A power communication optical cable reliability evaluation method and driving route optimization method

Abstract

The present application relates to a kind of power communication cable reliability evaluation method and driving route optimization method, wherein the cable reliability evaluation method includes the following steps: collecting the historical multi-source data of target power communication network and pre-processing, based on the historical multi-source data after pre-processing, construct historical space-time graph data with the node of the graph of power communication network site and the edge of cable;Build network correction coefficient calculation model that fuses graph attention layer and gated recurrent unit, pre-train network correction coefficient calculation model by historical space-time graph data;Build cable reliability score model, the model calculates the reliability score of cable by cable feature and network correction coefficient;Get the multi-source data of target power communication network at current time and pre-processing, generate space-time graph data and input into trained network correction coefficient calculation model, output the network correction coefficient of each cable and calculate reliability score.

Description

TECHNICAL FIELD

[0001] The present application relates to a power communication optical cable reliability evaluation method and a driving route optimization method, and belongs to the technical field of power communication optical cable optimization. BACKGROUND

[0002] The communication system is an important foundation support for power grid production control services, and its stable operation is crucial to improving the reliability of large power grids. With the advancement of new power system construction, the power communication network is facing many challenges. In coastal areas, power communication optical cables not only have to withstand the pressure of regular business loads, but also have to cope with the influence of typhoons, heavy rains and other extreme weather conditions.

[0003] Currently, there are many problems in the operation and maintenance management of power communication optical cables. The traditional reliability analysis method has defects such as narrow range of index selection and manual weight setting, and it is difficult to accurately evaluate the actual reliability of optical cables in complex environments. In terms of business route planning, the existing technology often separates the reliability analysis of optical cables from the business route, and cannot realize the organic combination of the two, resulting in that when the optical cable fails or its performance decreases, the business route cannot be timely optimized and adjusted, thereby affecting the business continuity. At the same time, the traditional model cannot quantify the topological cascade risk, and in extreme weather, it is difficult to predict the situation of multiple optical cables failing in succession, making the disaster resistance of the communication network insufficient. In addition, the existing digital twin system has not formed a "prediction-decision" closed loop in the application of power communication, and the operation and maintenance efficiency is low, which cannot meet the higher requirements of the new power system on the support capacity of the communication network. SUMMARY

[0004] In order to solve the problems existing in the prior art, the present application proposes a power communication optical cable reliability driving route optimization method and system.

[0005] The technical scheme of the present application is as follows:

[0006] On the one hand, the present application proposes a power communication optical cable reliability evaluation method, comprising the following steps:

[0007] Collecting the historical multi-source data of the target power communication network and preprocessing, based on the preprocessed historical multi-source data, constructing a historical space-time graph data with the power communication network site as the node of the graph and the optical cable as the edge;

[0008] A network correction coefficient calculation model is constructed by fusing a graph attention layer and a gated recurrent unit, and the network correction coefficient calculation model is pre-trained through the historical space-time graph data; the network correction coefficient is used to correct the reliability of the optical cable;

[0009] An optical cable reliability scoring model is constructed, which calculates the reliability score of the optical cable through the optical cable features and the network correction coefficient;

[0010] The multi-source data of the target power communication network at the current time is acquired and preprocessed, the spatio-temporal graph data is generated and input into the trained network correction coefficient calculation model, the network correction coefficient of each optical cable is output, and the reliability score is calculated.

[0011] As a preferred embodiment, the multi-source data comprises:

[0012] topology data of the power communication network, optical cable performance data, meteorological data, and service data;

[0013] The topology data of the power communication network includes site data, optical cable connection relationship, node number, and adjacency matrix.

[0014] The optical cable performance data includes optical cable type, optical power attenuation value, transmission delay, load rate, and operation life.

[0015] The meteorological data includes temperature, humidity, and wind speed data acquired from a meteorological station.

[0016] The service data includes service scheduling priority and historical fault data.

[0017] The preprocessing step specifically includes normalizing the multi-source data.

[0018] As a preferred embodiment, in the network correction coefficient calculation model:

[0019] The graph attention layer is used to input the spatio-temporal graph data, calculate the edge attention weight of each optical cable according to the spatio-temporal graph data, and output the updated feature vector of each graph node according to the calculated edge attention weight of each edge.

[0020] The gated recurrent unit is used to input the updated feature vector of each graph node, update the gating value according to the updated feature vector of the graph nodes at both ends of each optical cable and the hidden state vector of the corresponding optical cable at the previous time, and use the gating value as the network correction coefficient.

[0021] As a preferred embodiment, the meteorological influence factor is introduced into the gated recurrent unit.

[0022] The meteorological influence factor is calculated from the meteorological data and participates in the updating step of the gating value, specifically:

[0023] The gated recurrent unit inputs the updated feature vector of each graph node, updates the gating value according to the updated feature vector of the graph nodes at both ends of each optical cable and the hidden state vector of the corresponding optical cable at the previous time, and uses the gating value as the network correction coefficient, wherein:

[0024] The input of the gated recurrent unit is:

[0025] ;

[0026] wherein, represents the node at the current moment the feature vector updated by the graph attention layer, represents the node at the current moment the feature vector updated by the graph attention layer; represents the inter-node and edge feature matrix of the optical cable between nodes; is a meteorological influence factor.

[0027] As a preferred embodiment, the optical cable reliability score model extracts optical cable features of the target optical cable through multi-source data, and calculates a basic score value according to the optical cable features; and the reliability score of the corresponding optical cable is obtained by weighted calculation according to the basic score value and a network correction coefficient.

[0028] On the other hand, the present application also proposes a power communication optical cable reliability driven routing optimization method, comprising the following steps:

[0029] obtaining the reliability score of each optical cable in the target power communication network at the current moment by the power communication optical cable reliability evaluation method according to any embodiment of the present application;

[0030] constructing a routing cost function according to the reliability score of the optical cable and the service data;

[0031] obtaining the optimized optical cable routing path by solving the routing cost function through the Dijkstra algorithm.

[0032] As a preferred embodiment, the routing cost function is specifically:

[0033] ;

[0034] wherein, represents the routing cost function of the candidate path , wherein, represents the reliability score of the optical cable , wherein, represents the service level coefficient of the corresponding optical cable, is a service scheduling priority coefficient.

[0035] As a preferred embodiment, the method further comprises:

[0036] constructing a power communication network digital twin;

[0037] The generated optimized optical cable routing path is input into the power communication network digital twin for simulation verification, if the service interruption probability obtained through simulation exceeds the set threshold, the network correction coefficient calculation model is retrained, if the set threshold is not exceeded, the communication strategy is executed according to the optimized optical cable routing path.

[0038] In another aspect, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the power communication optical cable reliability evaluation method according to any embodiment of the present application when executing the program.

[0039] In another aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the program is executable on a processor to implement the power communication optical cable reliability evaluation method according to any embodiment of the present application.

[0040] The present application has the following beneficial effects:

[0041] The present application significantly improves the stability and transmission efficiency of the power communication network by comprehensively considering the reliability score of the optical cable and the service demand. At the same time, it can dynamically adapt to the changes of network state, ensuring that the optimal routing selection can be provided under different operating conditions. In addition, through deep mining of historical data and continuous optimization of the model, the prediction ability and decision accuracy of the system are further enhanced, providing strong technical support for the safe and reliable operation of the power communication network.

[0042] Additional aspects and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. Furthermore, various aspects and advantages of the present application can be realized and attained by means of the instrumentalities and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 The method flowchart of the embodiment one of the present application is shown in the figure;

[0044] Figure 2 The training schematic diagram of the network correction coefficient calculation model in the embodiment of the present application is shown in the figure;

[0045] Figure 3 The method flowchart of the embodiment two of the present application is shown in the figure;

[0046] Figure 4 The overall flowchart of the routing optimization driven by the optical cable reliability score in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0047] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0048] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0049] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, unless otherwise clear from the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0050] The terms "comprise" and "include" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0051] The term "and / or" means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0052] Embodiment one:

[0053] Referring to Figure 1 The present embodiment proposes a power communication optical cable reliability evaluation method and a driving route optimization method, comprising the following steps:

[0054] S100, collect the multi-source data of the history of the target power communication network, including the topology data of the power communication network, the optical cable performance data, the weather data and the service data; wherein:

[0055] The topology data of the power communication network includes the site, the optical cable connection relationship, the node number and the adjacency matrix;

[0056] The site data includes the highest voltage level of the substation, the number of protection and control service of the site equipment load above 220kV;

[0057] The optical cable performance data includes the optical cable type, the optical power attenuation value, the transmission delay, the load rate and the operation life;

[0058] The weather data includes the temperature, humidity and wind speed data obtained from the weather station;

[0059] The service data includes service scheduling priority (classified according to line level, such as 10kV, 500kV, etc.) and historical fault data (such as historical interruption times);

[0060] And the collected multi-source data is preprocessed, specifically, each of the above multi-source data is normalized, and is mapped to the [0, 1] interval by using Min-Max standardization. Based on the preprocessed historical multi-source data, a historical space-time graph data is constructed, taking the power communication network site as the node of the graph and the optical cable as the edge, including the site node set, the optical cable edge set, the feature matrix of the node and the edge; including:

[0061] Node set : each node corresponds to a power communication network site;

[0062] Edge set: : each edge corresponds to a section of optical cable, and is associated with two end nodes ;

[0063] Node feature matrix: is a dimensional tensor, is a node feature space, M is the number of sites, is the number of time sampling points (15 minutes once), is the site feature dimension, The dimension of the site data after standardization processing is determined, and the feature data in the node feature matrix is also obtained from the site data after standardization processing.

[0064] Edge feature matrix: is a dimensional tensor, is an edge feature space, N is the number of optical cables, Fe is the optical cable feature dimension, is the number of time sampling points, synchronized with the node, The dimension of the optical cable performance data after standardization processing is determined, and the feature data in the edge feature matrix is also obtained from the optical cable performance data after standardization processing.

[0065] S200, specifically, see Figure 2 , a network correction coefficient calculation model (ST-GATGRU model) fusing a graph attention layer and a gated recurrent unit is constructed, and the network correction coefficient calculation model is pre-trained by the historical space-time graph data.

[0066] Among them, the graph attention layer is used for inputting the space-time graph data, and the edge attention weight of each section of optical cable is calculated according to the space-time graph data, and the specific formula is:

[0067] ;

[0068] Among them is the node feature matrix of the current time step, is the edge feature matrix of the two nodes, and are learnable weight matrices and are uniformly aligned to the same dimension, is the attention coefficient, is the normalization function, is the activation function.

[0069] According to the calculated attention weight of each edge, the adjacent node features of the node are weighted and aggregated, and the updated feature vector of each graph node is output .

[0070] The gated recurrent unit is used to input the updated feature vector of each graph node, and the updated gate value is obtained according to the updated feature vector of the graph node at both ends of each optical cable and the hidden state vector of the corresponding optical cable at the last time step, which is used as the network correction coefficient. The GRU time sequence update mechanism mainly includes the following:

[0071] The input vector is:

[0072] .

[0073] wherein, represents the feature vector of the node updated by the graph attention layer at the current time step, represents the feature vector of the node updated by the graph attention layer at the current time step; represents the edge feature matrix of the optical cable between the nodes and . is the meteorological influence factor.

[0074] The reset gate formula is:

[0075] .

[0076] is the activation function (usually using sigmoid function), is the hidden state vector of the optical cable selected at the last time step (i.e. the time sequence state maintained by the GRU unit); is the trainable weight matrix of the reset gate, is the bias of the reset gate; is used to control the forgetting degree of the historical state .

[0077] The update gate formula is:

[0078] ;​

[0079] As the network correction coefficient output, For updating the trainable weight matrix of the gate, For updating the bias of the gate.

[0080] The candidate state formula is:

[0081] ;

[0082] tanh is the hyperbolic tangent activation function, Acts as a filter of effective information of the historical state in the candidate state, The trainable weight matrix calculated for the candidate state, The bias calculated for the candidate state.

[0083] The hidden state update formula is:

[0084] ;

[0085] Balancing the historical state And the candidate state The final output Will be the hidden state at the next moment.

[0086] The embodiment introduces a meteorological influence factor in the gated recurrent unit. The meteorological influence factor is calculated through meteorological data, which can effectively learn the long-period degradation rule and cope with the influence of complex meteorological conditions on the performance of optical cables. The specific calculation steps of the meteorological influence factor are as follows:

[0087] First, obtain the temperature, humidity, and wind speed data, and perform standardization processing. For single-dimensional meteorological data Such as wind speed, Min-Max standardization is adopted: Wherein , are the minimum and maximum values of the historical same period of this parameter.

[0088] Weighted fusion is performed on the standardized meteorological data to obtain the meteorological influence factor:

[0089] ;

[0090] Wherein, , and are the preset weight factors.

[0091] The embodiment introduces the meteorological influence factor to participate in the gating decision, so that the model enhances the sensitivity to optical power attenuation and optical cable physical damage at moments of sudden changes such as typhoons. For example, when sudden rise, will inhibit the influence of historical state , prefer to learn the impact of current meteorological mutation on optical cable reliability, so as to capture the coupling relationship between short-term failure risk and long-term degradation law.

[0092] S300, construct an optical cable reliability score model, which calculates the reliability score of the optical cable through the optical cable characteristics and the network correction coefficient; the reliability score has a mapping relationship with the failure rate of the optical cable.

[0093] Specifically, the optical cable reliability score model extracts the optical cable characteristics of the target optical cable through multi-source data, and calculates the basic score value according to the optical cable characteristics; in the weighted calculation according to the basic score value and the network correction coefficient to obtain the reliability score of the corresponding optical cable, in this embodiment, the weighted formula is:

[0094] ;

[0095] The basic score value is in percentage, which is generated by considering the optical cable type (OPGW, ADSS), operation time, and historical failure times through a preset manner. In this embodiment, the default value of the basic score value is set to 100 points, 40 points are deducted when the operation time is more than 10 years, 20 points are deducted when the operation time is 5-10 years, and no points are deducted when the operation time is less than 5 years; more than 5 times within a year, deduct 20 points, less than 5 times, deduct 10 points, no failure, no deduction; if the optical cable type is OPGW, the deduction value of the optical cable is multiplied by the weight 1.0, and if the optical cable type is ADSS, the deduction value of the optical cable is multiplied by the weight 1.25.

[0096] The network correction coefficient is output by the network correction coefficient calculation model in the subsequent step.

[0097] The mapping formula of the reliability score and the failure rate of the optical cable is:

[0098] ;

[0099] Wherein, is the failure rate. By mapping the failure probability, a basis can be provided for subsequent decision-making.

[0100] S400, acquire multi-source data of the target power communication network at the current time and preprocess, generate space-time graph data and input into the trained network correction coefficient calculation model, output the network correction coefficient of each optical cable and calculate the reliability score.

[0101] By fusing multi-source data, including the physical state of the optical cable, communication quality indicators, and external environmental information, the model can dynamically adjust the weight distribution of the network correction coefficient. In practical applications, this method effectively improves the adaptability and accuracy of the scoring system. For example, when a certain section of optical cable has a high historical failure rate and the current weather conditions are poor, its reliability score will be significantly reduced, providing a more reliable basis for route optimization. In addition, the model also supports comparative analysis of data from different time periods, further mining potential risk patterns.

[0102] This embodiment significantly improves the stability and transmission efficiency of the power communication network by considering the reliability score of the optical cable and the business demand. At the same time, it can dynamically adapt to changes in network state, ensuring optimal route selection under different operating conditions. In addition, through deep mining of historical data and continuous optimization of the model, the prediction ability and decision-making accuracy of the system are further enhanced, providing strong technical support for the safe and reliable operation of the power communication network.

[0103] Embodiment Two:

[0104] Referring to Figure 3 and Figure 4 , the embodiment provides a power communication optical cable reliability-driven route optimization method,

[0105] A100, obtaining the reliability score of each optical cable in the target power communication network at the current time by the power communication optical cable reliability evaluation method according to any one of the embodiments of the present application;

[0106] A200, constructing a route cost function according to the reliability score of the optical cable and the business data, the route cost function being specifically:

[0107] ;

[0108] wherein, represents the route cost function of the candidate path , represents the reliability score of the optical cable , represents the business level coefficient of the corresponding optical cable (1.5 for 500kV and above, 1.2 for 220kV, and 1.0 for 110kV and below), is the business scheduling priority coefficient (1.0 for protection and control business, and 0.8 for other businesses).

[0109] A300, solving the optimal optical cable route path based on the specific route cost function by the classical Dijkstra shortest path algorithm, the implementation process of the method mainly including the following steps:

[0110] ​​(1) Construct cost matrix

[0111] With node set as dimension, construct cost adjacency matrix , matrix element is defined as: if node and are directly connected by optical cable , then ; if node and have no direct optical cable connection, then (indicates that it cannot be directly reached); diagonal element (node to itself cost is 0).

[0112] (2) Initialize parameters

[0113] Set path starting point and end point ;

[0114] Initialize distance record structure: for each node , maintain a list to store the cost value of the first K lowest cost paths from the starting point to the node (initially , the list length of the remaining nodes is K);

[0115] Initialize predecessor record structure: for each node and each path cost, record the predecessor node of the node in the path, which is used to backtrack the complete path.

[0116] (3) Iterative calculation of path cost

[0117] Use priority queue (min heap) to store the "node-cost" pairs to be processed, initially add to the queue (indicating that the initial cost of the starting point is 0);

[0118] Take out the "node-cost" pair with the smallest current cost from the queue ( is the current node, is the path cost from the starting point to );

[0119] Traverse all adjacent nodes of node , calculate the new path cost from the starting point through to : ;

[0120] like Smaller than node of If the Kth largest cost value in the list (or the list length is less than K), then... insert And keep the list ordered (in ascending order of cost), while recording The predecessor node is ;

[0121] Will Add to the priority queue and continue iterating until the queue is empty or the endpoint is reached. of The costs of K valid paths have been recorded.

[0122] (4) Select K feasible paths with the lowest cost

[0123] From the finish line of The K smallest cost values ​​are selected from the list, and the corresponding paths are the candidate path set.

[0124] Tracing back the complete node sequence of each path using the predecessor record structure (from the endpoint) Tracing back to the starting point Finally, we obtain K lowest-cost feasible paths from the starting point to the ending point.

[0125] Finally, to ensure the reliability of the routing scheme, an N-1 security check mechanism is introduced to verify the robustness of the selected path under network failure scenarios. It should be noted that Dijkstra's algorithm, as a mature graph theory algorithm, has been extensively studied in related fields regarding its basic principles and standard implementation process; therefore, this embodiment will not repeat the specific details of the algorithm.

[0126] In a preferred embodiment of this invention, the method further includes:

[0127] Constructing a digital twin of the power communication network;

[0128] The generated optimized optical cable routing path is input into the digital twin of the power communication network for simulation verification. If the service interruption probability obtained from the simulation exceeds the set threshold, the network correction coefficient calculation model is retrained; if it does not exceed the set threshold, the communication strategy is executed according to the optimized optical cable routing path.

[0129] Through the above simulation verification process, the feasibility and reliability of the optimized path in actual application can be effectively evaluated. Meanwhile, the combination of digital twinning technology and routing optimization method not only improves the scientificity of the scheme, but also provides intuitive decision basis for network planning and operation. In addition, through the analysis of the simulation results, potential risk points can be further identified, and relevant parameters or strategies can be adjusted accordingly to ensure that the communication network always maintains efficient and stable operation state. This closed-loop optimization mechanism significantly enhances the adaptability and robustness of the system, providing a foundation for the long-term reliable operation of the power communication network.

[0130] To help those skilled in the art quickly understand the principles of the present embodiment, a specific case is provided as follows:

[0131] Taking a 500kV power communication optical cable network in a coastal area as an example, the topological data of the optical cable network in this area is collected, including the connection relationship of 12 site nodes, adjacency matrix, etc.; real-time optical cable performance data is obtained, such as the maximum standard deviation of optical power of A-B segment optical cable in the past month is 2.51%, the current average transmission delay is 12ms, and the load rate is 78%; meteorological data is collected, at this time it is typhoon season, the typhoon path passes through the A-B segment area, the wind speed is 15m / s, and the humidity is 92%; in terms of business data, the network carries 3 protection service channels, among which the stability business dispatching priority is the highest, and the current path redundancy is 2 standby paths. After Min-Max standardization preprocessing of these data, the spatio-temporal graph data is constructed.

[0132] The preprocessed spatio-temporal graph data is input into the constructed ST-GATGRU model for training. During the training process, the historical data of the past 3 years of typhoon season (June-September) is used, including 20 optical cable failure cases caused by typhoons as training samples. The loss function is set as , where =0.3, the iteration optimization process is set as =400, the learning rate is 0.01, the optimizer is used to make the loss converge to 0.028, and the model training is completed.

[0133] Based on the trained model, the reliability score of each optical cable segment is calculated. Taking A-B segment as an example, the basic reliability score is calculated, combined with the spatio-temporal attenuation coefficient of typhoon influence, and the final reliability score is 38 points, according to the formula, the failure probability is 40.62%; the reliability score of C-D segment is 75 points, and the failure probability is 32.09%.

[0134] According to the optical cable reliability score, the business level coefficient (the protection business =1.5) and the business dispatching priority (the stability control business =1.2) to build the routing cost function. Dijkstra algorithm is used to calculate the candidate paths, and the optimal path is A-E-C-D with a total cost of 0.86.

[0135] The optimal path scheme A-E-C-D is input to build the digital twin of the regional power communication network and perform simulation verification. The simulation results show that the service interruption probability meets the requirements, and the final decision is output to switch the stable service to the A-E-C-D path.

[0136] Embodiment Three

[0137] The embodiment provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the power communication optical cable reliability evaluation method according to any one of the embodiments of the present application when executing the program.

[0138] Embodiment Four

[0139] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executable on a processor to implement the power communication optical cable reliability evaluation method according to any one of the embodiments of the present application.

[0140] In the embodiments of the present application, “at least one” refers to one or more, and “multiple” refers to two or more. “And / or” describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character “ / ” generally represents an “or” relationship between the front and rear associated objects. “At least one of the following” and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, wherein a, b, and c can be single or multiple.

[0141] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be realized by electronic hardware, computer software and a combination of electronic hardware and computer software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0143] In several embodiments provided in the present application, any function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0144] The above description is only some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, based on the content of the specification and drawings of the present application, are also included in the patent protection scope of the present application.

Claims

1. A method for reliability assessment of power communication optical cables, characterized in that, Includes the following steps: Collect and preprocess historical multi-source data of the target power communication network. Based on the preprocessed historical multi-source data, construct a historical spatiotemporal graph with power communication network sites as nodes and optical cables as edges. A network correction coefficient calculation model integrating a graph attention layer and a gated recurrent unit is constructed, and the model is pre-trained using historical spatiotemporal graph data; the network correction coefficients are used to correct the reliability of optical cables. A reliability scoring model for optical cables is constructed, which calculates the reliability score of optical cables based on optical cable characteristics and network correction coefficients. The system acquires multi-source data of the target power communication network at the current moment and preprocesses it to generate spatiotemporal map data, which is then input into the trained network correction coefficient calculation model. The system outputs the network correction coefficient for each optical cable segment and calculates the reliability score. In the network correction coefficient calculation model: The graph attention layer is used to input spatiotemporal graph data, calculate the edge attention weight of each optical cable segment based on the spatiotemporal graph data, and output the updated feature vector of each graph node based on the calculated edge attention weight. The gated loop unit is used to input the updated feature vector of each graph node, and updates the gate value based on the updated feature vector of the graph nodes at both ends of each optical cable and the hidden state vector of the corresponding optical cable at the previous time step, which serves as the network correction coefficient. Meteorological influencing factors are also introduced into the gated loop unit; The meteorological impact factor is calculated using meteorological data and participates in the gating value update step, specifically as follows: The gated recurrent unit takes the updated feature vector of each graph node as input, and updates the gate value based on the updated feature vectors of the graph nodes at both ends of each optical cable and the hidden state vector of the corresponding optical cable at the previous time step. This value serves as the network correction coefficient, where: The input to the gated loop unit is: ； in, Indicates the current time node The feature vector updated after the graph attention layer Indicates the current time node The feature vector updated after the graph attention layer; Indicates the relationship between nodes and The edge feature matrix of the optical cable; These are meteorological influencing factors.

2. The reliability assessment method for power communication optical cables according to claim 1, characterized in that, The multi-source data includes: Topology data, optical cable performance data, meteorological data, and service data of power communication networks; The topology data of the power communication network includes site data, optical cable connection relationships, number of nodes, and adjacency matrix; The optical cable performance data includes optical cable type, optical power attenuation value, transmission delay, load rate, and service life; The meteorological data includes temperature, humidity, and wind speed data obtained from meteorological stations; The business data includes business scheduling priorities and historical fault data; The preprocessing step specifically involves normalizing the multi-source data.

3. The reliability assessment method for power communication optical cables according to claim 1, characterized in that: The optical cable reliability scoring model extracts the optical cable features of the target optical cable from multi-source data and calculates a basic score value based on the optical cable features; then, a weighted calculation is performed based on the basic score value and the network correction coefficient to obtain the reliability score of the corresponding optical cable.

4. A reliability-driven routing optimization method for power communication optical cables, characterized in that, Includes the following steps: The reliability score of each optical cable segment in the target power communication network at the current moment is obtained by the power communication optical cable reliability assessment method as described in any one of claims 1 to 3. A routing cost function is constructed based on the reliability score of the optical cable and service data; The optimal optical cable route path is obtained by solving the routing cost function using Dijkstra's algorithm.

5. The reliability-driven routing optimization method for power communication optical cables according to claim 4, characterized in that, The routing cost function is specifically as follows: ； in, Indicate candidate path The routing cost function, Indicates optical cable Reliability rating, This indicates the service level coefficient of the corresponding optical cable. This is the priority coefficient for service scheduling.

6. The reliability-driven routing optimization method for power communication optical cables according to claim 4, characterized in that, The method further includes: Constructing a digital twin of the power communication network; The generated optimized optical cable routing path is input into the digital twin of the power communication network for simulation verification. If the service interruption probability obtained from the simulation exceeds the set threshold, the network correction coefficient calculation model is retrained; if it does not exceed the set threshold, the communication strategy is executed according to the optimized optical cable routing path.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the power communication optical cable reliability assessment method as described in any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the power communication optical cable reliability assessment method as described in any one of claims 1 to 3.

Images