A method and system for 220kV substation topology data checking and evaluation

Abstract

The application discloses a kind of for 220kV transformer substation topological data check evaluation method and system, it is related to transformer substation digital technology field, including the topological connection data of a certain area 220kV transformer substation is accessed;Based on graph database, the geographical distribution model of the area 220kV transformer substation is constructed;Topological connection check scoring evaluation is completed based on hierarchical evaluation method;The topological check score of transformer substation is demonstrated on geographical distribution diagram;Normal update, dynamically demonstrate transformer substation topological data management effectiveness.The application adopts graph database technology, constructs a set of semi-real-time tracking demonstration large amount of 220kV transformer substation topological data management process system, and topological data check method is integrated isolated original piece check, equipment name coding check and equipment quantitative relationship check, compared with prior art is more comprehensive.

Description

Technical Field

[0001] This invention relates to the field of digital technology for substations, and in particular to a method and system for verifying and evaluating topology data of 220kV substations. Background Technology

[0002] In the context of the digital transformation of power systems, higher requirements are placed on the standardization and consistency of substation topology connection data from multiple departments and systems. This necessitates research into a method and system for verifying and evaluating 220kV substation topology data. This approach utilizes graph database technology, which has gained increasing attention in recent years. The smallest granularity of the data system is expanded from discrete numbers to nodes (a set of numbers including points, edges, and their attributes). The object of processing changes from tables to the links between nodes. The computation method shifts from inter-table links and calls in relational databases to batch synchronous parallelism in graph databases. This approach adapts to the development trend of the Internet and meets the needs of large-scale, multi-dimensional, cross-system, deep, real-time queries in both physical and virtual network worlds, employing artificial intelligence as an implementation method.

[0003] In the context of the digital transformation of the power system, higher requirements are placed on the standardization and consistency of substation topology connection data from multiple departments and systems. However, existing technologies still have many shortcomings, such as: existing topology verification methods are not comprehensive, generally only verifying equipment names and numbers, and lacking verification of the quantity relationship of equipment; the system uses relational databases, which have a slow processing speed and lack tracking and display of the verification improvement process; in the context of massive data in large power systems, relational database storage has greater hardware storage requirements, etc. Summary of the Invention

[0004] In view of the problems existing in the above-mentioned substation topology connection data technology, this invention is proposed.

[0005] Therefore, the problem to be solved by this invention is how to provide a system for constructing a semi-real-time tracking and display of the governance process of large-scale 220kV substation topology data.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a method for verifying and evaluating topology data of 220kV substations, comprising: accessing topology connection data of 220kV substations in a certain area; constructing a geographical distribution model of 220kV substations in the area based on a graph database; completing the topology connection verification scoring evaluation based on a hierarchical evaluation method; displaying the substation topology verification score on a geographical distribution map; and regularly updating the data to dynamically display the effectiveness of substation topology data governance.

[0008] As a preferred embodiment of the method for verifying and evaluating the topology data of a 220kV substation described in this invention, the connection data access includes summarizing and importing data from all 220kV substations in a certain area; the substation data includes substation structured files and substation coordinate information; the format of the structured files is not limited.

[0009] As a preferred embodiment of the method for verifying and evaluating the topology data of 220kV substations described in this invention, the process of constructing the geographical distribution model of the 220kV substations in the region is as follows: The substations are modeled as supernodes, further subdivided into various types of power equipment subnodes; the latitude and longitude coordinates of the substations are used to store the geographical location information of the nodes in a geospatial database; the connection relationship between the substation nodes and the power grid lines is also stored as graph edges to support power grid topology analysis; the Tigergraph graph computing framework is used to support large-scale distributed graph database modeling and efficient querying; based on graph data mining, complex association patterns between power grid equipment are discovered, providing equipment diagnosis and fault prediction; and integration with power grid planning, scheduling, and maintenance systems supports multi-source heterogeneous data aggregation analysis.

[0010] As a preferred embodiment of the method for topology data verification and evaluation of 220kV substations described in this invention, the specific process of equipment diagnosis and fault prediction is as follows: In the Tigergraph graph database, the substation is modeled as a supernode, and equipment child nodes are associated with the substation nodes through edges; the attributes of the equipment nodes include: equipment ID, equipment type, geographic coordinates location, real-time status, and historical fault records; through a community detection algorithm, key equipment subgraph modules related to faults in the model are identified; on the subgraph modules, the Apriori algorithm is used to discover frequent itemsets of equipment status:

[0011] L1={status1, status2,..., status n}

[0012] L2={status1, status2, status3,..., status n}

[0013] Generate association rules. When frequent state patterns are detected in the subgraph module, determine the faulty device based on the association rules. Combine the pattern association degree and historical statistics to obtain the device fault prediction result: Let the state pattern be A→B→C, calculate the support of each state A, B, and C in the historical fault records: sup(A), sup(B), sup(C); calculate the state transition frequency:

[0014] conf(A→B) = sup(A,B) / sup(A)

[0015] conf(B→C)=sup(B,C) / sup(B)

[0016] Defining the failure risk index using pattern correlation:

[0017] R=w1conf(A→B)+w2conf(B→C)

[0018] Where w1 and w2 are weighting coefficients; the fault prediction level is classified according to the risk index R.

[0019] As a preferred embodiment of the method for topology data verification and evaluation of 220kV substations described in this invention, the hierarchical evaluation method includes indicator weights, indicator scores, and indicator definitions; the indicator weights are determined using a subjective weighting method and an expert method; a questionnaire is designed according to the analytic hierarchy process to compare the importance of influencing factors pairwise at the same level; and the measurement scale is divided into 9 levels.

[0020] In a preferred embodiment of the method for verifying and evaluating topology data of a 220kV substation as described in this invention, the index scoring includes primary, secondary, and tertiary indicators; all primary, secondary, and tertiary indicators are ascending indicators, with a score of 0 for values ​​below the benchmark and 100 for values ​​above the target, exhibiting a linear distribution in the middle; the formula for scoring the ascending indicator gap is as follows:

[0021]

[0022] Wherein, the target value m = 100%; the baseline value j = 0.

[0023] As a preferred embodiment of the method for topology data verification and evaluation of 220kV substations described in this invention, the definition of the indicators includes:

[0024] Isolated Component Remediation Rate: This rate determines whether a device is considered an isolated component based on whether it shares a common connection node. The specific formula is as follows:

[0025]

[0026] Switch group name and coding accuracy: Based on the identical numerical codes in the names of the circuit breaker and the isolating switches on both sides, the switch group name is identified; the numerical code includes voltage level, bay number, and switch serial number information; the accuracy of switch group name and coding is calculated as follows:

[0027]

[0028] 35kV busbar quantity accuracy: If there are no feeders at the 35kV level, the number of 35kV busbars should be the same as the number of main transformers. The specific formula is as follows:

[0029]

[0030] Accuracy rates for the number of circuit breakers and circuit isolating switches: The number of circuits is determined by the sum of the number of line-end devices and the number of transformers; the main wiring type is determined by the quantitative relationship between the ratio of circuit breakers to the number of circuits and the ratio of circuit isolating switches to the number of circuits for various main wiring types, and errors are verified.

[0031]

[0032]

[0033] Secondly, to further address the problems existing in substation topology connection data technology, this invention provides a system for verifying and evaluating 220kV substation topology data, comprising: a data access module for summarizing and importing 220kV substation topology connection data; a model building module for constructing a geographical distribution model of 220kV substations in the region based on the graph database Tigergraph; an evaluation module for verifying and scoring the topology connection data using a hierarchical evaluation method; a display module for displaying the data verification results of substations on a geographical distribution map; and an update module for periodically updating substation data and dynamically displaying the data governance effect.

[0034] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the method for topology data verification and evaluation of 220kV substations as described in the first aspect of the present invention.

[0035] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for topology data verification and evaluation of a 220kV substation as described in the first aspect of the present invention.

[0036] The beneficial effects of this invention are as follows: It employs graph database technology to construct a semi-real-time system for tracking and displaying the governance process of large-scale 220kV substation topology data. The topology data verification method integrates isolated component verification, equipment name encoding verification, and equipment quantitative relationship verification, making it more comprehensive. The system utilizes graph database technology, resulting in fast processing speed. Evaluation scores are regularly updated and displayed on the geographic distribution map of the graph data, dynamically tracking the effectiveness of 220kV substation topology data governance. In the context of massive data in large-scale power systems, graph databases significantly improve the storage scale and computational efficiency of power data. Attached Figure Description

[0037] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0038] Figure 1 This is a diagram of the topology verification and scoring method for a 220kV substation (without feeders on the 35kV low-voltage side) based on a hierarchical evaluation in Example 1.

[0039] Figure 2 This is a diagram of the topology verification and scoring method for a 220kV substation (with feeders on the low-voltage side of 35kV or 10kV) based on a hierarchical evaluation in Example 1.

[0040] Figure 3 This is a schematic diagram of the expert investigation process in Example 1.

[0041] Figure 4 This is a weighted scoring diagram for the topology verification of a 220kV substation (without feeders on the 35kV low-voltage side) based on a hierarchical evaluation in Example 1.

[0042] Figure 5 This is a weighted scoring diagram for the topology verification of a 220kV substation (with feeders on the low-voltage side of 35kV or 10kV) based on a hierarchical evaluation in Example 1.

[0043] Figure 6 This is a schematic diagram of the upward-trending indicator gap scoring in Example 2. Detailed Implementation

[0044] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0045] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0047] Example 1

[0048] Reference Figures 1-5 This is the first embodiment of the present invention, which provides a method for topology data verification and evaluation of a 220kV substation, comprising the following steps:

[0049] S1: Connect the topology connection data of a 220kV substation in a certain area.

[0050] Preferably, the structured files of all 220kV substations in a certain area are compiled and imported. The format is not limited to Excel, XML, CIM / E, or JSON. The substations include coordinate information.

[0051] Furthermore, embodiments of the data access module of the present invention involve a data access method required for the verification and evaluation of a 220kV substation model system. Specific access methods can employ the following two typical methods, but are not limited to other methods: Access Method 1: Manual Input. When the format of the required data source cannot be automatically recognized by the software, data is entered item by item through a manual interface or input interface. The module will automatically load the data into the data model module after verification. Access Method 2: Data File Import. When the required data source is a structured file format, such as Excel, XML, or CIM / E, the file is imported through the software's file loading interface. The module will automatically identify, interpret, and verify the data format based on the file type before automatically loading it into the data model module. Access Method 3: Third-Party Software System Interface Input. When the required data source comes from a third-party software system, it is obtained through database access interfaces, communication protocols, API interfaces, etc. The module will automatically identify, interpret, and verify the data before automatically loading it into the data model module.

[0052] S2: Construct a geographical distribution model of 220kV substations in this region based on a graph database.

[0053] Specifically, substations are modeled as supernodes, further subdivided into various power equipment subnodes. This hierarchical modeling captures the internal topology of substations. The latitude and longitude coordinates of substations are used to store node geographic location information in a geospatial database, supporting visualized geographic distribution analysis. The connection relationships between substation nodes and power grid lines are also stored as graph edges, supporting power grid topology analysis. The Tigergraph graph computing framework supports large-scale distributed graph database modeling and efficient querying, ensuring model scalability. Custom graph algorithms are developed to achieve power grid-specific topology analysis, such as voltage cascading identification, fault isolation, and load optimization. Graph data mining is used to discover complex correlation patterns between power grid equipment, providing equipment diagnosis and fault prediction. Integration with power grid planning, dispatching, and maintenance systems supports multi-source heterogeneous data aggregation analysis.

[0054] Preferably, graph data is used to model the power grid topology elements, with power grid equipment modeled as nodes and the relationships between equipment modeled as edges in the graph. The topology data verification results can be stored as attributes on the nodes and edges of the graph.

[0055] As a containerized device, the 220kV substation possesses latitude and longitude geographic information, allowing visualization tools to display its distribution on a geographic map. This model has distributed parallel computing capabilities for large-scale, complex network topologies.

[0056] Addressing bottlenecks in computing performance and large-scale applications.

[0057] Furthermore, the specific process of equipment diagnosis and fault prediction is as follows: In the Tigergraph graph database, substations are modeled as supernodes, and equipment child nodes are associated with substation nodes through edges; the attributes of equipment nodes include: equipment ID, equipment type, geographic coordinates (location), real-time status, and historical fault records; through community detection algorithms, key equipment subgraph modules related to faults are identified in the model. For example, if the number of communities k = 3, then C = {C1, C2, C3}; on the subgraph modules, the Apriori algorithm is used to discover frequent itemsets of equipment status:

[0058] L1={status1, status2,..., status n}

[0059] L2={status1, status2, status3,..., status n}

[0060] Generate association rules. When a frequent state pattern is detected in the subgraph module, determine the possible faulty device based on the association rules. Combine the pattern association degree and historical statistics to obtain the device fault prediction result.

[0061] Furthermore, the process of obtaining equipment failure prediction results by combining the correlation of comprehensive patterns and historical statistics is as follows:

[0062] Given the state pattern A→B→C, calculate the support sum(A), sum(B), and sum(C) of each state A, B, and C in the historical fault records; calculate the state transition frequency.

[0063] conf(A→B) = sup(A,B) / sup(A)

[0064] conf(B→C)=sup(B,C) / sup(B)

[0065] Defining the failure risk index using pattern correlation:

[0066] R=w1conf(A→B)+w2conf(B→C)

[0067] Where w1 and w2 are weighting coefficients; the fault prediction level is classified according to the risk index R.

[0068] Furthermore, if R ≥ 0.8, the fault prediction level is "extremely high"; if 0.6 ≤ R < 0.8, the fault prediction level is "high"; if 0.4 ≤ R < 0.6, the fault prediction level is "medium"; if 0.2 ≤ R < 0.4, the fault prediction level is "low"; if R < 0.2, the fault prediction level is "extremely low". The risk index level threshold is adjusted according to the equipment's historical failure rate. Finally, based on the comprehensive level result, if the prediction is medium, high, or extremely high, then equipment that may fail is reported.

[0069] S3: The topology connection verification and scoring evaluation is completed based on the hierarchical evaluation method.

[0070] Preferred hierarchical evaluation methods include indicator weights, indicator scores, and indicator definitions.

[0071] The evaluation system adopts a hierarchical evaluation method, with each level of indicator assigned a weight coefficient (the weight coefficients take into account the characteristics of 220kV substations to establish a differentiated evaluation mechanism). The corresponding weight coefficients of the lower-level indicators are superimposed on the upper-level indicators, and the process is repeated layer by layer to arrive at the comprehensive score.

[0072] Based on the topology model, scoring was completed by verifying isolated components, equipment names and numbers, and equipment quantitative relationships for voltage levels of 220kV, 110kV, and 35kV (10kV) in sequence.

[0073] It should be noted that there are two situations when the low voltage side is 35kV: one is that there is no feeder at 35kV, and the other is that there is a feeder like at 10kV. Before scoring and evaluating, it is necessary to first identify whether the low voltage side is 35kV or 10kV by using the voltage label. If it is 35kV, semantic recognition is needed to determine whether there is a feeder.

[0074] The weights of the indicators are determined using a subjective weighting method and an expert method. If there are feeders on the 35kV or 10kV side of the low voltage side, the weight of the low voltage side score will be increased.

[0075] The questionnaire was designed using the Analytic Hierarchy Process (AHP), a method that compares the importance of influencing factors pairwise within the same level. The measurement scale is divided into 9 levels, where 9, 7, 5, 3, and 1 correspond to absolutely important, very important, relatively important, slightly important, and equally important, respectively, and 8, 6, 4, and 2 indicate that the importance lies between two adjacent levels.

[0076] Expert investigation flowchart as follows Figure 3 As shown, the topology verification scoring weights are assigned as follows: Figure 3 As shown.

[0077] Furthermore, the indicator scoring includes primary, secondary, and tertiary indicators; all primary, secondary, and tertiary indicators are upward-trending indicators, with scores of 0 for values ​​below the benchmark and 100 for values ​​above the target, and a linear distribution in the middle.

[0078] The formula for scoring the gap in rising indicators is as follows:

[0079]

[0080] Wherein, the target value m = 100%; the benchmark value j = 0; and the indicator definitions include...

[0081] (1) Isolated component management rate: Based on whether the equipment has a common connection node, it is determined whether it is an isolated component. Isolated component management rate = 100 - (number of isolated components) / (total number of equipment in the area)%; (2) Switch group name and coding accuracy rate: Based on the fact that the names of the circuit breaker and the isolating switches on both sides contain the same numerical code, the switch-isolating switch name identification is completed; the numerical code contains voltage level, bay number and switch serial number information; the calculation of switch group name and coding accuracy rate is as follows: Switch group name and coding accuracy rate = 100 - (number of switch groups with incorrect names or codes) / (total number of switch groups in the area)%; (3) 35kV bus quantity accuracy rate: If there is no 35kV feeder, the number of 35kV busbars is the same as the number of 35kV busbars. The number of main transformers is consistent; the accuracy rate of the number of 35kV busbars = 100 - (35kV busbars that do not correspond to the main transformers) / (total number of main transformers)%; (4) the accuracy rate of the number of circuit breakers and the accuracy rate of the number of circuit isolators: the number of circuits is determined according to the sum of the number of line-end equipment and the number of transformers; the main wiring type is judged according to the quantitative relationship of the ratio of circuit breakers to the number of circuits and the ratio of circuit isolators to the number of circuits of various main wiring types, and the error is checked: the accuracy rate of the number of circuit breakers = 100 - (number of substations with incorrect number of circuit breakers) / (total number of substations)%; the accuracy rate of the number of circuit isolators = 100 - (number of substations with incorrect number of circuit isolators) / (total number of substations)%.

[0082] S4: Display the substation topology verification score on a geographical distribution map.

[0083] Preferably, the comprehensive score of substation topology accuracy calculated in step S3 is displayed as an attribute on the geographic distribution map of the data. Substations with a score of 100 are displayed in green, those with a score of 90 or higher but less than 100 are displayed in yellow, and those with a score of less than 90 are displayed in red. The distribution density of red is used to monitor the distribution of the data governance level of 220kV substations in the monitoring area.

[0084] S5: Regular updates dynamically showcase the effectiveness of substation topology data governance.

[0085] Preferably, to track the progress of 220kV substation topology data governance, the comprehensive score of topology accuracy needs to be dynamically updated on a regular schedule (weekly / daily / 15-minute intervals); the progress of the color lightening can intuitively show the effectiveness of the 220kV substation topology data governance; the storage of a large amount of historical data can be achieved by using a graph database combined with a time-series database, with the graph database storing the data of the current day and the time-series database storing the historical cross-sectional data before the current day.

[0086] This embodiment also provides a system for verifying and evaluating the topology data of 220kV substations, including: a data access module for summarizing and importing 220kV substation topology connection data; a model building module for constructing a geographical distribution model of 220kV substations in the region based on the graph database Tigergraph; an evaluation module for verifying and scoring the topology connection data using a hierarchical evaluation method; a display module for displaying the data verification results of substations on a geographical distribution map; and an update module for periodically updating substation data and dynamically displaying the data governance effect.

[0087] This embodiment also provides a computer device applicable to the method for verifying and evaluating topology data of a 220kV substation, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for verifying and evaluating topology data of a 220kV substation as proposed in the above embodiment.

[0088] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0089] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the method for topology data verification and evaluation of a 220kV substation as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0090] In summary, this invention employs graph database technology to construct a semi-real-time system for tracking and displaying the governance process of large-scale 220kV substation topology data. The topology data verification method integrates isolated component verification, equipment name code verification, and equipment quantitative relationship verification, making it more comprehensive. The system utilizes graph database technology, resulting in fast processing speed. Evaluation scores are regularly updated and displayed on the geographic distribution map of the graph data, dynamically tracking the effectiveness of 220kV substation topology data governance. In the context of massive data in large-scale power systems, graph databases significantly improve the storage scale and computational efficiency of power data.

[0091] Example 2

[0092] Reference Figure 6 This is the second embodiment of the present invention. Based on the first embodiment, in order to verify its beneficial effects, simulation data for a method for topology data verification and evaluation of 220kV substations is provided.

[0093] The embodiments of the present invention involve the data model definition required for a method of verifying and evaluating a 220kV substation model system. Specifically, the basic data implementation definition for a 220kV substation model is given in Tables 1 and 2 below, but is not limited to more data definitions:

[0094] Table 1 Substation Model Definition Table

[0095] Data Name Data types Data Description 1 ID String Substation ID number 2 Name String Substation name 3 Desc String Substation Description 4 Location String Substation address 5 Feeders Integer array Substation feeder array 6 PF_array floating-point array Load forecast data 7 P_his floating-point array Historical load data

[0096] Table 2 Equipment Parameter Definition Table

[0097]

[0098]

[0099] The topology connectivity verification scoring evaluation is completed based on a hierarchical evaluation method, with the following formula for scoring the difference in ascending indicators:

[0100]

[0101] Wherein, the target value m = 100%; the baseline value j = 0.

[0102] Depend on Figure 6 As can be seen, all three levels of indicators are upward-trending indicators, with scores of 0 for values ​​below the benchmark and 100 for values ​​above the target, and a linear distribution in the middle. The comprehensive score of the substation topology accuracy calculated in the previous step is displayed as an attribute on the geographic distribution map of the graph data.

[0103] In summary, the topology data verification method integrates isolated component verification, equipment name code verification, and equipment quantitative relationship verification, making it more comprehensive; the system graph database technology has a fast processing speed, and the evaluation score is regularly updated and displayed on the geographic distribution map of the graph data, dynamically tracking the effectiveness of topology data governance in 220kV substations.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for verifying and evaluating topology data of a 220kV substation, characterized in that: include: Access the topology connection data of a 220kV substation in a certain area; A geographical distribution model of 220kV substations in this region was constructed based on a graph database. The process of constructing the geographical distribution model of 220kV substations in this region is as follows: the substations are modeled as supernodes, and internally refined into various types of power equipment subnodes. Using the latitude and longitude coordinates of the substation, the geographical location information of the nodes is stored in the geospatial database; The connection relationship between substation nodes and power grid lines is also stored as graph edges to support power grid topology analysis; Tigergraph, a graph computing framework, enables large-scale distributed graph database modeling and efficient querying. Based on graph data mining, complex correlation patterns between power grid equipment are discovered, providing equipment diagnosis and fault prediction. The specific process of equipment diagnosis and fault prediction is as follows: In the Tigergraph graph database, substations are modeled as supernodes, and equipment child nodes are associated with substation nodes through edges; the attributes of equipment nodes include: equipment ID, equipment type, geographic coordinates (location), real-time status (status), and historical fault records (fault); a community detection algorithm is used to identify key equipment subgraph modules in the model that are related to faults; on the subgraph modules, the Apriori algorithm is used to discover frequent itemsets of equipment status: L1={status1,status2,...,status n }; L2={status1,status2,status3,...,status n }; Generate association rules. When frequent state patterns are detected in the subgraph module, determine the faulty device based on the association rules. Combine the pattern association degree and historical statistics to obtain the device fault prediction result. Given the state pattern A→B→C, calculate the support of each state A, B, and C in the historical fault records: sup(A), sup(B), sup(C). Calculate the state transition frequency: conf(A→B)=sup(A,B) / sup(A); conf(B→C)=sup(B,C) / sup(B); Defining the failure risk index using pattern correlation: R=w1conf(A→B)+w2conf(B→C); Where w1 and w2 are weighting coefficients; the fault prediction level is divided according to the risk index R; It integrates with power grid planning, dispatching, and maintenance systems to support multi-source heterogeneous data aggregation and analysis. Topology connectivity verification and scoring evaluation were completed based on a hierarchical evaluation method. The substation topology verification scores are displayed on a geographical distribution map; Regular updates dynamically showcase the effectiveness of substation topology data governance.

2. The method for topology data verification and evaluation of 220kV substations as described in claim 1, characterized in that: The connection data access includes summarizing and importing data from all 220kV substations in a certain area; the substation data includes substation structured files and substation coordinate information; the format of the structured files is not limited.

3. The method for topology data verification and evaluation of 220kV substations as described in claim 2, characterized in that: The hierarchical evaluation method includes indicator weights, indicator scores, and indicator definitions. The weights of the indicators are determined using a subjective weighting method and an expert method. The questionnaire is designed according to the analytic hierarchy process, and the importance of the influencing factors is compared pairwise at the same level. The measurement scale is divided into 9 levels.

4. The method for topology data verification and evaluation of 220kV substations as described in claim 3, characterized in that: The scoring of the indicators includes primary indicators, secondary indicators, and tertiary indicators; The primary, secondary, and tertiary indicators are all upward-trending indicators, with scores of 0 for values ​​below the benchmark and 100 for values ​​above the target, and a linear distribution in the middle. The formula for scoring the gap in rising indicators is as follows: ； Wherein, the target value m = 100%; the baseline value j = 0.

5. The method for topology data verification and evaluation of 220kV substations as described in claim 4, characterized in that: The definitions of the indicators include, Isolated Component Remediation Rate: This rate determines whether a device is considered an isolated component based on whether it shares a common connection node. The specific formula is as follows: ； Switch group name and coding accuracy: Based on the fact that the names of the circuit breaker and the isolating switches on both sides contain the same numerical code, complete the identification of the switch and isolating switch name; The numerical designation includes voltage level, interval number, and switch serial number information; the calculation of switch group name and coding accuracy is as follows: ； 35kV busbar quantity accuracy: If there are no feeders at the 35kV level, the number of 35kV busbars should be the same as the number of main transformers. The specific formula is as follows: ； Accuracy of circuit breaker quantity and circuit isolating switch quantity: The number of circuits is determined based on the sum of the number of line-end equipment and the number of transformers; The main wiring type is determined based on the quantitative relationship between the ratio of circuit breakers to the number of circuits and the ratio of disconnectors to the number of circuits for various main wiring types, and errors are checked. ； 。 6. A system for verifying and evaluating topology data of a 220kV substation, based on the method for verifying and evaluating topology data of a 220kV substation as described in any one of claims 1 to 5, characterized in that: include: Data access module: Used to summarize and import 220kV substation topology connection data; Model building module: Based on the graph database Tigergraph, construct a geographical distribution model of 220kV substations in the region; Evaluation module: Used to perform verification and scoring of topology connectivity data using a hierarchical evaluation method; Display module: Used to display the data verification results of substations on a geographical distribution map; Update module: Used to periodically update substation data and dynamically display the results of data governance.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for topology data verification and evaluation of 220kV substations as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for topology data verification and evaluation of 220kV substations as described in any one of claims 1 to 5.

Images