A transient stability result tracing method and system for a large power grid

Abstract

The application discloses a transient stability result tracing method and system for a large power grid, and belongs to the technical field. The method comprises the following steps: based on historical user behavior data of the large power grid, a hierarchical list of key influence factors affecting transient stability results is established; based on the hierarchical list of key influence factors, a transient stability result tracing knowledge graph is constructed; based on the transient stability result tracing knowledge graph, a transient stability result tracing analysis framework is constructed; and based on the transient stability result tracing analysis framework, transient stability results of the large power grid are traced according to user behavior data of the large power grid. The application is applied to the field of power grid simulation analysis, and can realize transient stability tracing analysis based on simulation calculation, and has a certain application basis in power grid simulation analysis.

Description

Technical Field

[0001] This invention relates to the field of large power grid operation analysis technology, and more specifically, to a method and system for tracing the causes of transient stability results in large power grids. Background Technology

[0002] With the rapid development and construction of new power systems, the large-scale grid connection of new energy, pumped storage, and energy storage equipment has made the power grid operation mode more flexible and changeable, and the power grid operation characteristics and dispatch control more complex. At the same time, the requirements for power grid safety and stability analysis are gradually increasing, and the workload and intensity of simulation analysis are increasing day by day.

[0003] Because large-scale power grid simulation calculations involve numerous parameters and complex analysis of factors influencing the results, traditional methods relying on operators to quickly adjust operating modes and rapidly identify detailed transient results are difficult to implement. Transient calculations are crucial for mode operation analysis. In the entire power system, transient calculations are characterized by large computational loads and complex analysis, heavily relying on expert experience and expertise, and are time-consuming and labor-intensive. Summary of the Invention

[0004] To address the above problems, this invention proposes a method for attributing transient stability results in large power grids, comprising:

[0005] Based on historical user behavior data of the large power grid, a hierarchical list of key influencing factors affecting the transient stability results is established.

[0006] Based on the hierarchical list of key influencing factors, a knowledge graph for tracing the causes of transient stable results is constructed.

[0007] Based on the aforementioned knowledge graph for the attribution of transient stable results, a framework for the attribution analysis of transient stable results is constructed.

[0008] Based on the aforementioned metastatic stability result attribution analysis framework, the causes of the metastatic stability results of the large power grid are traced according to user behavior data of the large power grid.

[0009] Optionally, based on historical user behavior data of the large power grid, a hierarchical list of key influencing factors affecting the transient stability results can be established, including:

[0010] Historical user behavior data of the large power grid is obtained, and the historical user behavior data is preprocessed to obtain user transient stability calculation data. Historical calculation examples of the large power grid are obtained. Based on the historical calculation examples, key influencing factors at different levels affecting the transient stability results under disturbance-free anomaly and transient stability / instability scenarios are determined. The data used for transient stability calculation is associated with the key influencing factors to generate a hierarchical list of key influencing factors.

[0011] Optional, historical user behavior data, including:

[0012] Basic parameter data, steady-state data, dynamic data, calculation program data, adjustment measure data, and adjustment behavior log data.

[0013] Optional preprocessing includes cleaning and filtering of historical user behavior data.

[0014] Optionally, construct a knowledge graph for the attribution of transiently stable outcomes, including:

[0015] Based on a hierarchical list of key influencing factors, the key influencing factors, the rules and regulations followed, and the control measures are represented in the form of triples as a data structure that can be stored and utilized by a computer to generate a knowledge graph for the causal analysis of transient stable results.

[0016] Optionally, a triple consists of a node, a relation, and a node.

[0017] Optional nodes include:

[0018] State nodes, feature nodes, function nodes, weight nodes, and description nodes.

[0019] Optional relationships include:

[0020] The direct logical relationship between the two nodes.

[0021] Optionally, based on the aforementioned knowledge graph of transient stable outcomes, a framework for analyzing the causes of transient stable outcomes is constructed, including:

[0022] Identify the knowledge scenarios and corresponding task execution relationships in the knowledge graph of the transient stable results, and construct a transient stable results analysis framework based on the knowledge scenarios and corresponding task execution relationships;

[0023] The task execution relationships corresponding to the knowledge scenario include: the state of the power grid, the state transition conditions, and the actions taken under the state.

[0024] Optionally, attributing the transient stability results of the large power grid to the following causes includes:

[0025] Find the cause from the result;

[0026] For the identified causes, determine the weights of the key influencing factors corresponding to those causes;

[0027] The method of finding the cause from the result includes:

[0028] Based on the fishbone analysis method, the results are categorized and all influencing factors are listed exhaustively, and all influencing factors are considered as the causes of the results.

[0029] The process of determining the weights of key influencing factors corresponding to the identified causes includes:

[0030] The strategies or actions implemented by the large power grid are determined by the key influencing factors, and their impact on the result indicators are determined. Based on the impact, the key strategies or actions corresponding to the key changes in the result indicators are determined. The weights of the key influencing factors corresponding to the causes are determined by the determined key strategies or actions.

[0031] The weights of the key influencing factors corresponding to the identified causes are used to trace the causes of the temporary stability results of the large power grid.

[0032] Furthermore, this invention also proposes a system for tracing the causes of transient stability results in large power grids, comprising:

[0033] List building unit, used to establish a hierarchical list of key influencing factors affecting the transient stability result based on historical user behavior data of the large power grid;

[0034] The knowledge graph construction unit is used to construct a knowledge graph for tracing the causes of transient stable results based on the hierarchical list of the key influencing factors.

[0035] The analysis framework building unit is used to construct an analysis framework for the causes of transient stable results based on the knowledge graph of the causes of transient stable results.

[0036] The analysis unit is used to trace the causes of the transient stability results of the large power grid based on the transient stability result tracing analysis framework and user behavior data of the large power grid.

[0037] Optionally, based on historical user behavior data of the large power grid, a hierarchical list of key influencing factors affecting the transient stability results can be established, including:

[0038] Historical user behavior data of the large power grid is obtained, and the historical user behavior data is preprocessed to obtain user transient stability calculation data. Historical calculation examples of the large power grid are obtained. Based on the historical calculation examples, key influencing factors at different levels affecting the transient stability results under disturbance-free anomaly and transient stability / instability scenarios are determined. The data used for transient stability calculation is associated with the key influencing factors to generate a hierarchical list of key influencing factors.

[0039] Optional, historical user behavior data, including:

[0040] Basic parameter data, steady-state data, dynamic data, calculation program data, adjustment measure data, and adjustment behavior log data.

[0041] Optional preprocessing includes cleaning and filtering of historical user behavior data.

[0042] Optionally, construct a knowledge graph for the attribution of transiently stable outcomes, including:

[0043] Based on a hierarchical list of key influencing factors, the key influencing factors, the rules and regulations followed, and the control measures are represented in the form of triples as a data structure that can be stored and utilized by a computer to generate a knowledge graph for the causal analysis of transient stable results.

[0044] Optionally, a triple consists of a node, a relation, and a node.

[0045] Optional nodes include:

[0046] State nodes, feature nodes, function nodes, weight nodes, and description nodes.

[0047] Optional relationships include:

[0048] The direct logical relationship between the two nodes.

[0049] Optionally, based on the aforementioned knowledge graph of transient stable outcomes, a framework for analyzing the causes of transient stable outcomes is constructed, including:

[0050] Identify the knowledge scenarios and corresponding task execution relationships in the knowledge graph of the transient stable results, and construct a transient stable results analysis framework based on the knowledge scenarios and corresponding task execution relationships;

[0051] The task execution relationships corresponding to the knowledge scenario include: the state of the power grid, the state transition conditions, and the actions taken under the state.

[0052] Optionally, attributing the transient stability results of the large power grid to the following causes includes:

[0053] Find the cause from the result;

[0054] For the identified causes, determine the weights of the key influencing factors corresponding to those causes;

[0055] The method of finding the cause from the result includes:

[0056] Based on the fishbone analysis method, the results are categorized and all influencing factors are listed exhaustively, and all influencing factors are considered as the causes of the results.

[0057] The process of determining the weights of key influencing factors corresponding to the identified causes includes:

[0058] The strategies or actions implemented by the large power grid are determined by the key influencing factors, and their impact on the result indicators are determined. Based on the impact, the key strategies or actions corresponding to the key changes in the result indicators are determined. The weights of the key influencing factors corresponding to the causes are determined by the determined key strategies or actions.

[0059] The weights of the key influencing factors corresponding to the identified causes are used to trace the causes of the temporary stability results of the large power grid.

[0060] In another aspect, the present invention also provides a computing device, comprising: one or more processors;

[0061] A processor is used to execute one or more programs;

[0062] When the one or more programs are executed by the one or more processors, the method described above is implemented.

[0063] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method described above.

[0064] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0065] This invention provides a method for tracing the causes of transient stability results in large power grids, comprising: establishing a hierarchical list of key influencing factors affecting transient stability results based on historical user behavior data of the large power grid; constructing a knowledge graph for tracing the causes of transient stability results based on the hierarchical list of key influencing factors; constructing a tracing analysis framework for transient stability results based on the knowledge graph; and tracing the causes of transient stability results in the large power grid based on the user behavior data of the large power grid using the tracing analysis framework. This invention establishes a tracing analysis framework for transient stability results by building a knowledge graph, and the analysis framework can effectively trace the causes of transient stability results in large power grids with low computational load and high efficiency. Attached Figure Description

[0066] Figure 1 This is a flowchart of the method of the present invention;

[0067] Figure 2 This is a flowchart of an embodiment of the method of the present invention;

[0068] Figure 3 This is a fishbone analysis diagram of an embodiment of the method of the present invention;

[0069] Figure 4 This is a knowledge description diagram of simulation data modification and calculation in an embodiment of the method of the present invention;

[0070] Figure 5 This is a knowledge graph-based abductive reasoning analysis diagram of transient stability results in an embodiment of the method of the present invention;

[0071] Figure 6 This is a structural diagram of the system of the present invention. Detailed Implementation

[0072] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0073] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0074] Example 1:

[0075] This invention proposes a method for attributing transient stability results in large power grids, such as... Figure 1 As shown, it includes:

[0076] Step 1: Based on historical user behavior data of the large power grid, establish a hierarchical list of key influencing factors affecting the transient stability results;

[0077] Step 2: Based on the hierarchical list of key influencing factors, construct a knowledge graph for tracing the causes of transient stable results;

[0078] Step 3: Based on the knowledge graph of the transient stability results, construct a framework for the analysis of the causes of transient stability results;

[0079] Step 4: Based on the aforementioned transient stability result attribution analysis framework, attribution is performed on the transient stability results of the large power grid according to user behavior data.

[0080] Based on historical user behavior data of the large power grid, a hierarchical list of key influencing factors affecting the transient stability results was established, including:

[0081] Historical user behavior data of the large power grid is obtained, and the historical user behavior data is preprocessed to obtain user transient stability calculation data. Historical calculation examples of the large power grid are obtained. Based on the historical calculation examples, key influencing factors at different levels affecting the transient stability results under disturbance-free anomaly and transient stability / instability scenarios are determined. The data used for transient stability calculation is associated with the key influencing factors to generate a hierarchical list of key influencing factors.

[0082] Historical user behavior data includes:

[0083] Basic parameter data, steady-state data, dynamic data, calculation program data, adjustment measure data, and adjustment behavior log data.

[0084] Preprocessing includes cleaning and filtering historical user behavior data.

[0085] The construction of a knowledge graph for the attribution of transiently stable outcomes includes:

[0086] Based on a hierarchical list of key influencing factors, the key influencing factors, the rules and regulations followed, and the control measures are represented in the form of triples as a data structure that can be stored and utilized by a computer to generate a knowledge graph for the causal analysis of transient stable results.

[0087] A triple consists of a node, a relation, and a node.

[0088] Among them, nodes include:

[0089] State nodes, feature nodes, function nodes, weight nodes, and description nodes.

[0090] Among these, relationships include:

[0091] The direct logical relationship between the two nodes.

[0092] Specifically, based on the aforementioned knowledge graph for the attribution of transient stable outcomes, a framework for attribution analysis of transient stable outcomes is constructed, including:

[0093] Identify the knowledge scenarios and corresponding task execution relationships in the knowledge graph of the transient stable results, and construct a transient stable results analysis framework based on the knowledge scenarios and corresponding task execution relationships;

[0094] The task execution relationships corresponding to the knowledge scenario include: the state of the power grid, the state transition conditions, and the actions taken under the state.

[0095] The attribution of the transient stability results of the large power grid includes:

[0096] Find the cause from the result;

[0097] For the identified causes, determine the weights of the key influencing factors corresponding to those causes;

[0098] The method of finding the cause from the result includes:

[0099] Based on the fishbone analysis method, the results are categorized and all influencing factors are listed exhaustively, and all influencing factors are considered as the causes of the results.

[0100] The process of determining the weights of key influencing factors corresponding to the identified causes includes:

[0101] The strategies or actions implemented by the large power grid are determined by the key influencing factors, and their impact on the result indicators are determined. Based on the impact, the key strategies or actions corresponding to the key changes in the result indicators are determined. The weights of the key influencing factors corresponding to the causes are determined by the determined key strategies or actions.

[0102] The weights of the key influencing factors corresponding to the identified causes are used to trace the causes of the temporary stability results of the large power grid.

[0103] The present invention will be further described below with reference to embodiments thereof:

[0104] Implementation steps are as follows Figure 2 As shown, it includes:

[0105] Compile a hierarchical list of key influencing factors.

[0106] Construction of a knowledge graph for the etiological analysis of transient stability calculation results

[0107] Construction of an automated reasoning framework for metastability calculation results.

[0108] Intelligent cause analysis system for transient stability calculation results.

[0109] First, historical user behavior data is obtained from the database, including basic data parameters, steady-state data, dynamic data, calculation programs, adjustment measures, and adjustment behavior logs. After data cleaning and filtering, user transient stability calculation data is obtained. Through previous historical calculation examples, scenarios of disturbance-free anomalies and transient instability are collected, and factors at different levels affecting the transient stability results are sorted out to form a hierarchical list of key influencing factors.

[0110] Secondly, based on the hierarchical list of the above key influencing factors, a method for constructing a knowledge graph for causal analysis of transient stable results is proposed.

[0111] Furthermore, based on the knowledge graph of transient stability attribution, a framework for attribution analysis of transient stability results is constructed;

[0112] Finally, based on the verification of the metastability result traceability analysis framework and the comprehensive stability procedure, an intelligent traceability analysis system for metastability calculation results was developed.

[0113] The analysis results document, as part of the safety and stability control strategy, is provided for operators' reference. The knowledge graph for the cause analysis of transient stability results, its modeling principle is as follows: Figure 3 As shown,

[0114] First, the metastable result abduction knowledge is organized according to triple syntax. Second, the abduction analysis logic and process are decomposed into multiple states, each state corresponding to multiple operations, and different operations are executed in order based on weights. Finally, the metastable result abduction knowledge triples are imported into the Neo4j graph database to form a metastable result abduction knowledge base, which is then stored and managed using Neo4j. The metastable result abduction analysis framework is as follows: Figure 4 , Figure 5 As shown, firstly, an initial metastability calculation is performed to determine the current analysis state. Secondly, knowledge from the knowledge graph can intelligently guide the machine to automatically execute or adjust specific scenarios (such as power grid flow adjustment). Finally, a second metastability calculation is performed to determine the latest analysis state and whether further adjustments are needed. Through the above research, with the aim of automated reasoning analysis, a model is built based on the knowledge scenarios in the knowledge graph, as well as the corresponding states, state transition conditions, and actions that can be taken under each state. This model is then correlated with the data modification process, completing a metastability result attribution analysis framework based on task flow and knowledge graph.

[0115] The construction of a knowledge graph for transient stable attribution analysis includes:

[0116] The key influencing factors, rules and regulations, and effective control measures in the analysis process are represented in a data structure that is easy for computers to store and utilize. A triple consists of <node, relation, node>. Nodes include: state nodes, feature nodes, function nodes, weight nodes, description nodes, etc.; relations connect two nodes in the knowledge graph, representing the direct logical relationship between the two nodes. Relationships include: having features, operations, being, calling, having attributes, having weights, etc.

[0117] Taking transient stability calculation analysis as an example, the transient stability analysis knowledge triples are imported into the neo4j graph database to form a transient stability analysis knowledge base, which is then displayed in the form of a knowledge graph.

[0118] Methods for constructing causal analysis include:

[0119] Cause analysis can be described as two basic steps: finding the cause from the result and determining the weight of each possible cause.

[0120] Step 1: Find the causes from the results (identify the set of influencing factors)

[0121] Based on the three elements of causal analysis, causal analysis can be divided into three categories: inferring the result from the cause (also known as causal inference), finding the cause from the result, and inferring the cause and result from each other.

[0122] The causal analysis of key influencing factors of transient stability results belongs to the second category, which is a causal analysis method that finds the cause from the result. For example, if an anomaly is found in the transient stability curve, the cause of the anomaly is sought. A typical method is the fishbone diagram analysis method.

[0123] Fishbone diagram analysis involves categorizing and exhaustively listing all influencing factors of a problem for further analysis. The fish head represents the result (problem), the larger bones represent the categories of causes, and the smaller bones represent the specific causes. Fishbone diagram analysis is suitable for finding multiple possible causes.

[0124] Step 2: Determine the weight (significance) of each influencing factor.

[0125] The task of this causal analysis step is to assess the impact of a certain strategy or action on a certain outcome indicator that we are concerned about, and then to infer which strategies or actions triggered a certain key change in the outcome indicator that we are concerned about.

[0126] In this process, we can only deduce conclusions from the observation data, but the observation data itself is biased. We cannot know whether the observation data is influenced by specific strategies that are only part of the observation. Therefore, we need to find ways to eliminate this bias.

[0127] This invention combines the actual business scenario of transient stability calculation in large power grids, and provides an automatic reasoning analysis method for tracing the causes of transient stability problems, including uneven results of transient stability calculation curves caused by parameter input, abnormal transient stability calculations caused by unreasonable fault settings, abnormal changes in power grid state variables during transient stability calculations due to static or dynamic parameter issues, and transient stability results that do not meet expectations or lead to system instability due to multiple levels of factors such as equipment parameters, controller action events, and system stability characteristics.

[0128] Example 2:

[0129] This invention also proposes a transient stability result attribution system 200 for large power grids, such as... Figure 6 As shown, it includes:

[0130] List building unit 201 is used to establish a hierarchical list of key influencing factors affecting the transient stability results based on historical user behavior data of the large power grid.

[0131] The knowledge graph construction unit 202 is used to construct a knowledge graph for tracing the causes of transient stable results based on the hierarchical list of key influencing factors.

[0132] The analysis framework building unit 203 is used to construct a transient stability result traceability analysis framework based on the transient stability result traceability knowledge graph.

[0133] Analysis unit 204 is used to trace the causes of the transient stability results of the large power grid based on the transient stability result tracing analysis framework and user behavior data of the large power grid.

[0134] Based on historical user behavior data of the large power grid, a hierarchical list of key influencing factors affecting the transient stability results was established, including:

[0135] Historical user behavior data of the large power grid is obtained, and the historical user behavior data is preprocessed to obtain user transient stability calculation data. Historical calculation examples of the large power grid are obtained. Based on the historical calculation examples, key influencing factors at different levels affecting the transient stability results under disturbance-free anomaly and transient stability / instability scenarios are determined. The data used for transient stability calculation is associated with the key influencing factors to generate a hierarchical list of key influencing factors.

[0136] Historical user behavior data includes:

[0137] Basic parameter data, steady-state data, dynamic data, calculation program data, adjustment measure data, and adjustment behavior log data.

[0138] Preprocessing includes cleaning and filtering historical user behavior data.

[0139] The construction of a knowledge graph for the attribution of transiently stable outcomes includes:

[0140] Based on a hierarchical list of key influencing factors, the key influencing factors, the rules and regulations followed, and the control measures are represented in the form of triples as a data structure that can be stored and utilized by a computer to generate a knowledge graph for the causal analysis of transient stable results.

[0141] A triple consists of a node, a relation, and a node.

[0142] Among them, nodes include:

[0143] State nodes, feature nodes, function nodes, weight nodes, and description nodes.

[0144] Among these, relationships include:

[0145] The direct logical relationship between the two nodes.

[0146] Specifically, based on the aforementioned knowledge graph for the attribution of transient stable outcomes, a framework for attribution analysis of transient stable outcomes is constructed, including:

[0147] Identify the knowledge scenarios and corresponding task execution relationships in the knowledge graph of the transient stable results, and construct a transient stable results analysis framework based on the knowledge scenarios and corresponding task execution relationships;

[0148] The task execution relationships corresponding to the knowledge scenario include: the state of the power grid, the state transition conditions, and the actions taken under the state.

[0149] The attribution of the transient stability results of the large power grid includes:

[0150] Find the cause from the result;

[0151] For the identified causes, determine the weights of the key influencing factors corresponding to those causes;

[0152] The method of finding the cause from the result includes:

[0153] Based on the fishbone analysis method, the results are categorized and all influencing factors are listed exhaustively, and all influencing factors are considered as the causes of the results.

[0154] The process of determining the weights of key influencing factors corresponding to the identified causes includes:

[0155] The strategies or actions implemented by the large power grid are determined by the key influencing factors, and their impact on the result indicators are determined. Based on the impact, the key strategies or actions corresponding to the key changes in the result indicators are determined. The weights of the key influencing factors corresponding to the causes are determined by the determined key strategies or actions.

[0156] The weights of the key influencing factors corresponding to the identified causes are used to trace the causes of the temporary stability results of the large power grid.

[0157] This invention is applied in the field of power grid simulation analysis, and can realize transient stability cause analysis based on simulation calculation, which has a certain application basis in power grid simulation analysis.

[0158] Example 3:

[0159] Based on the same inventive concept, this invention also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement corresponding method flows or corresponding functions, thereby implementing the steps of the methods in the above embodiments.

[0160] Example 4:

[0161] Based on the same inventive concept, this invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of the method in the above embodiments.

[0162] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0163] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0164] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0165] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0166] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0167] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for attributing transient stability results in large power grids, characterized in that, include: Based on historical user behavior data of the large power grid, a hierarchical list of key influencing factors affecting the transient stability results is established. Based on the hierarchical list of key influencing factors, a knowledge graph for tracing the causes of transient stable results is constructed. Based on the aforementioned knowledge graph for the attribution of transient stable results, a framework for the attribution analysis of transient stable results is constructed. Based on the aforementioned metastatic stability result attribution analysis framework, the causes of the metastatic stability results of the large power grid are traced according to user behavior data of the large power grid. The framework for analyzing the causes of transiently stable outcomes, based on the knowledge graph, includes: Identify the knowledge scenarios and corresponding task execution relationships in the knowledge graph of the transient stable results, and construct a transient stable results analysis framework based on the knowledge scenarios and corresponding task execution relationships; The task execution relationships corresponding to the knowledge scenario include: the state of the power grid, the state transition conditions, and the actions taken under the state; The attribution of the transient stability results of the large power grid includes: Find the cause from the result; For the identified causes, determine the weights of the key influencing factors corresponding to those causes; The method of finding the cause from the result includes: Based on the fishbone analysis method, the results are categorized and all influencing factors are listed exhaustively, and all influencing factors are considered as the causes of the results. The process of determining the weights of key influencing factors corresponding to the identified causes includes: The strategies or actions implemented by the large power grid are determined by the key influencing factors, and their impact on the result indicators are determined. Based on the impact, the key strategies or actions corresponding to the key changes in the result indicators are determined. The weights of the key influencing factors corresponding to the causes are determined by the determined key strategies or actions. The weights of the key influencing factors corresponding to the identified causes are used to trace the causes of the temporary stability results of the large power grid.

2. The method for attributing transient stability results according to claim 1, characterized in that, Based on historical user behavior data from the large power grid, a hierarchical list of key influencing factors affecting the transient stability results is established, including: Historical user behavior data of the large power grid is obtained, and the historical user behavior data is preprocessed to obtain user transient stability calculation data. Historical calculation examples of the large power grid are obtained. Based on the historical calculation examples, key influencing factors at different levels affecting the transient stability results under disturbance-free anomaly and transient stability / instability scenarios are determined. The data used for transient stability calculation is associated with the key influencing factors to generate a hierarchical list of key influencing factors.

3. The method for attributing transient stability results according to claim 2, characterized in that, The historical user behavior data includes: Basic parameter data, steady-state data, dynamic data, calculation program data, adjustment measure data, and adjustment behavior log data.

4. The method for attributing transient stability results according to claim 2, characterized in that, The preprocessing includes cleaning and filtering historical user behavior data.

5. The method for attributing transient stability results according to claim 1, characterized in that, The construction of the knowledge graph for the etiology of transiently stable results includes: Based on a hierarchical list of key influencing factors, the key influencing factors, the rules and regulations followed, and the control measures are represented in the form of triples as a data structure that can be stored and utilized by a computer to generate a knowledge graph for the causal analysis of transient stable results.

6. The method for attributing transient stability results according to claim 5, characterized in that, The triple consists of a node, a relation, and a node.

7. The method for attributing transient stability results according to claim 6, characterized in that, The node includes: State nodes, feature nodes, function nodes, weight nodes, and description nodes.

8. The method for attributing transient stability results according to claim 6, characterized in that, The relationship includes: The direct logical relationship between the two nodes.

9. A system for tracing the causes of transient stability results in large power grids, characterized in that, include: List building unit, used to establish a hierarchical list of key influencing factors affecting the transient stability result based on historical user behavior data of the large power grid; The knowledge graph construction unit is used to construct a knowledge graph for tracing the causes of transient stable results based on the hierarchical list of the key influencing factors. The analysis framework building unit is used to construct an analysis framework for the causes of transient stable results based on the knowledge graph of the causes of transient stable results. The analysis unit is used to trace the causes of the transient stability results of the large power grid based on the transient stability result tracing analysis framework and user behavior data of the large power grid. The framework for analyzing the causes of transiently stable outcomes, based on the knowledge graph, includes: Identify the knowledge scenarios and corresponding task execution relationships in the knowledge graph of the transient stable results, and construct a transient stable results analysis framework based on the knowledge scenarios and corresponding task execution relationships; The task execution relationships corresponding to the knowledge scenario include: the state of the power grid, the state transition conditions, and the actions taken under the state; The attribution of the transient stability results of the large power grid includes: Find the cause from the result; For the identified causes, determine the weights of the key influencing factors corresponding to those causes; The method of finding the cause from the result includes: Based on the fishbone analysis method, the results are categorized and all influencing factors are listed exhaustively, and all influencing factors are considered as the causes of the results. The process of determining the weights of key influencing factors corresponding to the identified causes includes: The strategies or actions implemented by the large power grid are determined by the key influencing factors, and their impact on the result indicators are determined. Based on the impact, the key strategies or actions corresponding to the key changes in the result indicators are determined. The weights of the key influencing factors corresponding to the causes are determined by the determined key strategies or actions. The weights of the key influencing factors corresponding to the identified causes are used to trace the causes of the temporary stability results of the large power grid.

10. The transient stability result attribution system according to claim 9, characterized in that, Based on historical user behavior data from the large power grid, a hierarchical list of key influencing factors affecting the transient stability results is established, including: Historical user behavior data of the large power grid is obtained, and the historical user behavior data is preprocessed to obtain user transient stability calculation data. Historical calculation examples of the large power grid are obtained. Based on the historical calculation examples, key influencing factors at different levels affecting the transient stability results under disturbance-free anomaly and transient stability / instability scenarios are determined. The data used for transient stability calculation is associated with the key influencing factors to generate a hierarchical list of key influencing factors.

11. The transient stability result attribution system according to claim 10, characterized in that, The historical user behavior data includes: Basic parameter data, steady-state data, dynamic data, calculation program data, adjustment measure data, and adjustment behavior log data.

12. The transient stability result attribution system according to claim 10, characterized in that, The preprocessing includes cleaning and filtering historical user behavior data.

13. The transient stability result attribution system according to claim 9, characterized in that, The construction of the knowledge graph for the etiology of transiently stable results includes: Based on a hierarchical list of key influencing factors, the key influencing factors, the rules and regulations followed, and the control measures are represented in the form of triples as a data structure that can be stored and utilized by a computer to generate a knowledge graph for the causal analysis of transient stable results.

14. The transient stability result attribution system according to claim 13, characterized in that, The triple consists of a node, a relation, and a node.

15. The transient stability result attribution system according to claim 14, characterized in that, The node includes: State nodes, feature nodes, function nodes, weight nodes, and description nodes.

16. The transient stability result attribution system according to claim 14, characterized in that, The relationship includes: The direct logical relationship between the two nodes.

17. A computer device, characterized in that, include: One or more processors; A processor is used to execute one or more programs; When the one or more programs are executed by the one or more processors, the method described in any one of claims 1-8 is implemented.

18. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the method as described in any one of claims 1-8.

Images