New Energy Grid-Connected Path Optimization Configuration Method and System Based on Knowledge Graph Technology

Abstract

The present invention discloses a new energy grid connection path optimization configuration method and system based on knowledge graph technology, belonging to the field of distribution network dispatching technology, and including the following steps: acquiring grid operation data and performing scene similarity analysis and attribute similarity analysis on it to determine an abnormal map; expanding the original database through the abnormal map and extracting texture information and graphic element information in the expanded target database to construct a distribution network knowledge graph; determining an abnormal coexistence area according to the abnormal situation in combination with the distribution network knowledge graph, obtaining a load transfer path according to the abnormal transition factor of the abnormal coexistence area, and performing transfer situation analysis on the load transfer path to determine a target transfer strategy. The solution introduces a multi-objective path search algorithm driven by an abnormal transition factor to search for the optimal transfer path that meets the connection constraint, generates a transfer strategy that takes into account reliability, economy, and risk controllability, and significantly improves the generation efficiency and reliability of the transfer strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network scheduling. Specifically, it relates to a method and system for optimizing the configuration of new energy grid connection paths based on knowledge graph technology. Background Art

[0002] With the large-scale grid connection of new energy, the complexity and uncertainty of the distribution network have increased significantly. Traditional anomaly handling methods mainly rely on static databases and manual experience, and there are the following technical barriers: 1) relying on preset fault sets and static topology analysis, it is impossible to capture the correlation between new energy output fluctuations, load dynamic changes, and grid anomaly evolution in real time, resulting in a lag in anomaly area positioning and a fuzzy boundary description; 2) no semantic association of multi-source heterogeneous data (such as SCADA measurements, equipment ledgers, historical maintenance records) is established, resulting in a lack of global knowledge support for anomaly propagation path prediction and transfer supply strategy generation; 3) only evaluating transfer supply paths through topological connectivity or simple economic indicators, ignoring the impact of dynamic parameters such as equipment health status, real-time load rate, and risk degree on decision-making, it is easy to have problems such as transfer supply path overload or failure in high-penetration new energy scenarios.

[0003] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present application. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0004] The object of the present invention is to address the problems of poor dynamic adaptation ability to abnormal scenarios, low accuracy in predicting abnormal propagation paths, and single load transfer supply strategy in the prior art. The present invention proposes a method and system for optimizing the configuration of new energy grid connection paths based on knowledge graph technology. Through dual analysis of scenario similarity and attribute similarity, an abnormal map reflecting the spatio-temporal evolution law of grid anomalies is dynamically constructed to achieve accurate description of abnormal boundaries; based on the causal chain and rule chain reasoning mechanisms of the knowledge graph, the equipment texture information (such as electrical parameters) and graphic element information (such as topological connections) are deeply integrated to construct a dynamically expandable distribution network knowledge graph, enhancing the correlation mining ability of abnormal co-occurrence regions; introducing a multi-objective path search algorithm driven by an abnormal transition factor to search for the optimal transfer supply path that meets the connection constraints, generating a transfer supply strategy that takes into account reliability, economy, and risk controllability, significantly improving the generation efficiency and reliability of the transfer supply strategy.

[0005] In a first aspect, a technical solution provided in an embodiment of the present invention is: A method for optimizing the configuration of new energy grid connection paths based on knowledge graph technology, including the following steps:

[0006] Obtain grid operation data and perform scenario similarity analysis and attribute similarity analysis on it to determine an abnormal map;

[0007] Expand the native database through the anomaly map, extract the texture information and primitive information in the expanded target database, and construct a knowledge graph of the distribution network;

[0008] Determine the abnormal symbiotic area according to the abnormal situation in combination with the knowledge graph of the distribution network, obtain the load transfer path according to the abnormal transition factor of the abnormal symbiotic area, and conduct a transfer situation analysis on the load transfer path to determine the target transfer strategy.

[0009] Preferably, obtain the power grid operation data and conduct a scene similarity analysis and an attribute similarity analysis on it to determine the anomaly map; the method includes the following steps:

[0010] Obtain the abnormal records of the distribution network and the corresponding repair records, and determine the abnormal type, texture information, and primitive information corresponding to each primitive in the time dimension;

[0011] Perform time-domain slicing on the distribution network abnormal scene with the abnormal point as the center to determine the abnormal portrait corresponding to each time-domain slice;

[0012] Determine the scene similarity of the abnormal portrait based on the texture information and the abnormal type;

[0013] Determine the attribute similarity of the abnormal portrait based on the primitive information and the abnormal type;

[0014] Determine the abnormal boundary and repair window of each time-domain section based on the scene similarity and the attribute similarity, and construct an anomaly map based on the abnormal boundary and the repair window.

[0015] Preferably, the construction process of the distribution network knowledge graph includes:

[0016] Obtain the topological structure data and power grid operation data during the normal operation of the distribution network to construct a native database; extract the time-domain information matching the abnormal points in the native database, extract the texture information and primitive information of the time-domain section information corresponding to the abnormal point map, and determine the abnormal data according to the topological structure and the power flow direction with the abnormal point as the center; expand the native database according to the abnormal data to obtain a target database; extract the texture information in the target database to determine the causal chain and the primitive information to determine the rule chain; determine the distribution network knowledge graph corresponding to the abnormal point according to the causal chain and the rule chain.

[0017] Preferably, the determining the abnormal symbiotic area according to the abnormal situation in combination with the distribution network knowledge graph includes the following steps:

[0018] Extract the three-dimensional features of the current abnormal point, and index the historical abnormal records associated with the same-name equipment nodes according to the distribution network knowledge graph; activate the time dimension label in the graph and match the time-domain features corresponding to the current abnormal point;

[0019] Centered on the abnormal point, calculate the Euclidean distances of all devices within the set area, and construct the spatial adjacent distance according to the topological structure; traverse the connection relationships and logical relationships in the knowledge graph to identify the abnormal propagation path;

[0020] Construct a symbiotic feature library according to device homology and spatial proximity characteristics; calculate the Jaccard coefficient of the current abnormal combination and the historical pattern in turn, and activate the initial symbiotic area range of the corresponding pattern according to the Jaccard coefficient;

[0021] Determine the state estimation factor of the symbiotic area according to the abnormal situation and device health, and adjust the boundary of the initial symbiotic area range according to the state estimation factor to obtain the abnormal symbiotic area.

[0022] Preferably, obtain the load transfer path according to the abnormal transition factor of the abnormal symbiotic area, and conduct a transfer situation analysis on the load transfer path to determine the target transfer strategy; the steps are as follows:

[0023] Extract the device health, historical transfer rate, and real-time load rate of the devices within the abnormal symbiotic area from the distribution network knowledge graph, and combine the corresponding weight coefficients to determine the device abnormal transition factor;

[0024] Starting from the abnormal symbiotic area, search all device nodes in the distribution network knowledge graph that have a connection relationship with this area, and use the device nodes as candidate load transfer paths;

[0025] Construct a multi-dimensional transfer situation evaluation index system through reliability indicators, economic indicators, timeliness indicators, and risk degree indicators, calculate the comprehensive score of each candidate load transfer path, and use the candidate load transfer path with the highest comprehensive score as the target transfer path.

[0026] Preferably, starting from the abnormal symbiotic area, search all device nodes in the distribution network knowledge graph that have a connection relationship with this area, and use the device nodes as candidate load transfer paths; the steps are as follows:

[0027] Set the constraint conditions for path search, and the constraint conditions at least include connection switch capacity limit and voltage deviation threshold constraint; use the improved Dijkstra algorithm with the reciprocal of the abnormal transition factor as the heuristic information for path search, and gradually search for the shortest path from the starting point to each potential transfer path node; during the search process, continuously check whether the path meets the constraint conditions, and discard the path if it does not meet; for the searched paths, calculate the sum of the abnormal transition factors of all devices on each path, and select the top n paths with the smallest sum of abnormal transition factors as candidate load transfer paths.

[0028] Preferably, historical transfer records of equipment on the path are obtained from the distribution network knowledge graph, and the historical transfer success rate is calculated by counting the ratio of the number of successful transfers to the total number of transfers to obtain the reliability index;

[0029] The line resistance, transfer current, and transfer time on the path are obtained from the distribution network knowledge graph to determine the power loss during transfer to obtain the economic index;

[0030] The switch action time of the equipment on the path and the operation duration of the switchgear are obtained to calculate the total time required for the entire transfer process to obtain the timeliness index;

[0031] The transfer risk value is calculated based on the sum of the abnormal transition factors, load volatility, and their corresponding weights of the equipment on the path to obtain the risk degree index.

[0032] In a second aspect, a technical solution provided in an embodiment of the present invention is: a new energy grid connection path optimization configuration system, including:

[0033] A determination module: obtains grid operation data and performs scene similarity analysis and attribute similarity analysis on it to determine an abnormal map;

[0034] A construction module: expands the native database through the abnormal map and extracts the texture information and graphic element information in the expanded target database to construct a distribution network knowledge graph;

[0035] A generation module: determines an abnormal coexistence area according to the abnormal situation in combination with the distribution network knowledge graph, obtains a load transfer path according to the abnormal transition factor of the abnormal coexistence area, and performs transfer situation analysis on the load transfer path to determine a target transfer strategy.

[0036] In a third aspect, a technical solution provided in an embodiment of the present invention is: including a memory and a processor, where a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the new energy grid connection path optimization configuration method based on knowledge graph technology are implemented.

[0037] In a fourth aspect, a technical solution provided in an embodiment of the present invention is: computer-executable instructions are stored in the storage medium, and when the computer-executable instructions are loaded and executed by the processor, the steps of the new energy grid connection path optimization configuration method based on knowledge graph technology are implemented.

[0038] Advantages of the present invention:

[0039] (1) Aiming at the problems of lagging and blurred boundaries in traditional abnormal area localization, this application dynamically constructs an abnormal map through dual analysis of scene similarity and attribute similarity, achieving precise characterization of abnormal boundaries. Specifically, time-domain slicing is performed using abnormal records and repair records, and scene similarity and attribute similarity are calculated by combining texture information (such as electrical parameters) and primitive information (such as topological connections), dynamically generating an abnormal map containing abnormal boundaries and repair windows, solving the problem that traditional static topological analysis cannot real-time associate new energy fluctuations with load dynamic changes, significantly improving the accuracy of abnormal area localization, significantly shortening the abnormal response time, and avoiding the expansion of faults;

[0040] (2) Aiming at the problem of insufficient decision-making support due to the lack of semantic association of multi-source heterogeneous data, through causal chain (equipment electrical parameter association) and rule chain (topological connection logic) reasoning mechanisms, heterogeneous data such as SCADA measurements, equipment ledgers, and historical operation and maintenance records are associated to form a dynamically extensible knowledge graph, enhancing the global knowledge reasoning ability to support more complex power grid abnormal decision-making scenarios;

[0041] (3) Aiming at the problem of single evaluation index for traditional power transfer paths, this application introduces a multi-objective path search algorithm driven by an abnormal transition factor to generate an optimal power transfer strategy that takes into account multiple dimensions; constructs an abnormal transition factor by combining dynamic parameters such as equipment health, historical power transfer rate, and real-time load rate, uses an improved Dijkstra algorithm to search for the optimal path that meets the connection constraints, and makes a comprehensive decision through a four-dimensional evaluation system of reliability, economy, timeliness, and risk degree. Avoid the risk of overload or failure of power transfer paths and significantly enhance the resilience of the power grid.

[0042] The above invention content is only an overview of the technical solution of the present invention. In order to be able to more clearly understand the technical means of the present invention, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, purposes and advantages of the present invention will become more obvious. The drawings are only used for the purpose of showing the preferred embodiments and are not considered as a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components.

[0044] Figure 1 It is a flowchart of the new energy grid connection path optimization configuration method based on knowledge graph technology of the present invention.

[0045] Figure 2 It is a schematic structural diagram of the new energy grid connection path optimization configuration system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation manners described herein are only the best embodiments of the present invention, which are only used to explain the present invention and do not limit the protection scope of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0047] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations (or steps) can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. When the operations are completed, the process can be terminated, but there may also be additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, and so on.

[0048] Embodiment: As Figure 1 shown, a new energy grid connection path optimization configuration method based on knowledge graph technology includes the following steps:

[0049] S1. Obtain grid operation data and perform scene similarity analysis and attribute similarity analysis on it to determine the abnormal map.

[0050] As an alternative embodiment, S1 includes the following steps:

[0051] Obtain the abnormal records and corresponding repair records of the distribution network to determine the abnormal types, texture information, and graphic element information corresponding to each graphic element in the time dimension;

[0052] Perform time-domain slicing on the distribution network abnormal scene with the abnormal points to determine the abnormal portrait corresponding to each time-domain slice;

[0053] Determine the scene similarity of the abnormal portrait based on the texture information and abnormal types;

[0054] Determine the attribute similarity of the abnormal portrait based on the graphic element information and abnormal types;

[0055] Determine the abnormal boundary and repair window of each time-domain section based on the scene similarity and attribute similarity, and construct an abnormal map based on the abnormal boundary and repair window.

[0056] It is understandable that taking the 10kV distribution network connected to a wind farm in a coastal area as an example, frequent fluctuations in wind power output in this area have led to frequent abnormal events such as voltage over-limit and line overload. Obtain historical abnormal records (such as voltage dips, line tripping) in the past 3 years and corresponding repair records (such as breaker operation time, load shedding). Abstract the distribution network equipment (such as transformer T1, feeder L5) as graphic element nodes, and associate their electrical parameters (impedance, capacity) with the time-series status (such as the load factor of T1 is 85% at 10:00 on August 15, 2023). For a voltage abnormal event caused by a certain typhoon weather, taking the abnormal occurrence time (14:30 on September 1, 2023) as the center, expand 30 minutes forward and backward to form a time-domain slice (14:00 - 15:00). Extract the texture information (such as voltage deviation ±7%) and graphic element information (topological connection between L5 and T1) of each device within the slice, generate an abnormal portrait, and mark the abnormal type as "voltage over-limit caused by new energy fluctuations".

[0057] Furthermore, compare the current abnormal portrait with historical portraits (such as a similar event caused by a typhoon in July 2022), and calculate the scenario similarity as 0.88 (threshold 0.75) based on the texture information (voltage deviation trend matching degree 92%) and abnormal type (both are voltage over-limit). Calculate the attribute similarity: Calculate the attribute similarity as 0.91 through the graphic element information (topological connection consistency 95%, same device type). Integrate the results of the two similarities (weighted score 0.89), determine that the abnormal boundary covers feeders L5, L6 and adjacent nodes N12 - N15, and predict the repair window as "it is necessary to cut off the load of L5 and start energy storage compensation within 15 minutes". The abnormal map shows the highest risk level (red) in the L5 area in the form of a heat map and recommends the priority repair strategy.

[0058] S2. Expand the original database through the abnormal map and extract the texture information and graphic element information in the expanded target database to construct a distribution network knowledge graph.

[0059] As an alternative embodiment, S2 includes the following steps:

[0060] Obtain the topological structure data and grid operation data during the normal operation of the distribution network to construct the original database; extract the time-domain information matching the abnormal points in the original database, extract the texture information and graphic element information of the time-domain section information corresponding to the abnormal point map, and determine the abnormal data according to the topological structure and power flow direction with the abnormal point as the center; expand the original database according to the abnormal data to obtain the target database; extract the texture information in the target database to determine the causal chain and the graphic element information to determine the rule chain; determine the distribution network knowledge graph corresponding to the abnormal point according to the causal chain and the rule chain.

[0061] It is understandable that for the above-mentioned grid-connected area of the wind farm, the native database contains 500 device nodes, 2,000 topological connection relationships, and SCADA real-time measurement data. The topological structure exported from the GIS system (such as L5 connecting T1 and the wind turbine group WF1) is associated and stored with the SCADA measurement data (such as the output fluctuation range of WF1 being 0 - 5 MW). Match the time-domain section information of the current abnormal point L5, and extract its texture information (voltage volatility of 12% / min) and graphic element information (downstream connection to the energy storage system ESS1).

[0062] Construct a causal chain "new energy output fluctuation → L5 overload → ESS1 charge and discharge response delay" according to the power flow direction (L5 → ESS1) and store it in the target database. Define a rule based on the graphic element connection relationship: "If the load rate of L5 > 90% and the ESS1 SOC < 20%, then trigger load transfer". Add the new abnormal data (such as the L5 overload event) to the knowledge graph in the form of a triple (L5, hasFaultType, VoltageSag) and associate it with historical events (similar faults in 2022). When the SCADA detects a sudden increase in the load rate of L5, the knowledge graph automatically activates the association rule and pushes the suggestion of "start ESS1 compensation" to the dispatching system.

[0063] S3. Determine the abnormal coexistence area according to the abnormal situation in combination with the distribution network knowledge graph, obtain the load transfer path according to the abnormal transition factor of the abnormal coexistence area, and conduct a transfer situation analysis on the load transfer path to determine the target transfer strategy.

[0064] As an alternative embodiment, the determination of the abnormal coexistence area according to the abnormal situation in combination with the distribution network knowledge graph includes the following steps:

[0065] Extract the three-dimensional features of the current abnormal point, and index the historical abnormal records associated with the device nodes of the same name according to the distribution network knowledge graph; activate the time dimension label in the knowledge graph and match the time-domain features corresponding to the current abnormal point;

[0066] Taking the abnormal point as the center, calculate the Euclidean distance of all devices within the set area range, and construct the spatial adjacent distance according to the topological structure; traverse the connection relationships and logical relationships in the knowledge graph to identify the abnormal propagation path;

[0067] Construct a coexistence feature library according to device homology and spatial proximity characteristics; calculate the Jaccard coefficient of the current abnormal combination and the historical pattern in turn, and activate the initial coexistence area range of the corresponding pattern according to the Jaccard coefficient;

[0068] Determine the state estimation factor of the coexistence area according to the abnormal situation and device health, and adjust the boundary of the initial coexistence area range according to the state estimation factor to obtain the abnormal coexistence area.

[0069] In this embodiment, it is assumed that the output of a certain photovoltaic power station drops suddenly, causing the voltage of feeder L7 to be abnormal, and a transfer path needs to be generated quickly; the spatial coordinates (x = 32.5, y = 45.2), timestamp (October 10, 2023, 11:20), and electrical characteristics (voltage drops to 0.9 pu) of the abnormal point of L7 are extracted. By retrieving the historical abnormal records of the devices with the same name as L7 in the knowledge graph, it is found that in June 2023, the same voltage characteristics were caused by lightning strikes, and the initial co - existing area covered L7, L8, and circuit breaker CB3. The Jaccard coefficient of the current abnormal combination (abnormal voltage of L7 + health degree of CB3 is 72%) and the historical mode is 0.82, and the co - existing area is extended to the adjacent capacitor C1 (state estimation factor = 0.75×health degree + 0.25×load rate = 0.68).

[0070] As an alternative embodiment, the load transfer path is obtained according to the abnormal transition factor of the abnormal co - existing area, and the transfer situation of the load transfer path is analyzed to determine the target transfer strategy; the following steps are included:

[0071] Extract the device health degree, historical transfer rate, and real - time load rate of the devices in the abnormal co - existing area from the distribution network knowledge graph, and combine the corresponding weight coefficients to determine the device abnormal transition factor;

[0072] Starting from the abnormal co - existing area, search for all device nodes in the distribution network knowledge graph that have a connection relationship with this area, and use these device nodes as candidate load transfer paths;

[0073] Construct a multi - dimensional transfer situation evaluation index system through reliability indicators, economic indicators, timeliness indicators, and risk degree indicators, calculate the comprehensive score of each candidate load transfer path, and use the candidate load transfer path with the highest comprehensive score as the target transfer path.

[0074] In this embodiment, the device health degree (weight 0.6), historical transfer rate (0.3), and real - time load rate (0.1). For the devices in the co - existing area, calculate: CB3: health degree 72%×0.6 + transfer rate 85%×0.3 + load rate 88%×0.1 = 76.3%; C1: health degree 65%×0.6 + transfer rate 70%×0.3 + load rate 50%×0.1 = 64.5%; Path screening: Only select devices with a transition factor > 70% to participate in the transfer.

[0075] As an alternative embodiment, starting from the abnormal co - existing area, search for all device nodes in the distribution network knowledge graph that have a connection relationship with this area, and use these device nodes as candidate load transfer paths; the following steps are included:

[0076] Set the constraint conditions for path search, where the constraint conditions at least include the capacity limit of tie switches and the voltage deviation threshold constraint; use the improved Dijkstra algorithm with the reciprocal of the abnormal transition factor as the heuristic information for path search, and gradually search for the shortest paths from the starting point to each potential load transfer path node; during the search process, continuously check whether the path meets the constraint conditions, and discard the path if it does not; for the searched paths, calculate the sum of the abnormal transition factors of all devices on each path, and select the top n paths with the smallest sum of abnormal transition factors as the candidate load transfer paths.

[0077] In this embodiment, the capacity limit of the tie switch (≤1000A) and the voltage deviation threshold (±10%); use the reciprocal of the transition factor (1 / 76.3≈0.013) as the search weight, and traverse the tie nodes (such as L9, ESS2) starting from L7; two candidate paths are searched in this embodiment: Path 1: L7→CB3→L9 (the sum of transition factors 76.3 + 81.2 = 157.5, time-consuming 12s); Path 2: L7→C1→ESS2 (the sum of transition factors 64.5 + 89.1 = 153.6, time-consuming 15s). Table 1 shows the calculation table of the comprehensive scores of the paths.

[0078] Table 1. Calculation Table of Comprehensive Scores

[0079]

[0080] It can be seen from Table 1 that Path 1 is selected as the target transfer path, and control instructions are automatically sent to the CB3 and L9 switches.

[0081] As an alternative embodiment, obtain the historical transfer records of the devices on the path from the distribution network knowledge graph, and calculate the historical transfer success rate by counting the ratio of the number of successful transfers to the total number of transfers to obtain the reliability index;

[0082] Obtain the line resistance, transfer current, and transfer time on the path from the distribution network knowledge graph to determine the loss of transferred power to obtain the economic index;

[0083] Obtain the switch action time of the devices on the path and the operation duration of the switchgear to calculate the total time required for the entire transfer process to obtain the timeliness index;

[0084] Calculate the transfer risk value according to the sum of the abnormal transition factors of the devices on the path, the load volatility, and their corresponding weights to obtain the risk degree index.

[0085] Embodiment 2: Second, another technical solution provided in the embodiments of the present invention is: a new energy grid-connected path optimization configuration system, as Figure 2 shown, including:

[0086] Determination module 101: Obtain power grid operation data, perform scenario similarity analysis and attribute similarity analysis on it to determine the abnormal map;

[0087] Construction module 102: Expand the native database through the abnormal map and extract the texture information and primitive information in the expanded target database to construct a distribution network knowledge graph;

[0088] Generation module 103: Determine the abnormal symbiotic area according to the abnormal situation combined with the distribution network knowledge graph, obtain the load transfer path according to the abnormal transition factor of the abnormal symbiotic area, and perform transfer situation analysis on the load transfer path to determine the target transfer strategy.

[0089] Embodiment 3: Thirdly, a technical solution provided in an embodiment of the present invention is: including a memory and a processor, a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the new energy grid connection path optimization configuration method based on the knowledge graph technology are implemented.

[0090] Embodiment 4: An alternative embodiment provided in an embodiment of the present invention is: a storage medium, a computer executable instruction is stored in the storage medium, and when the computer executable instruction is loaded and executed by a processor, the steps of the new energy grid connection path optimization configuration method based on the knowledge graph technology are implemented.

[0091] Through the description of the above embodiments, those skilled in the art can understand that for the convenience and brevity of description, only the above division of each functional module is used as an example for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of a specific device is divided into different functional modules to complete all or part of the functions described above.

[0092] In the embodiments provided in the present application, it should be understood that the disclosed structure and method can be implemented in other ways. For example, the above-described embodiment of the structure is only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another structure, or some features can be ignored or not executed. Another point, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, and the indirect coupling or communication connection of structures or units may be in electrical, mechanical or other forms.

[0093] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may be a physical unit or multiple physical units, that is, it may be located in one place or may be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, each functional unit in the embodiments of the present application can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0095] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read only memory (ROM), random access memory (RAM), magnetic disks or optical discs and other various media that can store program codes.

[0096] The above-mentioned specific implementation manners are the preferred implementation manners of the new energy grid-connected path optimization configuration method and system based on the knowledge graph technology of the present invention, and do not limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation manner. Any equivalent changes made according to the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A new energy grid connection path optimization configuration method based on knowledge graph technology, characterized by: The steps include: Obtain power grid operation data and perform scene similarity analysis and attribute similarity analysis on it to determine the abnormal map; The native database is expanded through the abnormal map and the texture information and graphic element information in the expanded target database are extracted to build the distribution network knowledge graph; According to the abnormal situation and the knowledge graph of the distribution network, the abnormal symbiosis area is determined, the load transfer path is obtained according to the abnormal transition factor of the abnormal symbiosis area, and the load transfer situation analysis is performed on the load transfer path to determine the target transfer strategy; The method of determining the abnormal co-existence area according to the abnormal situation and the distribution network knowledge graph includes the following steps: Extract the three-dimensional features of the current abnormal point, and index the historical abnormal records associated with the device nodes with the same name according to the distribution network knowledge graph; activate the time dimension label in the graph to match the time domain features corresponding to the current abnormal point; Taking the abnormal point as the center, calculate the Euclidean distance of all devices in the set area, and build the spatial proximity distance according to the topological structure; traverse the connection relationship and logical relationship in the knowledge graph to identify the abnormal propagation path; Construct a symbiotic feature library based on device homology and spatial proximity characteristics; The Jaccard coefficients of the current anomaly combination and the historical pattern are calculated in turn, and the initial symbiotic region range of the corresponding pattern is activated according to the Jaccard coefficient; Determine the state estimation factor of the symbiotic area according to the abnormal situation and the health of the equipment, and adjust the boundary of the initial symbiotic area according to the state estimation factor to obtain the abnormal symbiotic area; The method of obtaining a load transfer path according to the abnormal transition factor of the abnormal symbiotic area and performing a transfer situation analysis on the load transfer path to determine a target transfer strategy comprises the following steps: The equipment health, historical transfer rate, and real-time load rate of the equipment in the abnormal symbiosis area are extracted from the distribution network knowledge graph and combined with the corresponding weight coefficient to determine the equipment abnormal transition factor; Taking the abnormal symbiotic area as the starting point, search for all device nodes that have contact with the area in the distribution network knowledge graph, and use the device nodes as candidate load transfer paths; A multi-dimensional transfer situation assessment index system is constructed by reliability index, economic index, timeliness index and risk index to calculate the comprehensive score of each candidate load transfer path, and the candidate load transfer path with the highest comprehensive score is taken as the target transfer path.

2. The new energy grid connection path optimization configuration method based on knowledge graph technology according to claim 1 is characterized in that: Obtaining power grid operation data and performing scene similarity analysis and attribute similarity analysis on it to determine an abnormal map; including the following steps: Obtain the abnormal records and corresponding repair records of the distribution network to determine the abnormal type, texture information and element information corresponding to each element in the time dimension; The abnormal scene of the distribution network is sliced ​​in the time domain based on the abnormal point to determine the abnormal portrait corresponding to each time domain slice; Determine the scene similarity of the abnormal image based on texture information and abnormal type; Determine the attribute similarity of the abnormal image based on the image element information and the abnormal type; The anomaly boundary and repair window of each time domain section are determined by scene similarity and attribute similarity, and an anomaly map is constructed based on the anomaly boundary and repair window.

3. The new energy grid connection path optimization configuration method based on knowledge graph technology according to claim 1 is characterized in that: The construction process of the distribution network knowledge graph includes: Acquire the topological structure data and grid operation data of the distribution network during normal operation to build a native database; extract the time domain information matching the abnormal points in the native database, extract the texture information and graphic element information of the time domain section information corresponding to the abnormal point diagram, and determine the abnormal data based on the topological structure and flow direction with the abnormal point as the center; expand the native database according to the abnormal data to obtain the target database; extract the texture information in the target database to determine the causal chain and the graphic element information to determine the rule chain; determine the distribution network knowledge graph corresponding to the abnormal point according to the causal chain and the rule chain.

4. The new energy grid connection path optimization configuration method based on knowledge graph technology according to claim 1 is characterized in that: Taking the abnormal symbiotic area as the starting point, searching all device nodes that have contact with the area in the distribution network knowledge graph, and taking the device nodes as candidate load transfer paths; including the following steps: The constraint conditions of the path search are set, and the constraint conditions at least include the capacity limit of the tie switch and the voltage deviation threshold constraint; the improved Dijkstra algorithm is used to take the inverse of the abnormal transition factor as the heuristic information of the path search, and the shortest path to each potential transfer path node is gradually searched from the starting point; during the search process, whether the path meets the constraint conditions is continuously checked, and if not, the path is discarded; for the searched paths, the sum of the abnormal transition factors of all devices on each path is calculated, and the first n paths with the smallest sum of abnormal transition factors are selected as candidate load transfer paths.

5. The new energy grid connection path optimization configuration method based on knowledge graph technology according to claim 1 is characterized in that: Obtain the historical power transfer records of the equipment on the path from the distribution network knowledge graph, calculate the ratio of successful power transfer times to the total power transfer times, and calculate the historical power transfer success rate to obtain the reliability index; Obtain the line resistance, transfer current and transfer time on the path from the distribution network knowledge graph to determine the transfer power loss and obtain the economic index; Obtain the switch action time of the equipment on the path, the operation time of the switch equipment, and calculate the total time required for the entire transfer process to obtain the timeliness index; The transfer risk value is calculated according to the sum of abnormal transition factors of equipment on the path, load fluctuation rate and their corresponding weights to obtain the risk index.

6. A new energy grid-connected path optimization configuration system, applicable to the new energy grid-connected path optimization configuration method based on knowledge graph technology as described in any one of claims 1 to 5, characterized in that: include: Determination module: obtains power grid operation data and performs scene similarity analysis and attribute similarity analysis to determine the abnormal map; Construction module: Expand the native database through the abnormal map and extract the texture information and graphic element information in the expanded target database to build the distribution network knowledge graph; Generation module: Determine the abnormal symbiosis area based on the abnormal situation and the distribution network knowledge graph, obtain the load transfer path based on the abnormal transition factor of the abnormal symbiosis area, analyze the transfer situation of the load transfer path and determine the target transfer strategy.

7. An electronic device, characterized in that: It includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of the new energy grid-connected path optimization configuration method based on knowledge graph technology as described in any one of claims 1 to 5 are implemented.

8. A storage medium, characterized in that: The storage medium stores computer executable instructions, which, when loaded and executed by the processor, implement the steps of the new energy grid-connected path optimization configuration method based on knowledge graph technology as described in any one of claims 1 to 5.

Images