Intelligent substation communication link fault self-healing regulation and control method and system

Abstract

The invention discloses an intelligent substation communication link fault self-healing regulation and control method and system, and relates to the technical field of fault self-healing regulation and control, and the method comprises the following steps: constructing a link disturbance intensity sequence reflecting link quality fluctuation; performing trend fitting and mutation identification on the link disturbance intensity sequence based on a sliding window mechanism, and generating a link state transaction index; when the link state transaction index exceeds a first threshold value, identifying an affected key easy-to-disturb service set according to the service path topological data of the abnormal link; constructing a context-aware path migration cost model based on the key easy-to-disturb service set, and generating an optimal switching path sequence; and implementing hierarchical link regulation and control according to the path switching optimal sequence. According to the method, trend fitting and mutation detection are carried out by adopting an overlapped sliding window mechanism and a mutation scoring function, so that intermittent or hidden link degradation abnormity which is difficult to capture can be effectively identified, and a link state transaction index has higher judgment precision.

Description

Technical Field

[0001] The present invention relates to the technical field of fault self-healing control, and more specifically, to a method and system for self-healing control of communication link faults in an intelligent substation. Background Art

[0002] With the development of smart grids, substation internal communication networks are responsible for critical tasks such as collecting device status, transmitting protection commands, and coordinating control. The quality fluctuations and real-time nature of these communication links directly impact the safety and efficiency of grid operations. Currently, mainstream communication link status detection methods rely on fixed-cycle polling mechanisms or preset heartbeat packet response mechanisms, which can, to a certain extent, detect serious faults such as link interruptions or complete loss of connection.

[0003] However, in actual operation, communication links more often exhibit weak anomalies such as intermittent fluctuations, minor degradation, or path congestion. These state changes are often not continuous or incomplete, making it difficult for traditional methods to promptly identify or effectively respond to them. On the one hand, fixed polling mechanisms have significant latency in responding to abnormal changes, failing to meet the stringent link timeliness requirements of critical services. On the other hand, heartbeat-based response methods are insensitive to link degradation and have a high rate of misjudgment of short-term fluctuations, which can easily lead to false triggering of link switching or missed detection of potential faults, resulting in safety hazards such as delayed self-healing responses or control failures.

[0004] Furthermore, existing self-healing strategies often decouple link anomalies from business impact analysis, lacking precise impact identification based on business path dependencies, making it difficult to generate recovery paths with controllable resources and clear regulation objectives. Therefore, a link fault self-healing method is urgently needed that can accurately identify subtle link disturbances, dynamically detect anomaly trends, and implement path regulation based on business dependencies to improve the robustness of communication systems and ensure business continuity.

[0005] The above-mentioned disclosed technical solutions have at least the following technical problems: existing methods mostly rely on a fixed polling mechanism or a preset heartbeat packet mechanism to detect the status of the communication link, which makes it difficult to timely perceive link degradation or weak abnormalities; they are often unable to effectively distinguish short-term link fluctuations or intermittent abnormalities, and are prone to misjudgment or omission, resulting in delayed or ineffective self-healing responses.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method and system for self-healing control of communication link faults in an intelligent substation. By constructing a link disturbance intensity sequence and triggering a key business path analysis and path control mechanism based on state change indicators, the system solves the problem that the existing methods rely on fixed polling or heartbeat mechanisms, cannot promptly identify link degradation or weak anomalies, and lead to delayed self-healing responses or false triggering. The system realizes dynamic perception, accurate identification and hierarchical control of the communication link status, thereby improving the business continuity and operational robustness of the substation communication system.

[0008] To achieve the above object, the present invention provides the following technical solutions: On the one hand, a method for self-healing and control of communication link faults in smart substations includes the following steps: collecting time-series operation characteristic data and service path topology data of the substation communication link to construct a link disturbance intensity sequence reflecting link quality fluctuations; performing trend fitting and mutation identification on the link disturbance intensity sequence based on a sliding window mechanism to generate a dynamically updated link state change index; when the link state change index exceeds a first threshold, identifying the affected key and easily disturbed service set based on the service path topology data of the abnormal link; combining the topological coupling relationship between the key and easily disturbed service set and the abnormal link and historical control feedback data to construct a context-aware path migration cost model to output an optimal switching path sequence; A hierarchical link switching operation is performed according to an optimal switching path sequence, link status feedback data after the switching is collected to evaluate the control result, and the first threshold is dynamically modified based on the evaluation result.

[0009] In a preferred embodiment, the link disturbance intensity sequence reflecting the link quality fluctuation comprises the following specific steps: for each communication link, first data is periodically collected within a preset time window; the first data includes transmission delay data, packet loss rate and routing hop count time series data; the collected delay data is subjected to fluctuation calculation, the packet loss rate time series data is subjected to instantaneous burst amplitude extraction, the hop count time series data is subjected to discontinuity detection, and each of the data is normalized; the normalized delay fluctuation rate, packet loss burst amplitude and hop count discontinuity index are linearly combined according to a preset weight coefficient to generate a disturbance intensity index reflecting the instantaneous instability level of the link; the disturbance intensity indexes at each sampling moment are aggregated in chronological order to form a link disturbance intensity sequence.

[0010] In a preferred embodiment, the link disturbance intensity sequence is trend fitted and mutation identified based on the sliding window mechanism to generate a dynamically updated link status anomaly index, specifically: based on the sliding window mechanism with a preset overlap rate, the link disturbance intensity sequence is segmented, and the disturbance intensity mean and disturbance intensity variance in each window are calculated respectively; the disturbance intensity mean change trend of the current window and its previous window is fitted, and a mutation scoring function is constructed in combination with the sudden increase of the disturbance intensity variance of the current window relative to the historical maker; when the mutation score exceeds the preset scoring threshold, a link status anomaly index characterizing the abnormal state of the link is generated.

[0011] In a preferred embodiment, the business path topology data of the abnormal link is used to identify the affected key and easily disturbed business set, specifically: based on the abnormal link node marked by the link state change indicator, its topological position in the business path mapping relationship is analyzed to generate a link disturbance propagation map representing the fault propagation path; for the business path containing the abnormal link in the map, the structural dependency parameters of the path relative to the abnormal link are calculated based on its path topology position and communication performance parameters; the structural dependency parameters are weighted and fused according to preset weights to generate a path impact strength score; the impact strength score of each path is compared with the set interference tolerance threshold, and the services carried by the path with a score exceeding the threshold are screened to generate a key and easily disturbed business set.

[0012] In a preferred embodiment, the construction of a context-aware path migration cost model is specifically as follows: based on the key and easily disturbed business set, the topological structure information and historical interference co-occurrence data of the network area where the abnormal link is located are extracted to construct a link coupling relationship matrix that characterizes the strength of the fault correlation between links; based on the link coupling relationship matrix and the state change index of the abnormal link, a weighted graph propagation algorithm is input to generate a structural dynamic propagation chain model, and a high-risk path cluster containing potential chain failure risks is output; based on the high-risk path cluster, the disturbance risk weight is adjusted, and the data of each business in the key and easily disturbed business set is combined to construct a context-aware path migration cost model.

[0013] In a preferred embodiment, the structure dynamic propagation chain model is generated and outputs a high-risk path cluster containing potential chain failure risks, specifically: link propagation is constructed based on the link coupling relationship matrix and the state anomaly index; abnormal link nodes are used as the initial disturbance source, and risk propagation is performed through a multi-source random walk algorithm, including defining the propagation attenuation factor, the path coupling strength coefficient and the path propagation probability, calculating the cumulative disturbance risk value of each node, and outputting a structure dynamic propagation chain model that characterizes the disturbance diffusion intensity; analyzing the spatial distribution of the cumulative risk value in the propagation chain model, calculating the risk density value in the unit topological area, and screening the path set with a risk density higher than the set threshold to form a high-risk path cluster.

[0014] In a preferred embodiment, the disturbance risk weight is adjusted based on the high-risk path cluster, and the data of each service in the key and easily disturbed service set is combined to construct a context-aware path migration cost model. The specific steps are: based on the high-risk path cluster, the disturbance risk level of each link is marked, and the risk level is determined by counting the frequency of each link appearing in the high-risk path cluster; for each candidate path in the path candidate set, the risk level value of the link it contains is accumulated to generate a path disturbance risk weight value; for each target service in the key and easily disturbed service set, the reachable path is screened from the candidate path set, and the indicator parameters of each path are collected in real time; and a context-aware path migration cost model is constructed based on the indicator parameters.

[0015] In a preferred embodiment, the output of the optimal switching path sequence is specifically as follows: historical link switching records and corresponding service recovery feedback data are obtained, and a heterogeneous graph with path nodes and service recovery quality indicators as elements is constructed; the relationship between path switching operations and service recovery quality is learned through a graph neural network model, and the expected recovery value of each candidate path for the target service is output; the expected recovery value is weightedly fused with the output of the path migration cost model, and the path optimization sorting strategy is dynamically adjusted based on the fusion result, and the optimal switching path sequence is generated by arranging in ascending order of migration cost; based on the recovery results of different sorting strategies in historical control feedback, the weight parameters in the path migration cost function are dynamically corrected.

[0016] In a preferred embodiment, the hierarchical link switching operation is performed according to the optimal switching path sequence, the link status feedback data after the switching is collected to evaluate the control results, and the first threshold is dynamically corrected based on the evaluation results, specifically: a path switching preferred sequence is constructed, and the core business is mapped to the minimum migration cost path according to the path migration cost and the service level priority, and the non-core business is allocated to a redundant link or a speed-limited channel; the link status and service message transmission status of the switched path are continuously sampled, and the packet loss rate, retransmission rate and service recovery delay indicators are collected to form a link control feedback indicator set; a control effectiveness scoring function is constructed based on the link control feedback indicator set to calculate the effectiveness score of the current path switching strategy; the effectiveness score is compared with the preset tolerance threshold. If the score is lower than the tolerance threshold for multiple consecutive rounds, the first threshold for link status change judgment is dynamically corrected according to the score trend.

[0017] On the other hand, a smart substation communication link fault self-healing control system includes the following modules: a link disturbance modeling module: used to collect the time-series operation characteristic data and service path topology data of the substation communication link, and construct a link disturbance intensity sequence reflecting the link quality fluctuation; a state change detection module: used to perform trend fitting and mutation identification on the link disturbance intensity sequence based on a sliding window mechanism, and generate a dynamically updated link state change index; a susceptible-to-disturbance service identification module: used to identify the affected key susceptible-to-disturbance service set based on the service path topology data of the abnormal link when the link state change index exceeds a first threshold; a path evaluation module: used to combine the topological coupling relationship between the key susceptible-to-disturbance service set and the abnormal link and historical control feedback data to construct a context-aware path migration cost model and output the optimal switching path sequence; a link control and adaptive feedback module: used to perform hierarchical link switching operations according to the optimal switching path sequence, collect the link state feedback data after switching to evaluate the control results, and dynamically correct the first threshold based on the evaluation results.

[0018] The technical effects and advantages of the present invention's method and system for self-healing control of communication link failures in smart substations are as follows: 1. This invention constructs a link disturbance intensity sequence that integrates multi-dimensional indicators such as delay, packet loss rate, and hop count, and adopts an overlapping sliding window mechanism and a mutation scoring function for trend fitting and mutation detection. It can effectively identify intermittent or hidden link degradation anomalies that are difficult to capture with traditional polling / heartbeat mechanisms. This makes the link status anomaly indicator more sensitive and accurate, providing a reliable foundation for subsequent self-healing control, achieving highly sensitive perception and accurate identification of weak disturbances in the communication link, and improving the timeliness and effectiveness of the response to link anomaly triggers.

[0019] 2. The present invention constructs a migration cost model by integrating contextual information such as link topology coupling relationships, disturbance propagation risks, link resource status and protocol adaptability, and combines graph neural networks to predict the impact of path switching on business recovery effects. It also performs adaptive weight correction based on historical feedback, and can dynamically generate an optimal switching path sequence driven by business sensitivity. It further reversely adjusts the discrimination threshold based on the scoring results to achieve adaptive closed-loop evolution of the control logic, effectively improving the quality fluctuation and adaptability of the self-healing strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flow chart of a method for self-healing control of a communication link failure in a smart substation according to the present invention; Figure 2 The present invention is a structural diagram of a smart substation communication link fault self-healing control system. DETAILED DESCRIPTION

[0021] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] Example 1, Figure 1 The present invention provides a method for self-healing control of communication link faults in smart substations, comprising the following steps: S1, collects the time-series operation characteristic data and service path topology data of the substation communication link, and constructs a link disturbance intensity sequence that reflects the link quality fluctuation; Among them, the timing operation characteristic data includes delay variation sequence, packet loss rate variation sequence, hop count variation sequence, jitter intensity sequence and forwarding interval fluctuation sequence; Service path topology data includes the forwarding paths of various service messages, the sequence of link nodes involved in the path, path priority, and message arrival delay threshold.

[0023] In this embodiment, a link disturbance intensity sequence reflecting link quality fluctuations is constructed, and the specific steps are as follows: Collect the time series data of delay, packet loss rate and hop count changes for each communication link within the preset time window, and normalize the sampling results; The normalized delay fluctuation rate, instantaneous packet loss burst amplitude, and hop discontinuity are linearly combined according to preset weights to obtain a disturbance intensity index reflecting the instantaneous instability level of the link. The disturbance intensity indicators corresponding to each time point are arranged in sampling order to form a link disturbance intensity sequence, which serves as the input basis for subsequent status trend identification and anomaly judgment.

[0024] S2, based on the sliding window mechanism, performs trend fitting and mutation identification on the link disturbance intensity sequence to generate dynamically updated link status anomaly indicators, specifically: The disturbance intensity sequence is segmented based on overlapping sliding windows, and the mean and variance of the disturbance intensity in each window are calculated respectively. By fitting the change trend of the mean disturbance intensity between the current window and its previous window, combined with the disturbance intensity variance The sudden increase in magnitude, constructing the mutation scoring function , When the mutation score exceeds the preset score threshold, a link status change indicator is generated to trigger path dependency analysis and regulatory response.

[0025] In this embodiment, the mutation scoring function , specifically:

[0026] in, is the mean disturbance intensity of the current sliding window, is the mean disturbance intensity of the first k-step window, is the variance of the disturbance intensity in the current window, is the variance of the disturbance intensity of the first k-step window, To prevent small positive numbers with denominators equal to 0, 、 They are preset weight coefficients, which are used to adjust the contribution weight of mean and variance to the score.

[0027] In this embodiment, the overlapping sliding window refers to segmenting the disturbance intensity sequence with a step size smaller than the window width, so that there is partial overlapping data between adjacent windows, thereby realizing continuous observation of disturbance trends and enhanced recognition of mutations.

[0028] S3, when the link status abnormality indicator exceeds a first threshold, identifying the affected key and susceptible service sets based on the service path topology data of the abnormal link; The first threshold is a reference threshold used to determine whether the link status anomaly indicator triggers business dependency analysis. It can be initially set to a fixed value or obtained through historical data training, and then dynamically modified according to control feedback to improve the adaptability of anomaly recognition sensitivity.

[0029] Furthermore, the critical and susceptible-to-disturbance service set refers to a set of services that are most susceptible to abnormal links when disturbances or degradation trends occur in the substation communication link, and whose communication interruption may pose a significant risk to the stable operation of the system, identified based on the service path dependency structure, service level and delay tolerance characteristics.

[0030] In this embodiment, the identification of the affected key and susceptible service sets based on the service path topology data of the abnormal link is specifically as follows: Based on the abnormal link nodes marked in the link state change indicator, their positions in the service path mapping relationship are extracted to construct a link disturbance propagation map to describe the structural diffusion relationship of link state fluctuations in multiple service paths; For each service path containing an abnormal link in the link disturbance propagation map, the structural dependency parameters of the path relative to the abnormal link are calculated based on its path topology position and communication parameters. The structural dependency parameters include structural dependency, path hop count variation, available backup path ratio, and the maximum tolerable delay of the target service (this item is usually a service configuration item and does not need to be calculated in the scoring. If the delay is expected after the path migration, the target service will be delayed). Less than the preset maximum tolerable delay , it is considered tolerable, otherwise the tolerance score of the business in the rating will be penalized); The above structural dependency parameters are weighted and integrated to form a path impact strength score, which reflects the potential damage ability of the abnormal link to the service continuity of the path; Based on the path impact intensity score and the set interference tolerance threshold, the service set corresponding to the path with a score exceeding the threshold is screened, and a key interference-prone service set is constructed. This set serves as the input basis for the subsequent path switching optimization strategy generation and link resource regulation.

[0031] In this embodiment, the specific calculation formula of the structural dependence is:

[0032] Furthermore, the specific calculation formula for the path hop count change range is:

[0033] The specific calculation formula for the available backup path ratio is:

[0034] The specific calculation formula for the path impact strength score is:

[0035] in, is the structural dependence, is the number of alternative paths (i.e., the number of detour paths) that can replace the abnormal link in path i, is the variation range of the path hop count, is the number of hops of the path after detour, is the number of hops of the original path, is the ratio of available backup paths, is the number of link segments in the current path that are affected by abnormal links but have switchable links. is the total number of path links, Score the path impact strength, 、 、 、 are the weights of each factor (calculated according to the entropy weight method), is the expected delay after path migration, is the maximum tolerable delay of the target service, is an indicator function that takes the value 1 when the path migration causes the delay to exceed the maximum tolerable delay, and takes the value 0 otherwise.

[0036] S4, combining the topological coupling relationship of key and easily disturbed services, abnormal links, and historical control feedback data, builds a context-aware path migration cost model and outputs the optimal switching path sequence; In this embodiment, a context-aware path migration cost model is constructed, specifically: Based on the key interference-prone service set, the topology information of the network area where the abnormal link is located and the historical interference co-occurrence data between links are extracted to construct a link coupling relationship matrix. The link coupling relationship matrix reflects the interference transmission intensity and linkage risk between links. Based on the link coupling relationship matrix and the abnormal link status change indicators, a weighted graph propagation algorithm is used to deduce the propagation path of disturbances along multiple link paths in the network and their cumulative risk. This generates a structural dynamic propagation chain model and identifies high-risk path clusters. By adjusting the disturbance risk weight of high-risk path clusters and combining the link idleness, path forwarding delay, and protocol adaptability of each service in the key susceptible-to-disturbance service set, a context-aware path migration cost model is constructed. The disturbance risk weight serves as an important adjustment factor in the cost function, reflecting the risk of path quality fluctuation.

[0037] In this embodiment, a link coupling relationship matrix is ​​constructed as follows: Centered on the abnormal link node, analyze the link sharing node relationship between it and the adjacent links , fault coupling frequency and traffic forwarding relevance , calculate the coupling strength between link pairs , forming a coupling relationship matrix that reflects the risk of link state linkage , and identify high-risk path segments containing abnormal links based on the matrix.

[0038] The link coupling relationship matrix , coupling strength The calculation formula is:

[0039]

[0040]

[0041]

[0042] in For Link and links The coupling strength, is the link sharing node relationship, is the Pearson correlation coefficient of the historical traffic of the two links, is the fault coupling frequency, 、 、 They are weight coefficients (set through historical experience), satisfying , For Link The flow in the tth time window, for The mean of For Link The flow in the tth time window, for The mean of is the total number of time windows, For Link and links The number of windows that failed simultaneously.

[0043] Furthermore, based on the link coupling relationship matrix and combined with the abnormal link status change indicators, a weighted graph propagation algorithm is used to deduce the propagation path of the disturbance along multiple link paths in the network and its cumulative risk. This generates a structural dynamic propagation chain model and identifies high-risk path clusters. Specifically: Construct a link propagation graph based on the link coupling relationship matrix and state change indicators , where each link is a node in the graph , the coupling strength is the edge weight , the abnormal link node adds the state change weight as the disturbance source incentive value ; Based on the multi-source random walk algorithm, the abnormal link node is used as the initial disturbance source to deduce the path disturbance diffusion, and the attenuation factor of each hop propagation is comprehensively considered during the propagation process. , path coupling strength and path propagation probability , output the cumulative disturbance risk value of each link, which is the weighted superposition result of the edge weight on the propagation chain and the path propagation probability, and obtain a structural dynamic propagation chain model that reflects the disturbance diffusion intensity; Based on the spatial distribution of cumulative risk values ​​in the transmission chain model, a set of paths with a risk aggregation degree higher than the set risk density threshold is extracted to form a high-risk path cluster, which is used to guide subsequent path regulation and avoidance.

[0044] The cumulative disturbance risk value of each link is calculated as follows:

[0045] in, is the cumulative disturbance risk value of the node, is the initial disturbance source The incentive value, is the initial abnormal link node set, From the disturbance source To Node The set of all propagation paths of is the propagation attenuation factor, is the product of the path coupling strength, is the propagation probability of the disturbance along the edge (u,v), is the number of hops of path p.

[0046] The above method adjusts the disturbance risk weight by using high-risk path clusters, combines the link idleness, path forwarding delay and protocol adaptability of each service in the key and easily disturbed service set, and constructs a context-aware path migration cost model. The specific steps are as follows: Based on the high-risk path cluster, the disturbance risk level of each link is marked, and the risks of the paths in the path candidate set are accumulated to obtain the disturbance risk weight value of each candidate path. The disturbance risk level of each link is obtained by counting the number of times each link appears in the high-risk path cluster.

[0047] For each service in the key and easily disturbed service set, select the reachable path from the candidate path set and collect the link idleness of each path , path forwarding delay and protocol adaptation coefficient ; The disturbance risk weight, link resource idleness, forwarding delay and protocol adaptability are integrated into a multi-factor path migration cost function to construct a context-aware path migration cost model.

[0048] The path migration cost model is specifically:

[0049] in, is the path migration cost, 、 、 、 are the preset weight coefficients of idleness, delay, protocol adaptability, and disturbance risk in path selection (obtained based on the hierarchical analysis method), is the link idleness, is the path forwarding delay, is the protocol adaptation coefficient, is the disturbance risk weight value.

[0050] In this embodiment, the optimal switching path sequence is output, specifically: Acquire and build a path service state reasoning graph based on historical link switching and service recovery feedback data. Use a graph neural network model to learn the impact of path switching on service recovery quality and predict the expected recovery value of each candidate path for the target service. The predicted expected value of service recovery is weighted and integrated with the results of the path migration cost model to dynamically adjust the path optimization sorting strategy. Based on the recovery results of different path optimization sorting strategies in historical control feedback, the weight parameters in the path migration cost function are adaptively modified, and the candidate paths are arranged in ascending order of migration cost to form the optimal switching path sequence.

[0051] In this embodiment, the weight parameters of the path migration cost function are adaptively modified based on historical control feedback, specifically including: We collect data on the control effects of various link switching strategies under similar topologies and service types in the past, quantify the service recovery time, path quality fluctuations, and interference suppression level corresponding to each strategy, construct a strategy-effect mapping model, and use this model to drive the weight adjustment of each factor in the path cost function, so as to achieve the self-evolution of the path optimization strategy with the system status.

[0052] S5: Perform a hierarchical link switching operation according to the optimal switching path sequence, collect link status feedback data after the switching to evaluate the control result, and dynamically modify the first threshold based on the evaluation result, specifically: Based on the preferred path switching sequence, services are classified according to path migration costs. Core services with high criticality and high time sensitivity are prioritized and mapped to the lowest-cost, high-quality paths, while non-core services are allocated to redundant links or rate-limited channels to alleviate resource competition. Continuously sample the link status and service message transmission status of the switched path to obtain the packet loss rate, retransmission rate, and service recovery delay of the link after switching, forming a link control feedback indicator set; Construct a control effectiveness scoring function based on the link control feedback indicator set to generate the effectiveness score of the current path switching strategy; Compare the effectiveness score with the preset tolerance threshold. If the score is lower than the tolerance threshold for multiple consecutive rounds, dynamically adjust the first threshold for link status change judgment based on the score trend.

[0053] The regulation effectiveness scoring function is specifically:

[0054] in, Score the effectiveness. To restore the service delay, is the packet loss rate, is the retransmission rate, 、 、 They are preset weights (based on historical experience), is the maximum allowed delay, 、 They are the historical benchmark values ​​of packet loss rate and retransmission rate respectively.

[0055] In this embodiment, the effectiveness score is compared with a preset tolerance threshold. If the score is lower than the tolerance threshold for multiple consecutive rounds, the first threshold for link status change determination is dynamically adjusted based on the score trend. Specifically, The system continuously monitors the scoring results generated after path switching. When the continuous score is lower than the expected scoring threshold, it calculates the scoring deviation trend and dynamically corrects the first threshold for link status anomaly judgment based on the trend direction and magnitude. Specifically, when the scoring deviation is continuously negative and exceeds the tolerance threshold, the system lowers the threshold to improve the sensitivity of link anomaly detection; when the scoring deviation is continuously positive, the system raises the threshold to suppress over-regulation, thereby achieving threshold adaptive adjustment.

[0056] Example 2, a smart substation communication link fault self-healing control system, including the following modules: Link disturbance modeling module: used to collect the time-series operation characteristic data and service path topology data of the substation communication link, and construct a link disturbance intensity sequence that reflects the link quality fluctuation; State change detection module: This module is used to perform trend fitting and mutation identification on the link disturbance intensity sequence based on a sliding window mechanism, generating dynamically updated link state change indicators. Susceptible service identification module: used to identify the affected key susceptible service set based on the service path topology data of the abnormal link when the link status abnormality indicator exceeds the first threshold; Path evaluation module: This module combines the topological coupling relationship of key and vulnerable services, abnormal links, and historical control feedback data to build a context-aware path migration cost model and output the optimal switching path sequence. Link control and adaptive feedback module: used to perform hierarchical link switching operations according to the optimal switching path sequence, collect link status feedback data after switching to evaluate the control results, and dynamically modify the first threshold based on the evaluation results.

[0057] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0058] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0059] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0060] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0061] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0062] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for self-healing control of communication link failure in smart substation, characterized in that: The following steps are involved: Collect the time-series operation characteristic data and service path topology data of the substation communication link, and construct a link disturbance intensity sequence that reflects the link quality fluctuation; Based on the sliding window mechanism, trend fitting and mutation identification are performed on the link disturbance intensity series to generate dynamically updated link status anomaly indicators; When the link status abnormality indicator exceeds a first threshold, identifying the affected key and susceptible service sets based on the service path topology data of the abnormal link; By combining the topological coupling relationship between key and vulnerable service sets, abnormal links, and historical control feedback data, a context-aware path migration cost model is constructed to output the optimal switching path sequence. A hierarchical link switching operation is performed according to an optimal switching path sequence, link status feedback data after the switching is collected to evaluate the control result, and the first threshold is dynamically modified based on the evaluation result.

2. The method for self-healing control of communication link failure in smart substation according to claim 1, characterized in that: The link disturbance intensity sequence reflecting link quality fluctuations comprises the following specific steps: For each communication link, first data is periodically collected within a preset time window; the first data includes time series data of transmission delay data, packet loss rate and routing hop count; Calculate the fluctuation rate of the collected delay data, extract the instantaneous burst amplitude of the packet loss rate time series data, detect the discontinuity of the hop count time series data, and perform normalization processing on them respectively; The normalized delay fluctuation rate, packet loss burst increase, and hop discontinuity index are linearly combined according to preset weight coefficients to generate a disturbance intensity index that reflects the instantaneous instability level of the link. The disturbance intensity indicators at each sampling moment are aggregated in chronological order to form a link disturbance intensity sequence.

3. The method for self-healing control of communication link failure in smart substation according to claim 2, characterized in that: The link disturbance intensity sequence is subjected to trend fitting and mutation identification based on the sliding window mechanism to generate a dynamically updated link status anomaly indicator, specifically: Based on a sliding window mechanism with a preset overlap rate, the link disturbance intensity sequence is segmented and the mean and variance of the disturbance intensity within each window are calculated. Fit the change trend of the mean disturbance intensity of the current window and its previous window, and construct a mutation scoring function by combining the sudden increase of the current window disturbance intensity variance relative to the historical maker; When the mutation score exceeds the preset score threshold, a link status abnormality indicator is generated to represent the abnormal state of the link.

4. The method for self-healing control of communication link failure in smart substation according to claim 3, characterized in that: The identification of the affected key and susceptible service sets based on the service path topology data of the abnormal link is specifically as follows: Based on abnormal link nodes marked by link status anomaly indicators, the topological position of the nodes in the service path mapping relationship is analyzed to generate a link disturbance propagation map that represents the fault propagation path. For the service path containing abnormal links in the graph, the structural dependency parameters of the path relative to the abnormal link are calculated based on its path topology position and communication performance parameters; The structure-dependent parameters are weighted and fused according to preset weights to generate a path impact intensity score; Compare the impact intensity score of each path with the set interference tolerance threshold, filter the services carried by the paths with scores exceeding the threshold, and generate a set of key susceptible-to-interference services.

5. The method for self-healing control of communication link failure in smart substation according to claim 4, characterized in that: The context-aware path migration cost model is constructed as follows: Based on the key and easily disturbed service set, the topology information of the network area where the abnormal link is located and the historical interference co-occurrence data are extracted to construct a link coupling relationship matrix that characterizes the strength of the fault correlation between links. Based on the link coupling relationship matrix and the abnormal link status change indicators, a weighted graph propagation algorithm is input to generate a structural dynamic propagation chain model and output a high-risk path cluster with potential cascading failure risks. The disturbance risk weight is adjusted based on the high-risk path cluster, and the data of each business in the key and easily disturbed business set are combined to build a context-aware path migration cost model.

6. The method for self-healing control of communication link failure in smart substation according to claim 5, characterized in that: The generation structure dynamic propagation chain model outputs a high-risk path cluster containing potential cascading failure risks, specifically: Construct link propagation based on link coupling relationship matrix and state change index; Taking abnormal link nodes as the initial disturbance source, risk propagation is performed through a multi-source random walk algorithm, including defining the propagation attenuation factor, path coupling strength coefficient, and path propagation probability, calculating the cumulative disturbance risk value of each node, and outputting a structural dynamic propagation chain model that characterizes the disturbance diffusion intensity; Analyze the spatial distribution of cumulative risk values ​​in the transmission chain model, calculate the risk density value within the unit topological area, and screen the path set with risk density higher than the set threshold to form a high-risk path cluster.

7. The method for self-healing control of communication link failure in smart substation according to claim 6, characterized in that: The above method adjusts the disturbance risk weight based on the high-risk path cluster and combines the data of each service in the key and easily disturbed service set to build a context-aware path migration cost model. The specific steps are as follows: Marking the disturbance risk level of each link based on the high-risk path cluster. The risk level is determined by counting the frequency of each link appearing in the high-risk path cluster. For each candidate path in the path candidate set, the risk level values ​​of the links included are accumulated to generate the path disturbance risk weight value; For each target service in the key and easily disturbed service set, a reachable path is selected from the candidate path set, and the indicator parameters of each path are collected in real time; A context-aware path migration cost model is constructed based on indicator parameters.

8. The method for self-healing control of communication link failure in smart substation according to claim 7, characterized in that: The output optimal switching path sequence is specifically: Obtain historical link switching records and corresponding service recovery feedback data, and construct a heterogeneous graph with path nodes and service recovery quality indicators as elements; The graph neural network model learns the relationship between path switching operations and service recovery quality, and outputs the expected recovery value of each candidate path for the target service. The expected recovery value is weightedly fused with the output of the path migration cost model. Based on the fusion result, the path optimization sorting strategy is dynamically adjusted to generate the optimal switching path sequence in ascending order of migration cost. Based on the recovery results of different sorting strategies in historical control feedback, the weight parameters in the path migration cost function are dynamically corrected.

9. The method for self-healing control of communication link failure in smart substation according to claim 8, characterized in that: The step of performing a hierarchical link switching operation according to the optimal switching path sequence, collecting feedback data of the link status after the switching to evaluate the control result, and dynamically revising the first threshold value based on the evaluation result is specifically as follows: Establish a path switching optimization sequence, map core services to the path with the lowest migration cost based on the path migration cost and service level priority, and allocate non-core services to redundant links or rate-limited channels; Continuously sample the link status and service message transmission status of the switched path, collect packet loss rate, retransmission rate, and service recovery delay indicators, and form a link control feedback indicator set; Based on the link control feedback indicator set, a control effectiveness scoring function is constructed to calculate the effectiveness score of the current path switching strategy; Compare the effectiveness score with the preset tolerance threshold. If the score is lower than the tolerance threshold for multiple consecutive rounds, dynamically adjust the first threshold for link status change judgment based on the score trend.

10. A system using the method for self-healing control of communication link failure in a smart substation according to any one of claims 1 to 9, characterized in that: Includes the following modules: Link disturbance modeling module: used to collect the time-series operation characteristic data and service path topology data of the substation communication link, and construct a link disturbance intensity sequence that reflects the link quality fluctuation; State change detection module: This module is used to perform trend fitting and mutation identification on the link disturbance intensity sequence based on a sliding window mechanism, generating dynamically updated link state change indicators. Susceptible service identification module: used to identify the affected key susceptible service set based on the service path topology data of the abnormal link when the link status abnormality indicator exceeds the first threshold; Path evaluation module: This module combines the topological coupling relationship of key and vulnerable services, abnormal links, and historical control feedback data to build a context-aware path migration cost model and output the optimal switching path sequence. Link control and adaptive feedback module: used to perform hierarchical link switching operations according to the optimal switching path sequence, collect link status feedback data after switching to evaluate the control results, and dynamically modify the first threshold based on the evaluation results.

Images