, and provides fault warning for the power optical communication network based on the predicted data, thereby realizing fault perception and early warning for power optical communication networks based on digital twins.

[0102] 2. This invention proposes a multi-level fault perception index system for power optical communication networks. By using the exponential scaling method to establish a fuzzy judgment matrix and dynamically adjusting the relative importance between matrix elements, the adaptability of weights to actual fault perception requirements is improved. This avoids the influence of expert subjective preferences in the weight determination process and is suitable for accurate assessment of fault perception in power optical communication networks.

[0103] It should be noted that, for the sake of simplicity, the above methods or process embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0104] Please see Figure 4 This invention also provides a fault detection device for power optical communication networks, comprising:

[0105] Data acquisition module 1 is used to collect operating status data of the power optical communication network; wherein, the multi-level fault perception index system of the power optical communication network includes a target layer, a criterion layer and an index layer;

[0106] The indicator layer element scoring module 2 is used to select the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer.

[0107] The indicator layer weight calculation module 3 is used to construct an indicator layer fuzzy judgment matrix based on the scores of each indicator element in the indicator layer, perform consistency transformation on the indicator layer fuzzy judgment matrix, and calculate the weight of the indicator layer elements.

[0108] The criteria layer element scoring module 4 is used to calculate the score of each criterion element in the criteria layer based on the scores of each indicator element in the indicator layer and the weights of the indicator layer elements.

[0109] The criterion layer weight calculation module 5 is used to construct a criterion layer fuzzy judgment matrix based on the scores of each indicator element in the criterion layer, perform consistency transformation on the criterion layer fuzzy judgment matrix, and calculate the weights of the criterion layer elements.

[0110] The fault perception scoring module 6 is used to calculate the fault perception score of the power optical communication network based on the scores of each criterion element in the criterion layer and the weights of the criterion layer elements.

[0111] The fault perception and prediction module 7 is used to select reliability operation status data based on the fault perception score of the power optical communication network and upload it to the power optical communication digital twin network. It is used to train the digital twin model to predict the future operation data of the power optical communication network, and to perform fault perception and prediction of the power optical communication network based on the predicted data through the multi-level fault perception index system.

[0112] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention. The power optical communication network fault detection device provided by the embodiments of the present invention can implement the power optical communication network fault detection method provided by any one of the method embodiments of the present invention.

[0113] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fault detection method for power optical communication networks as described in any one of the claims.

[0114] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0115] Those skilled in the art will clearly understand that, for convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0116] The terminal device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0117] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0118] The memory can be used to store the computer program. The processor implements various functions of the terminal device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0119] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0120] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A fault detection method for power optical communication networks, characterized in that, include: Collect operational status data of the power optical communication network; wherein, the multi-level fault perception index system of the power optical communication network includes a target layer, a criterion layer, and an index layer; The membership function model corresponding to the type of each element in the indicator layer is selected to calculate the score of each indicator element in the indicator layer; A fuzzy judgment matrix for the indicator layer is constructed based on the scores of each indicator element in the indicator layer. The fuzzy judgment matrix for the indicator layer is then subjected to a consistency transformation, and the weights of the indicator layer elements are calculated. The scores of each criterion element in the criterion layer are calculated based on the scores of each criterion element in the criterion layer and the weights of the criterion elements in the criterion layer. A fuzzy judgment matrix for the criterion layer is constructed based on the scores of each indicator element in the criterion layer. The fuzzy judgment matrix for the criterion layer is then subjected to a consistency transformation, and the weights of the criterion layer elements are calculated. The fault perception score of the power optical communication network is calculated based on the scores of each criterion element in the criterion layer and the weights of the criterion layer elements. Based on the fault perception score of the power optical communication network, the reliability operation status data is selected and uploaded to the power optical communication digital twin network for training the digital twin model to predict the future operation data of the power optical communication network. The multi-level fault perception index system is used to perform fault perception prediction of the power optical communication network based on the predicted data. Specifically, the consistency transformation of the fuzzy judgment matrix of the indicator layer is as follows: If it is determined that the fuzzy judgment matrix of the indicator layer does not meet the preset consistency condition, then the fuzzy judgment matrix of the indicator layer is converted into the consistent judgment matrix of the indicator layer based on the preset conversion formula; the consistency conversion of the fuzzy judgment matrix of the criterion layer is specifically as follows: if it is determined that the fuzzy judgment matrix of the criterion layer does not meet the preset consistency condition, then the fuzzy judgment matrix of the criterion layer is converted into the consistent judgment matrix of the criterion layer based on the preset conversion formula.

2. The fault detection method for power optical communication networks according to claim 1, characterized in that, The target layer represents the physical entity of the power optical communication network; the criteria layer includes resource usage criteria, network operation level criteria, service support criteria, and communication network operation and maintenance criteria.

3. The fault detection method for power optical communication networks according to claim 2, characterized in that, In the aforementioned indicator layer, the indicator elements belonging to resource usage criteria include: packet loss rate, online rate, packet error rate, average transmission rate, response time, and channel redundancy; the indicator elements belonging to network operation level criteria include: end-to-end transmission delay, optical transmission equipment failure duration, optical switch equipment failure duration, communication power supply equipment failure duration, optical cable failure duration, and data acquisition module failure duration; the indicator elements belonging to service support criteria include: service importance, number of service interruptions, average service interruption duration, service recoverability, service transmission stability, and service success rate; and the indicator elements belonging to communication network operation and maintenance criteria include: communication network investment amount, number of on-duty maintenance personnel, equipment maintenance execution rate, spare parts and spare parts configuration quantity, network attack frequency, and security mechanism completeness.

4. The fault detection method for power optical communication networks according to claim 3, characterized in that, The index elements in the index layer include positively correlated index elements, negatively correlated index elements, and interval-related index elements. For positively correlated index elements, a larger value indicates higher reliability and lower potential failure probability of the power optical communication network. For negatively correlated index elements, a smaller value indicates higher reliability and lower potential failure probability of the power optical communication network. For interval-related index elements, a value within a preset range indicates higher reliability and lower potential failure probability of the power optical communication network, while a value deviating further from the preset range indicates lower reliability and higher potential failure probability of the power optical communication network.

5. The fault detection method for power optical communication networks according to claim 1, characterized in that, The step of selecting the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer specifically includes: Based on the type of each element in the indicator layer, select the corresponding membership function model, and calculate the membership degree of each element in the indicator layer to the three fuzzy evaluations of good, medium and poor based on the corresponding membership function model; The score of each indicator element in the indicator layer is calculated based on the calculated membership degree of the indicator layer elements.

6. A fault detection device for power optical communication networks, characterized in that, include: The data acquisition module is used to collect operational status data of the power optical communication network; wherein, the multi-level fault perception index system of the power optical communication network includes a target layer, a criterion layer, and an index layer; The indicator layer element scoring module is used to select the corresponding membership function model based on the type of each element in the indicator layer to calculate the score of each indicator element in the indicator layer. The indicator layer weight calculation module is used to construct an indicator layer fuzzy judgment matrix based on the scores of each indicator element in the indicator layer, perform consistency transformation on the indicator layer fuzzy judgment matrix, and calculate the weight of the indicator layer elements. The criteria layer element scoring module is used to calculate the scores of each criterion element in the criteria layer based on the scores of each indicator element in the indicator layer and the weights of the indicator layer elements. The criterion layer weight calculation module is used to construct a criterion layer fuzzy judgment matrix based on the scores of each indicator element in the criterion layer, perform a consistency transformation on the criterion layer fuzzy judgment matrix, and calculate the weights of the criterion layer elements. The fault perception scoring module is used to calculate the fault perception score of the power optical communication network based on the scores of each criterion element in the criterion layer and the weights of the criterion layer elements. The fault perception and prediction module is used to select reliability operation status data based on the fault perception score of the power optical communication network and upload it to the power optical communication digital twin network. It is used to train the digital twin model to predict the future operation data of the power optical communication network, and to perform fault perception and prediction of the power optical communication network based on the predicted data through the multi-level fault perception index system. Specifically, the consistency transformation of the fuzzy judgment matrix of the indicator layer is as follows: If it is determined that the fuzzy judgment matrix of the indicator layer does not meet the preset consistency condition, then the fuzzy judgment matrix of the indicator layer is converted into the consistent judgment matrix of the indicator layer based on the preset conversion formula; the consistency conversion of the fuzzy judgment matrix of the criterion layer is specifically as follows: if it is determined that the fuzzy judgment matrix of the criterion layer does not meet the preset consistency condition, then the fuzzy judgment matrix of the criterion layer is converted into the consistent judgment matrix of the criterion layer based on the preset conversion formula.

7. The power optical communication network fault sensing device according to claim 6, characterized in that, The target layer represents the physical entity of the power optical communication network; the criteria layer includes resource usage criteria, network operation level criteria, service support criteria, and communication network operation and maintenance criteria.

8. A terminal device, comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the power optical communication network fault detection method according to any one of claims 1 to 5.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the fault detection method for power optical communication networks as described in any one of claims 1 to 5.

Images