Rapid power grid recovery method under self-healing fault diagnosis

Abstract

The invention discloses a power grid rapid recovery method under self-healing fault diagnosis, relates to the related technical field of power supply systems, and constructs a power grid twinborn model based on a power grid topological structure of a target power grid. And performing self-healing capability evaluation on the power grid twinborn model, and performing hierarchical division on the power grid twinborn model according to a self-healing capability evaluation result to obtain a hierarchical power grid twinborn model. And performing fault self-healing strategy configuration from bottom to top according to the layered power grid twinborn model. Docking the power grid twinborn model with target power grid data, collecting power grid data in real time and synchronously updating the power grid data, calling a pre-constructed fault diagnosis model to perform fault diagnosis, and obtaining a fault diagnosis result. And strategy matching is carried out in the fault self-healing strategies, a corresponding fault self-healing strategy cluster is extracted, and self-healing processing of the power grid fault is carried out. The technical problem that in the prior art, a power grid self-healing fault diagnosis and recovery method is slow in response and low in efficiency, and consequently the fault recovery speed and the power supply reliability of a power grid are difficult to improve is solved.

Description

Technical Field

[0001] This application relates to the technical field of power supply systems, and specifically to a method for rapid restoration of power grids under self-healing fault diagnosis. Background Art

[0002] With the continuous improvement of the scale and complexity of modern power grids, ensuring the reliability and continuous power supply of power systems has become a major challenge. When facing problems such as equipment failures, line failures, and external interferences, traditional power grids mainly rely on manual intervention and independent system operations, which are not only time-consuming and laborious but also difficult to prevent the spread of faults or quickly restore power supply in a timely manner. The emergence of digital twin technology has provided new possibilities for the real-time simulation and analysis of power grids. By constructing a digital twin model of the power grid, the operating state and characteristics of the power grid can be simulated in a virtual space, providing a virtual environment for predicting and diagnosing faults. However, existing digital twin power grid models lack a systematic method in fault diagnosis and self-healing strategy configuration, and cannot make full use of the hierarchical structure and self-healing ability of the power grid, resulting in low fault handling efficiency and slow power grid restoration speed.

[0003] Therefore, in the prior art, there are technical problems that the response of the power grid self-healing fault diagnosis and restoration method is slow and the efficiency is low, resulting in difficulties in improving the fault restoration speed and power supply reliability of the power grid. Summary of the Invention

[0004] This application provides a method for rapid restoration of power grids under self-healing fault diagnosis, and solves the technical problems that the response of the power grid self-healing fault diagnosis and restoration method in the prior art is slow and the efficiency is low, resulting in difficulties in improving the fault restoration speed and power supply reliability of the power grid. By constructing a digital twin model of the power grid, evaluating the self-healing ability and conducting hierarchical division, and combining the simulation verification of self-healing strategies, rapid diagnosis and precise self-healing of power grid faults are achieved, improving the fault response speed and power supply reliability of the power grid.

[0005] The present application provides a method for rapid power grid restoration under self-healing fault diagnosis. The method includes: constructing a power grid twin model based on the power grid topology of the target power grid. Evaluating the self-healing ability of the power grid twin model, and hierarchically dividing the power grid twin model according to the self-healing ability evaluation result to obtain a hierarchical power grid twin model, where the hierarchical power grid twin model includes multiple hierarchical power grid twin models, and the multiple hierarchical power grid twin models correspond to different fault levels. Configuring fault self-healing strategies from bottom to top according to the hierarchical power grid twin model, where the fault self-healing strategy includes a cascaded multi-level fault self-healing strategy cluster. Connecting the power grid twin model with the data of the target power grid, collecting power grid data in real time and synchronously updating it, and invoking a pre-constructed fault diagnosis model to perform fault diagnosis to obtain a fault diagnosis result, where the fault diagnosis result includes the fault location, fault level, and fault category. Based on the fault diagnosis result, perform strategy matching in the fault self-healing strategy, extract the corresponding fault self-healing strategy cluster, and perform self-healing disposal of the power grid fault.

[0006] In an implementation manner, constructing a power grid twin model based on the power grid topology of the target power grid includes: interacting with the power grid management end of the target power grid to collect the power grid device information and device connection information of the target power grid. Constructing a reference power grid topology according to the device connection information, and combining the power grid device information to perform node definition and edge definition of the reference power grid topology to obtain the power grid twin model.

[0007] In an implementation manner, evaluating the self-healing ability of the power grid twin model, and hierarchically dividing the power grid twin model according to the self-healing ability evaluation result to obtain a hierarchical power grid twin model includes: traversing the power grid twin model, and obtaining multiple control nodes based on the node definition information. According to the self-healing disposal ability and self-healing disposal range of the multiple control nodes, and combining the preset control level definition, determine the node levels of the multiple control nodes. Perform hierarchical division according to the node levels to obtain multiple hierarchical power grid twin models, where each hierarchical power grid twin model includes the control nodes corresponding to the node levels and the subordinate device nodes.

[0008] In the implementation manner, the fault self-healing strategy configuration is performed from bottom to top according to the hierarchical power grid twin model, including: the power grid management end of the interactive target power grid calls a plurality of fault handling plans, performs self-healing feasibility verification on the plurality of fault handling plans, and extracts a plurality of self-healing handling plans. Perform statement processing on the plurality of self-healing handling plans, and configure the statement processing results as a plurality of initial policy groups. The plurality of initial policy groups correspond to a plurality of fault categories, and each initial policy group includes multi-level policy statements. Taking the plurality of hierarchical power grid twin models as configuration targets, match and call the plurality of initial policy groups from bottom to top, and the corresponding output is a multi-level fault self-healing policy cluster, which is stored as the fault self-healing strategy.

[0009] In the implementation manner, taking the plurality of hierarchical power grid twin models as configuration targets, match and call the plurality of initial policy groups from bottom to top, and the corresponding output is a multi-level fault self-healing policy cluster, which is stored as the fault self-healing strategy, including: call the first-level power grid twin model of the hierarchical power grid twin model from bottom to top. Analyze and extract the device identity information of a plurality of device nodes in the first-level power grid twin model. Based on the device fault knowledge base, combine the device identity information to define the fault feature set of the first-level power grid twin model, where the fault feature set includes a plurality of fault type information and corresponding plurality of fault level information. Taking the plurality of fault type information as the first index constraint and the plurality of fault level information as the second index constraint, perform policy statement calls on the plurality of initial policy groups, and the output is the first fault self-healing policy sub-cluster. Traverse the plurality of hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom to obtain a multi-level fault self-healing policy cluster, where each level of the fault self-healing policy cluster includes a plurality of fault self-healing policy sub-clusters. Cascade the multi-level fault self-healing policy clusters to obtain the fault self-healing strategy.

[0010] In the implementation manner, after traversing the plurality of hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom to obtain a multi-level fault self-healing policy cluster, it further includes: according to the hierarchical relationship of the plurality of hierarchical power grid twin models, perform hierarchical combination on the multi-level fault self-healing policy clusters to determine a plurality of hierarchical groups, where the hierarchical group includes a sub-first-level fault self-healing policy cluster and a parent-first-level fault self-healing policy cluster with adjacent levels. Traverse the plurality of hierarchical groups, obtain the intersection policy of the sub-first-level fault self-healing policy cluster and the parent-first-level fault self-healing policy cluster, and simplify the policy of the parent-first-level fault self-healing policy cluster with the intersection policy.

[0011] In the implementation manner, the fault self-healing strategy configuration is performed from bottom to top according to the hierarchical power grid twin model. After that, it further includes: obtaining the homologous historical fault records and the eigenhistorical fault records of the target power grid. Mutating and expanding the eigenhistorical fault records based on the homologous historical fault records to generate a fault sample set. Randomly selecting from the fault sample set and performing simulation verification of the fault self-healing strategy according to the random selection result.

[0012] In the implementation manner, the method further includes: according to the hierarchical power grid twin model, obtaining multiple subnet self-healing control units of the multiple hierarchical power grid twin models. Establishing an associated mapping between the fault self-healing strategy and the multiple subnet self-healing control units, and deploying the fault self-healing strategy locally according to the associated mapping.

[0013] It is intended to construct a power grid twin model based on the power grid topology structure of the target power grid by means of the self-healing fault diagnosis-based power grid rapid recovery method proposed in this application. Evaluate the self-healing ability of the power grid twin model, and perform hierarchical division on the power grid twin model according to the self-healing ability evaluation result to obtain a hierarchical power grid twin model, where the hierarchical power grid twin model includes multiple hierarchical power grid twin models, and the multiple hierarchical power grid twin models correspond to different fault levels. Perform fault self-healing strategy configuration from bottom to top according to the hierarchical power grid twin model, where the fault self-healing strategy includes a cascaded multi-level fault self-healing strategy cluster. Perform data docking between the power grid twin model and the target power grid, collect power grid data in real time and synchronously update it, and call a pre-constructed fault diagnosis model to perform fault diagnosis to obtain a fault diagnosis result, where the fault diagnosis result includes the fault location, fault level, and fault category. Based on the fault diagnosis result, perform strategy matching in the fault self-healing strategy, extract the corresponding fault self-healing strategy cluster, and perform self-healing disposal of the power grid fault. It solves the technical problems in the prior art that the response of the power grid self-healing fault diagnosis and recovery method is slow and the efficiency is low, resulting in difficulty in improving the power grid fault recovery speed and power supply reliability. By constructing a power grid digital twin model, evaluating the self-healing ability and performing hierarchical division, and combining the simulation verification of the self-healing strategy, it realizes the rapid diagnosis and precise self-healing of power grid faults, and improves the power grid fault response speed and power supply reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 Schematic diagram of the process of the power grid rapid recovery method under self-healing fault diagnosis provided by the embodiments of the present application; Figure 2 Schematic diagram of the process of constructing a power grid twin model for the power grid rapid recovery method under self-healing fault diagnosis provided by the embodiments of the present application. Detailed implementation manners

[0016] The above description is only an overview of the technical solution of the present application. In order to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the detailed implementation manners of the present application are specifically given below.

[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as a limitation of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0018] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily limit to those clearly listed steps or units, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0019] The embodiments of the present application provide a power grid rapid recovery method under self-healing fault diagnosis, as Figure 1 shown, the method includes: Based on the grid topology of the target grid, a grid twin model is constructed. The self-healing ability of the grid twin model is evaluated, and the grid twin model is hierarchically divided according to the self-healing ability evaluation result to obtain a hierarchical grid twin model, where the hierarchical grid twin model includes multiple hierarchical grid twin models, and the multiple hierarchical grid twin models correspond to different fault levels. The fault self-healing strategy is configured from bottom to top according to the hierarchical grid twin model, where the fault self-healing strategy includes a cascaded multi-level fault self-healing strategy cluster.

[0020] Based on the grid topology of the target grid, which refers to the connection relationship and layout mode among various devices (such as generators, transformers, transmission lines, etc.) in the grid, a grid twin model is constructed. The grid twin model, that is, the digital twin model, is a virtual mapping of the actual grid and can simulate the operating state and characteristics of the grid in the digital space. Subsequently, the self-healing ability of the grid twin model is evaluated, and the grid twin model is hierarchically divided according to the self-healing ability evaluation result to obtain a hierarchical grid twin model. Among them, the hierarchical grid twin model includes multiple hierarchical grid twin models, and the multiple hierarchical grid twin models correspond to different fault levels. Further, the fault self-healing strategy is configured from bottom to top according to the hierarchical grid twin model, so as to ensure that there is a corresponding fault self-healing strategy for each layer of the grid twin model. Among them, the fault self-healing strategy includes a cascaded multi-level fault self-healing strategy cluster, and the cascaded multi-level fault self-healing strategy cluster is multiple fault self-healing strategy clusters with associated levels.

[0021] As Figure 2 shown, the method provided by the embodiment of the present application further includes: interacting with the grid management terminal of the target grid to collect the grid device information and device connection information of the target grid. A reference grid topology is constructed according to the device connection information, and node definition and edge definition of the reference grid topology are carried out in combination with the grid device information to obtain the grid twin model.

[0022] Based on the power grid topology of the target power grid, a power grid twin model is constructed, including: the power grid management end of the interactive target power grid, which collects the power grid device information and device connection information of the target power grid. The power grid device information includes the detailed information of all devices in the power grid, including device type, parameters, location, operating status, etc. The device connection information describes the connection relationship between various devices in the power grid, that is, which devices are connected to each other and how they are connected. Subsequently, a reference power grid topology is constructed according to the device connection information, that is, a reference power grid topology with only connection relationships and layouts is constructed according to the device connection information, and the node definition and edge definition of the reference power grid topology are carried out in combination with the power grid device information, that is, detailed attributes such as device type, parameters, operating status, etc. are added to each node of the reference power grid topology, and attributes such as line parameters and switch status are added to each edge. Further, the model can be further improved according to special devices and connection methods, such as ring networks, parallel lines, series reactors, etc., to ensure the accuracy and integrity of the model. After the definition is completed, the power grid twin model is obtained, so that the physical structure and device attributes of the power grid are completely mapped and presented in the digital space.

[0023] The method provided by the embodiment of the present application further includes: traversing the power grid twin model, and obtaining a plurality of control nodes based on the node definition information. According to the self-healing disposal capabilities and self-healing disposal ranges of the plurality of control nodes, in combination with the preset control level definition, the node levels of the plurality of control nodes are determined. Hierarchical division is carried out according to the node levels to obtain a plurality of hierarchical power grid twin models, where each hierarchical power grid twin model includes the control nodes corresponding to the node levels and the subordinate device nodes.

[0024] Evaluate the self-healing ability of the power grid twin model, and perform hierarchical division on the power grid twin model according to the self-healing ability evaluation results to obtain a hierarchical power grid twin model, including: traversing the power grid twin model, obtaining multiple control nodes based on the node definition information, where the control nodes are power grid nodes with control and management capabilities in the node definition and can perform self-healing disposal operations, such as substation control centers, intelligent switches, etc. Further, according to the self-healing disposal capabilities and self-healing disposal scopes of the multiple control nodes, combined with the preset control hierarchy definition, determine the node hierarchies of the multiple control nodes. The self-healing disposal ability is the type of faults that the control node can handle and the severity of the faults that can be handled (such as the control ability for harmonics, the filtering ability for output ripple, the correction ability for power factor, etc.), and the self-healing disposal scope is the power grid scope that the control node can regulate, including the number of devices, geographical scope, etc. The control hierarchy definition is the corresponding relationship between the preset hierarchy and the self-healing disposal ability and self-healing disposal scope. Different self-healing disposal capabilities and self-healing disposal scopes have corresponding node hierarchies, and the higher the node hierarchy, the stronger the corresponding node control scope and self-healing disposal ability. Finally, perform hierarchical division according to the node hierarchies, that is, perform hierarchical division according to the node hierarchies of each control node, and use the power grid scope that the control node can regulate as a whole hierarchy to obtain multiple hierarchical power grid twin models, where each hierarchical power grid twin model includes the control nodes corresponding to the node hierarchy and the subordinate device nodes.

[0025] The method provided by the embodiment of the present application further includes: interacting with the power grid management end of the target power grid, calling multiple fault disposal plans, and performing self-healing feasibility verification on the multiple fault disposal plans to extract multiple self-healing disposal plans. Perform statement processing on the multiple self-healing disposal plans, and configure the statement processing results as multiple initial policy groups. The multiple initial policy groups correspond to multiple fault categories, and each initial policy group includes multi-level policy statements. Using the multiple hierarchical power grid twin models as the configuration target, match and call the multiple initial policy groups from bottom to top, and the corresponding output is multi-level fault self-healing policy clusters, which are stored as the fault self-healing policies.

[0026] Configure the fault self-healing strategy from bottom to top according to the hierarchical power grid twin model, including: interacting with the power grid management end of the target power grid. The disposal solutions of historical faults are recorded in the power grid management end of the target power grid, and multiple historical processing solutions of multiple faults in the power grid management end, that is, multiple fault disposal plans, are called. The fault disposal plans correspond to the fault categories one by one, and the self-healing feasibility of the multiple fault disposal plans is verified. When performing the self-healing feasibility verification, analyze the operations in the plan item by item, judge whether the conditions for automatic execution are met, and obtain the processing effect of the fault. When the processing effect and operation steps of the fault disposal plan meet the conditions for automatic execution, retain the self-healing disposal plan, otherwise eliminate the self-healing disposal plan, and then extract multiple self-healing disposal plans. Further, perform statement processing on the multiple self-healing disposal plans, that is, convert the plans described in natural language into structured policy statements that can be parsed and executed by the system. And configure the statement processing results as multiple initial policy groups. The multiple initial policy groups correspond to multiple fault categories, and each initial policy group includes multi-level policy statements. Further, taking the multiple hierarchical power grid twin models as the configuration target, match and call the multiple initial policy groups from bottom to top. According to the level corresponding to the power grid twin model, match the policy statements in the initial policy group to the corresponding model from the bottom level to the top level, so that each level corresponds to a corresponding initial policy group. Then, the corresponding output is multiple levels of the fault self-healing strategy clusters, which are stored as the fault self-healing strategy, so as to facilitate the subsequent acquisition of corresponding strategies when handling faults.

[0027] The method provided by the embodiment of this application further includes: calling the first-level power grid twin model of the hierarchical power grid twin model from bottom to top. Parse and extract the device identity information of multiple device nodes in the first-level power grid twin model. Based on the device fault knowledge base, combine the device identity information to define the fault feature set of the first-level power grid twin model, where the fault feature set includes multiple fault type information and corresponding multiple fault level information. Using the multiple fault type information as the first index constraint and the multiple fault level information as the second index constraint, call the policy statements in the multiple initial policy groups, and the output is the first fault self-healing strategy sub-cluster. Traverse the multiple hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom, and obtain multiple levels of the fault self-healing strategy clusters, where each level of the fault self-healing strategy cluster includes multiple fault self-healing strategy sub-clusters. Cascade the multiple levels of the fault self-healing strategy clusters to obtain the fault self-healing strategy.

[0028] Taking the multiple hierarchical power grid twin models as configuration targets, the multiple initial policy groups are called and matched from bottom to top, and the corresponding output is multiple levels of the fault self-healing policy clusters, which are stored as the fault self-healing policies, including: calling the first-level power grid twin model of the hierarchical power grid twin model from bottom to top, where the first-level power grid twin model is the bottommost power grid twin model, usually corresponding to the device layer, including a single device or a small-scale control node. Subsequently, parse and extract the device identity information of multiple device nodes in the first-level power grid twin model, where the device identity information is the relevant information that uniquely identifies the device node, including device ID, type, model, location, etc. Further, based on the device fault knowledge base, the device fault knowledge base is a database containing information such as the fault modes, fault types, and fault characteristics of various devices. Define the fault feature set of the first-level power grid twin model in combination with the device identity information, that is, obtain the corresponding fault features through the device fault knowledge base according to the device identity information, so as to define the fault feature set of the first-level power grid twin model. Among them, the fault feature set includes multiple fault type information and corresponding multiple fault level information. Further, taking the multiple fault type information as the first index constraint and the multiple fault level information as the second index constraint, that is, call the policy statements in the initial policy group through the fault type information and the fault level information to ensure that the subsequent obtained fault policy statements are completely matched with the faults, and then output as the first fault self-healing policy sub-cluster. Finally, traverse the multiple hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom to obtain multiple levels of the fault self-healing policy clusters, and the fault self-healing policy clusters correspond one by one to the hierarchical power grid twin models. Among them, each level of the fault self-healing policy cluster includes multiple fault self-healing policy sub-clusters.

[0029] The method provided by the embodiment of the present application further includes: according to the hierarchical relationship of the multiple hierarchical power grid twin models, perform hierarchical combination on the multiple levels of the fault self-healing policy clusters to determine multiple hierarchical groups, where the hierarchical group includes a sub-first-level fault self-healing policy cluster and a parent-first-level fault self-healing policy cluster with adjacent levels. Traverse the multiple hierarchical groups, obtain the intersection policy of the sub-first-level fault self-healing policy cluster and the parent-first-level fault self-healing policy cluster, and simplify the policy of the parent-first-level fault self-healing policy cluster with the intersection policy.

[0030] Traverse the multiple hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom to obtain multiple levels of the fault self-healing strategy clusters. After that, it further includes: according to the hierarchical relationship of the multiple hierarchical power grid twin models, perform hierarchical combination on the multiple levels of the fault self-healing strategy clusters to determine multiple hierarchical groups, and each hierarchical group is composed of the original level, the adjacent sub-levels and adjacent parent levels of the original level. Among them, the hierarchical group includes a sub-first-level fault self-healing strategy cluster and a parent-first-level fault self-healing strategy cluster with adjacent levels. Traverse the multiple hierarchical groups, obtain the intersection strategy of the sub-first-level fault self-healing strategy cluster and the parent-first-level fault self-healing strategy cluster, and simplify the strategy of the parent-first-level fault self-healing strategy cluster with the intersection strategy, that is, by removing the corresponding strategies in the original-level fault self-healing strategy cluster and the sub-first-level fault self-healing strategy cluster for the strategies with intersections in the fault self-healing strategy clusters in the hierarchical group, and retaining the strategies of the parent-first-level fault self-healing strategy cluster, so as to complete the simplification of the strategy of the parent-first-level fault self-healing strategy cluster.

[0031] The method provided by the embodiment of the present application further includes: obtaining the homologous historical fault records and the eigen historical fault records of the target power grid. Mutate and expand the eigen historical fault records based on the homologous historical fault records to generate a fault sample set. Randomly select from the fault sample set, and perform simulation verification of the fault self-healing strategy according to the random selection result.

[0032] Configure the fault self-healing strategy from bottom to top according to the hierarchical power grid twin model. After that, it further includes: obtaining the homologous historical fault records and the eigen historical fault records of the target power grid. The homologous historical fault records are the historical fault data of other power grids with the same topological structure and equipment type as the target power grid. The eigen historical fault records are the historical fault data of the target power grid itself, including various fault information that occurred in the past. Mutate and expand the eigen historical fault records based on the homologous historical fault records, that is, mutate and expand the eigen historical fault records according to the homologous historical fault records to generate more fault samples to enrich the fault sample set and generate a fault sample set. Randomly select from the fault sample set, and perform simulation verification of the fault self-healing strategy according to the random selection result.

[0033] Perform data docking between the power grid twin model and the target power grid, collect power grid data in real time and synchronously update it, and call the pre-constructed fault diagnosis model to perform fault diagnosis to obtain the fault diagnosis result. Among them, the fault diagnosis result includes the fault location, fault level, and fault category. Based on the fault diagnosis result, perform strategy matching in the fault self-healing strategy, extract the corresponding fault self-healing strategy cluster, and perform self-healing disposal of the power grid fault.

[0034] Perform the docking of the power grid twin model with the target power grid data, collect the power grid data in real time and synchronously update it, and input the real-time operation data of the actual power grid into the power grid twin model so that it can reflect the current power grid state. Then call the pre-constructed fault diagnosis model for fault diagnosis. The fault diagnosis model is constructed based on machine learning or an expert system and can quickly identify the location, level, and category of power grid faults in the power grid twin model. Obtain the fault diagnosis result, where the fault diagnosis result includes the fault location, fault level, and fault category. Finally, based on the fault diagnosis result, obtain the location, level, and category of the fault, perform policy matching in the fault self-healing strategy, extract the corresponding fault self-healing strategy cluster, and perform self-healing disposal of the power grid fault. This solves the technical problems in the prior art that the power grid self-healing fault diagnosis and recovery methods have slow response and low efficiency, resulting in difficulty in improving the power grid fault recovery speed and power supply reliability. By constructing a power grid digital twin model, evaluating the self-healing ability and performing hierarchical division, and combining the simulation verification of the self-healing strategy, fast diagnosis and precise self-healing of power grid faults are realized, and the power grid fault response speed and power supply reliability are improved.

[0035] The method provided in the embodiment of this application further includes: according to the hierarchical power grid twin model, obtain multiple subnet self-healing control units of the multiple hierarchical power grid twin models. Establish an associated mapping between the fault self-healing strategy and the multiple subnet self-healing control units, and issue the fault self-healing strategy for on-site deployment according to the associated mapping.

[0036] According to the hierarchical power grid twin model, obtain multiple subnet self-healing control units of the multiple hierarchical power grid twin models. The subnet self-healing control unit is a self-healing control unit that is lower than the level of the hierarchical power grid twin model and is associated with the hierarchical power grid twin model. Further, establish an associated mapping between the fault self-healing strategy and the multiple subnet self-healing control units, that is, establish a corresponding relationship between the fault self-healing strategy and the subnet self-healing control unit, clarify which strategies are executed by which control units, and issue the fault self-healing strategy for on-site deployment according to the associated mapping, that is, send the fault self-healing strategy to the corresponding subnet self-healing control unit through the communication network, configure and implement the fault self-healing strategy in the on-site control unit, so that it has the ability to execute the strategy.

[0037] The technical solution provided by the embodiments of the present invention constructs a power grid twin model based on the power grid topology of the target power grid. Evaluate the self-healing ability of the power grid twin model, and perform hierarchical division on the power grid twin model according to the self-healing ability evaluation result to obtain a hierarchical power grid twin model. Configure the fault self-healing strategy from bottom to top according to the hierarchical power grid twin model. Perform data docking between the power grid twin model and the target power grid, collect power grid data in real time and synchronously update it, and call the pre-constructed fault diagnosis model to perform fault diagnosis to obtain the fault diagnosis result. Based on the fault diagnosis result, perform strategy matching in the fault self-healing strategy, extract the corresponding fault self-healing strategy cluster, and perform self-healing disposal of the power grid fault. It solves the technical problems in the prior art that the response of the power grid self-healing fault diagnosis and recovery method is slow and the efficiency is low, resulting in difficulty in improving the power grid fault recovery speed and power supply reliability. By constructing a power grid digital twin model, evaluating the self-healing ability and performing hierarchical division, combined with the simulation verification of the self-healing strategy, the rapid diagnosis and precise self-healing of power grid faults are realized, and the power grid fault response speed and power supply reliability are improved.

[0038] Note that the above is only the preferred embodiment of the present invention and the applied technical principle. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described here, and various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, it can also include more other equivalent embodiments, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for rapid restoration of power grid under self-healing fault diagnosis, characterized in that, The method includes: Constructing a power grid twin model based on the power grid topology of the target power grid; Evaluating the self-healing ability of the power grid twin model, and hierarchically dividing the power grid twin model according to the self-healing ability evaluation result to obtain a hierarchical power grid twin model, where the hierarchical power grid twin model includes multiple hierarchical power grid twin models, and the multiple hierarchical power grid twin models correspond to different fault levels; Configuring fault self-healing strategies from bottom to top according to the hierarchical power grid twin model, where the fault self-healing strategy includes a cascaded multi-level fault self-healing strategy cluster; Connecting the power grid twin model with the target power grid data, collecting power grid data in real time and synchronously updating it, and invoking a pre-built fault diagnosis model to perform fault diagnosis to obtain a fault diagnosis result, where the fault diagnosis result includes the fault location, fault level, and fault category; Based on the fault diagnosis result, perform strategy matching in the fault self-healing strategy, extract the corresponding fault self-healing strategy cluster, and perform self-healing disposal of the power grid fault.

2. The fast grid restoration method under self-healing fault diagnosis according to claim 1, characterized in that Constructing a power grid twin model based on the power grid topology of the target power grid, including: Interacting with the power grid management terminal of the target power grid to collect the power grid equipment information and equipment connection information of the target power grid; Constructing a reference power grid topology according to the equipment connection information, and performing node definition and edge definition on the reference power grid topology in combination with the power grid equipment information to obtain the power grid twin model.

3. The fast power grid restoration method under self-healing fault diagnosis according to claim 2, wherein Evaluating the self-healing ability of the power grid twin model, and hierarchically dividing the power grid twin model according to the self-healing ability evaluation result to obtain a hierarchical power grid twin model, including: Traversing the power grid twin model to obtain multiple control nodes based on the node definition information; Determining the node levels of the multiple control nodes according to the self-healing disposal ability and self-healing disposal range of the multiple control nodes, in combination with the preset control level definition; Performing hierarchical division according to the node levels to obtain multiple hierarchical power grid twin models, where each hierarchical power grid twin model includes control nodes corresponding to the node levels and subordinate equipment nodes.

4. The fast power grid restoration method under self-healing fault diagnosis according to claim 3, wherein, Configuring fault self-healing strategies from bottom to top according to the hierarchical power grid twin model, including: Interacting with the power grid management terminal of the target power grid, invoking multiple fault disposal plans, and performing self-healing feasibility verification on the multiple fault disposal plans to extract multiple self-healing disposal plans; Performing statement processing on the multiple self-healing disposal plans, and configuring the statement processing results as multiple initial strategy groups, where the multiple initial strategy groups correspond to multiple fault categories, and each initial strategy group includes multi-level strategy statements; Taking the multiple hierarchical power grid twin models as the configuration targets, matching and invoking the multiple initial strategy groups from bottom to top, and correspondingly outputting multiple levels of the fault self-healing strategy clusters, which are stored as the fault self-healing strategy.

5. The fast power grid restoration method under self-healing fault diagnosis according to claim 4, characterized in that Taking the multiple hierarchical power grid twin models as the configuration targets, matching and invoking the multiple initial strategy groups from bottom to top, and correspondingly outputting multiple levels of the fault self-healing strategy clusters, which are stored as the fault self-healing strategy, including: Invoking the first-level power grid twin model of the hierarchical power grid twin model from bottom to top; Analyze and extract the device identity information of multiple device nodes in the first-level power grid twin model; Based on the device failure knowledge base, define the failure feature set of the first-level power grid twin model in combination with the device identity information, where the failure feature set includes multiple failure type information and corresponding multiple failure level information; Using the multiple failure type information as the first index constraint and the multiple failure level information as the second index constraint, call the policy statements for multiple initial policy groups, and the output is the first failure self-healing policy cluster; Traverse the multiple hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom, and obtain multiple levels of the failure self-healing policy clusters, where each level of the failure self-healing policy cluster includes multiple failure self-healing policy clusters; Cascade multiple levels of the failure self-healing policy clusters to obtain the failure self-healing policy.

6. The fast power grid restoration method under self-healing fault diagnosis according to claim 5, wherein Traverse the multiple hierarchical power grid twin models of the hierarchical power grid twin model from top to bottom, and obtain multiple levels of the failure self-healing policy clusters. After that, it further includes: According to the hierarchical relationship of the multiple hierarchical power grid twin models, perform hierarchical combination on the multiple levels of the failure self-healing policy clusters to determine multiple hierarchical groups, where the hierarchical group includes a sub-first-level failure self-healing policy cluster and a parent-first-level failure self-healing policy cluster with adjacent levels; Traverse the multiple hierarchical groups, obtain the intersection policy of the sub-first-level failure self-healing policy cluster and the parent-first-level failure self-healing policy cluster, and simplify the policy of the parent-first-level failure self-healing policy cluster with the intersection policy.

7. The fast power grid restoration method under self-healing fault diagnosis according to claim 1, characterized in that After performing the failure self-healing policy configuration from bottom to top according to the hierarchical power grid twin model, it further includes: Obtain the homologous historical failure records and the eigenhistorical failure records of the target power grid; Mutate and expand the eigenhistorical failure records based on the homologous historical failure records to generate a failure sample set; Randomly select from the failure sample set, and perform simulation verification of the failure self-healing policy according to the random selection result.

8. The fast power grid restoration method under self-healing fault diagnosis according to claim 1, characterized in that The method further includes: According to the hierarchical power grid twin model, obtain multiple subnet self-healing control units of the multiple hierarchical power grid twin models; Establish an associated mapping between the failure self-healing policy and the multiple subnet self-healing control units, and issue the failure self-healing policy for in-situ deployment according to the associated mapping.

Images