Point-by-point marking method and system based on defect elimination state change

By establishing topology and state correlation models in the distribution network and optimizing node marking with genetic algorithms, the problem of insufficient fault propagation path identification in the existing technology is solved, and the fault elimination efficiency and grid stability are improved.

CN119030128APending Publication Date: 2024-11-26GUIZHOU POWER GRID CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202410907165.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The prior art is difficult to efficiently and accurately analyze the fault propagation path and its impact range of power distribution networks and identify key nodes, resulting in insufficient fault elimination efficiency and grid stability.

Method used

A point-by-point marking method based on the change of defect removal state is adopted. By collecting distribution network data, a topological model and state correlation model are established, the node marking scheme is optimized using genetic algorithms, fault propagation paths and impact ranges are identified, and key nodes are marked.

Benefits of technology

Improves fault elimination efficiency and grid stability, reduces the impact of faults on the system, and achieves more accurate fault location and rapid recovery.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119030128A_ABST
    Figure CN119030128A_ABST
Patent Text Reader

Abstract

The invention discloses a point-by-point marking method and system based on defect elimination state change, and relates to the field of correlation analysis, and the method comprises the steps: collecting the data of a power distribution network, building a topological model of a power grid, and analyzing the topological structure change of the power grid in different states; based on the topological model and the operation state data of the power grid, establishing a correlation model of states among nodes of the power grid, and analyzing a fault propagation path and an influence range; based on the state correlation model, identifying a fault propagation path, analyzing the node influence degree, and marking key nodes; and constructing a genetic algorithm optimization model, expressing a node marking scheme as chromosomes in the genetic algorithm, and defining a fitness function to evaluate the advantages and disadvantages of the chromosomes according to the analyzed node influence degree. By establishing the power grid topology model and the state correlation model, analyzing the fault propagation path and the node influence degree, and designing the genetic algorithm to optimize key node marks, the fault identification and processing accuracy is improved, and the operation stability and reliability of the power grid are enhanced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of association analysis, and in particular to a point-by-point marking method and system based on defect elimination state changes. Background Art

[0002] During the operation of the power system, various faults or abnormalities may occur in the power grid due to equipment failures, external interference, etc., which may lead to unstable operation of the power grid or even power outages. In order to quickly restore the normal operation of the power grid, it is necessary to promptly discover and locate the fault point, which requires an efficient marking method to mark each point in the system to help operation and maintenance personnel quickly locate the problem.

[0003] Traditional fault location methods rely more on changes in equipment status or the transmission of fault signals, while the point-by-point marking method based on the associated changes in fault elimination status pays more attention to the monitoring and analysis of changes in fault elimination status in the system, thereby being able to more accurately determine the location of the fault point.

[0004] During the operation of the power system, each point in the system is marked point by point according to the changes in the fault elimination status, so that the fault point can be identified and located in time, and the normal operation of the power grid can be quickly restored. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: how to efficiently and accurately analyze the fault propagation path and its impact range in the distribution network, identify key nodes, and improve the node marking scheme through optimization algorithm, so as to improve the fault elimination efficiency and overall stability of the distribution network.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a point-by-point marking method based on the change of fault elimination state, which includes the following steps: collecting data information of the distribution network, establishing a topological model of the power grid, and analyzing the changes in the topological structure of the power grid under different states.

[0008] Based on the topological model and operating status data of the power grid, a correlation model between the states of various nodes in the power grid is established to analyze the fault propagation path and impact range.

[0009] Based on the established state association model, the fault propagation path is identified, and the node impact degree is analyzed. Based on the analysis results, the key nodes are marked.

[0010] Based on the point-by-point marking method, a genetic algorithm optimization model is constructed. The node marking scheme determined by point-by-point marking is represented as a chromosome in the genetic algorithm. According to the analysis of the influence of each node, a fitness function is defined to evaluate the quality of each chromosome.

[0011] As a preferred solution of the point-by-point marking method based on fault elimination state changes described in the present invention, the data information includes topological structure data, operating status data and equipment parameter data of the distribution network; each node in the topological map is identified and the attributes of the node are defined.

[0012] The establishment of the topological model of the power grid includes drawing a topological graph of the positions and connection relationships of nodes and lines based on the collected node and line connection relationships using a topological graph drawing tool, converting the topological graph into a network model, using the network model in graph theory to represent the topological structure of the power grid, representing the nodes as vertices in the graph, and representing the connection relationships as edges in the graph.

[0013] Based on the collected topological structure data, a topological model of the power grid is established, and through equipment status simulation, the topological structure changes of the power grid under different states are analyzed.

[0014] As a preferred scheme of the point-by-point marking method based on fault elimination state changes described in the present invention, wherein: the analysis of the topological structure changes of the power grid under different states includes applying the real-time equipment status to the topological model according to the collected operating status data and equipment parameter data, simulating the equipment status of the power grid at different time points by simulating the closing and opening of switches and the connection and removal of transformers, updating the connection relationship between each node in the topological model according to the simulated equipment status changes, using a drawing tool to draw a topological diagram, and marking the status information of different devices to show the topological structure changes of the power grid under different states.

[0015] As a preferred solution of the point-by-point marking method based on the change of the fault elimination state described in the present invention, wherein: the establishment of the association model of the state between each node of the power grid based on the topological model and the operating status data of the power grid includes using sensor equipment to collect the state data of each node of the power grid, and associating the operating status data with the topological structure model, establishing the association model of the state between each node of the power grid, determining the operating status data of each node, matching and associating the collected data with the corresponding node according to the location of the sensor and the connection relationship of the node, and using the associated operating status data to establish the association model of the state between each node of the power grid, and representing the power grid containing N nodes as an undirected graph, the expression is:

[0016] G=(V,E)

[0017] Where V is the set of nodes and E is the set of edges.

[0018] The state association degree of each node is represented as the feature vector of the node, the connection relationship between the nodes is represented as the adjacency matrix A, and the state data of each node in the power grid is used as the feature to construct the feature matrix X, which is an N×D feature matrix, where N is the number of nodes, D is the dimension of the feature, and Y is an N×1 target variable vector, which represents the state association degree between the nodes.

[0019] Define a target variable Y to represent the degree of state association between nodes. Take the feature matrix X and the target variable Y as input, train a graph convolutional network model, and learn the relationship between the feature matrix X and the target variable Y. The expression is:

[0020] Z=f(A,X,θ)

[0021] Among them, Z is an N×F matrix, which is the representation of the node, F is the number of hidden units, θ is the parameter of the model, f is a nonlinear activation function, X is the feature matrix, and A is the adjacency matrix.

[0022] After training, a linear regression model is used to fit the relationship between the node representation Z and the target variable Y, expressed as:

[0023] Y=βZ+ε

[0024] Among them, β is the coefficient matrix of the model, ε is the error term, Y represents the degree of state association between nodes, and Z is the representation of the node.

[0025] As a preferred solution of the point-by-point marking method based on the change of the fault elimination state described in the present invention, wherein: based on the established state association model, the fault propagation path is identified and the node influence degree is analyzed. Based on the analysis result, marking the key nodes includes using the trained state association model, inputting the starting node of the fault and the fault type information, the model outputs the node sequence on the fault propagation path, indicating the path of the fault propagating from the starting node to other nodes, and propagating the fault signal to the surrounding nodes. For each node, according to the node sequence on the fault propagation path, the state association degree of each node is calculated, and the fault signal is propagated according to the connection relationship between the nodes. According to the calculation result of the node influence degree, the node with the greatest influence in the fault propagation process is determined, the node is marked as a key node, and the number of key nodes is counted. During the propagation process, the nodes and edges passed by the fault signal are recorded, the propagation path of the fault signal in the power grid is tracked, and the time when the fault signal arrives at each node and the degree of influence on each node are calculated. According to the propagation path and propagation time, the propagation speed and influence range of the fault signal are analyzed.

[0026] As a preferred solution of the point-by-point marking method based on defect elimination state changes described in the present invention, wherein: the construction of the genetic algorithm optimization model includes using binary coding to represent the node marking scheme as the chromosome code, each chromosome represents a node marking scheme, wherein each gene bit represents the marking state of a node, 0 represents unmarked, 1 represents marked, and a group of initial chromosomes are randomly generated to constitute the initial population of the genetic algorithm. According to the degree of influence of the node, a fitness function is designed to evaluate the fitness of each chromosome. By calculating the length of the fault propagation path, the scope of influence and the number of key nodes, and combining the results, the advantages and disadvantages of each chromosome are comprehensively evaluated.

[0027] According to the fitness of the chromosome, selection, crossover, mutation, and population update operations are repeated until the stopping condition is met. After the iterative optimization of the genetic algorithm is completed, multiple optimized node marking schemes are obtained, and the optimized node marking schemes are applied to the associated changes of the actual distribution network fault elimination state.

[0028] As a preferred solution of the point-by-point marking method based on the change of the defect elimination state described in the present invention, the comprehensive evaluation of the quality of each chromosome includes starting from the fault node, following the path in the state association model, calculating the path length to each affected node, adding up all the path lengths, and obtaining the total fault propagation path length, which is expressed as:

[0029]

[0030] Among them, L 路径 is the total fault propagation path length, L i is the path length from the faulty node to the i-th affected node, and M is the number of affected nodes.

[0031] Count the number and location of all affected nodes, and use the Euclidean distance formula to calculate the distance between the affected nodes and the faulty nodes. The expression is:

[0032]

[0033] Among them, (x1, y1) and (x2, y2) are the coordinates of the affected node and the faulty node respectively, and S is the distance between the affected node and the faulty node.

[0034] The fault propagation path length, impact range, and number of key nodes are combined, and the weighted summation method is used to comprehensively evaluate the quality of each chromosome. The expression is:

[0035] Q=ω1×L 路径 +ω2×S+ω3×P

[0036] Among them, Q represents fitness, L 路径 is the total fault propagation path length, S is the distance between the affected node and the faulty node, P is the number of critical nodes, and (ω1, ω2, ω3) represent the weights corresponding to the fault propagation path length, impact range, and number of critical nodes, respectively.

[0037] Another object of the present invention is to provide a point-by-point marking system based on fault elimination status changes, which can automatically mark and update the status changes of fault nodes by real-time monitoring of the power grid operation status, thereby solving the problem of untimely and inaccurate marking of fault nodes in existing systems.

[0038] To solve the above technical problems, the present invention provides the following technical solutions: a point-by-point marking system based on fault elimination state changes, comprising: a data acquisition and management module, a power grid topology model building module, a state association model building module, a fault propagation analysis module and a genetic algorithm optimization module.

[0039] The data acquisition and management module collects and manages the topological structure data, operation status data and equipment parameter data of the distribution network.

[0040] The power grid topology model building module builds a topological structure model of the power grid based on the collected data, and analyzes the topological changes under different states through device state simulation, draws a topological diagram, defines node attributes, converts into a network model, and verifies and corrects the topological model.

[0041] The state association model building module builds an association model of states between nodes in the power grid based on the topological model and operation state data of the power grid, and analyzes the fault propagation path and impact range.

[0042] The fault propagation analysis module identifies the fault propagation path based on the established state association model, analyzes the node impact degree, and marks the key nodes.

[0043] The genetic algorithm optimization module is used to design a genetic algorithm optimization model, optimize the node marking scheme, and optimize the fault elimination efficiency and the stability of the power grid.

[0044] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the point-by-point marking method based on the change of the defect elimination state are implemented as described above.

[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a point-by-point marking method based on defect elimination state changes as described above.

[0046] The beneficial effects of the present invention include collecting topological structure data, operating status data and equipment parameter data of the distribution network, establishing a topological model of the power grid based on the collected topological structure data, analyzing the topological structure changes of the power grid under different states through equipment state simulation, establishing a correlation model of the states between the nodes of the power grid based on the topological model and operating status data of the power grid, identifying the fault propagation path, and analyzing the node influence degree, marking key nodes based on the analysis results, designing a genetic algorithm optimization model, representing the node marking scheme as a chromosome in the genetic algorithm, defining a fitness function according to the analyzed node influence degree, and evaluating the quality of each chromosome, and by establishing a state association model and genetic algorithm optimization, being able to more accurately identify key nodes, optimize and mark them, identify the power grid fault propagation path and influence range, and the optimized node marking scheme can be directly applied to the actual distribution network, which helps to improve the operating stability and reliability of the power grid and reduce the impact of faults on the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0048] Figure 1 An overall flow chart of a point-by-point marking method based on defect elimination state changes provided for the first embodiment of the present invention.

[0049] Figure 2 A structural diagram of a point-by-point marking system based on defect elimination state changes provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0051] Example 1

[0052] Reference Figure 1As an embodiment of the present invention, a point-by-point marking method based on fault elimination state changes is provided, including: step 101, collecting topological structure data, operating status data and equipment parameter data of the distribution network, establishing a topological model of the power grid based on the collected topological structure data, and analyzing the topological structure changes of the power grid under different states through equipment state simulation.

[0053] Step 102: Based on the topological model and operation status data of the power grid, a correlation model of the status between various nodes of the power grid is established to analyze the fault propagation path and impact range.

[0054] Step 103: Based on the established state association model, identify the fault propagation path, analyze the node impact degree, and mark the key nodes based on the analysis results.

[0055] Step 104, design a genetic algorithm optimization model, represent the node marking scheme as a chromosome in the genetic algorithm, define a fitness function according to the node influence degree analyzed in step 103, and evaluate the quality of each chromosome.

[0056] Preferably, in step 101, the topological structure data, operating status data and equipment parameter data of the distribution network are collected, and a topological model of the power grid is established based on the collected topological structure data. The topological structure changes of the power grid under different states are analyzed through equipment state simulation. The topological structure data of the distribution network includes connection relationship data of nodes, lines, substations and switch devices of the power grid; the operating status data includes operating status, current, voltage and power parameters of power grid equipment; the equipment parameter data includes line parameters, switch status and transformer parameters. The specific steps are as follows:

[0057] A1. Draw a topology map: Based on the collected node and line connection relationships, use the topology map drawing tool to draw a topology map of the location and connection relationship of the nodes and lines.

[0058] A2. Node identification and attribute definition: Identify each node in the topology map and define the node's attributes, which include node type, region, and rated capacity information.

[0059] A3. Network modeling: Convert the topological graph into a topological network model. Use the network model in graph theory to represent the topological structure of the power grid. Represent the nodes as vertices in the graph and the connection relationships as edges in the graph.

[0060] A4. Verification and correction: Verify and correct the established topology model, compare it with the actual power grid data, check the accuracy and completeness of the model, and make corrections and adjustments.

[0061] Preferably, the device state simulation is used to analyze the topological structure changes of the power grid under different states, and the specific steps are as follows:

[0062] Step B1, device status simulation: Based on the collected operating status data and device parameter data, the real-time device status is applied to the topology model. By simulating the closing and opening of switches and the connection and removal of transformers, the device status of the power grid at different time points is simulated. According to the simulated device status changes, the connection relationship between each node in the topology model is updated to reflect the topological structure changes of the power grid at different time points.

[0063] Step B2, display topology changes: count the number of closed and open switches, the number of connected and disconnected transformers, and the connection status of nodes and lines, use drawing tools to draw a topology diagram, and mark the status information of different devices to display the topology changes of the power grid in different states.

[0064] Preferably, in step 102, based on the topological structure and operation status data of the power grid, an association model of the status between various nodes of the power grid is established to analyze the fault propagation path and impact range. The specific steps are as follows:

[0065] Step C1, establishing a correlation model: using sensor equipment to collect status data of each node of the power grid, and associating the operating status data with the topological structure model to establish a correlation model of the status between each node of the power grid.

[0066] Step C2, fault propagation simulation: simulate the fault propagation path and impact range of various fault conditions in the power grid in the established correlation model, track the propagation path of the fault signal in the power grid according to the real-time operation status data, and analyze the propagation speed and range of the fault.

[0067] Preferably, in the step C1 of establishing the association model, the state data of each node of the power grid is collected by using sensor equipment, and the operation state data is associated with the topology structure model to establish the association model of the state between each node of the power grid, further comprising the following steps:

[0068] Step C101, data association: associate the operating status data collected by the sensor with the topological structure model of the power grid, determine the operating status data of each node, and match and associate the collected data with the corresponding node according to the location of the sensor and the connection relationship of the node.

[0069] Step C102: using the associated operating status data, establish a correlation model between the states of the various nodes in the power grid, adopt a machine learning method to analyze the state correlation degree and influencing factors between the nodes, and represent the power grid containing N nodes as an undirected graph G = (V, E), where V is a set of nodes, E is a set of edges, the state correlation degree of each node is represented as a feature vector of the node, and the connection relationship between the nodes is represented as an adjacency matrix A.

[0070] Step C103, constructing a feature matrix: and taking the state data of each node in the power grid as features, constructing a feature matrix X which is an N×D feature matrix, where N is the number of nodes, D is the dimension of the feature, and Y is an N×1 target variable vector, which represents the degree of state correlation between nodes.

[0071] Step C104, model training: define a target variable Y, representing the degree of state association between nodes, take the feature matrix X and the target variable Y as input, train a graph convolutional network model, so that it can learn the relationship between the feature matrix X and the target variable Y, expressed as: Z = f(A, X, θ), where Z is an N×F matrix, is the representation of the node, F is the number of hidden units, θ is the parameter of the model, f is a nonlinear activation function, X is the feature matrix, and A is the adjacency matrix.

[0072] Step C105, function relationship mapping: After training is completed, a linear regression model is used to fit the relationship between the node representation Z and the target variable Y, which is expressed as: Y = βZ + ε, where β is the coefficient matrix of the model, ε is the error term, Y represents the degree of state association between nodes, and Z is the node representation.

[0073] Preferably, in step 103, based on the established state association model, the fault propagation path is identified, and the node impact degree is analyzed, and based on the analysis result, the key nodes are marked, which specifically includes the following steps:

[0074] Step D1, initialize the fault signal: use the trained state association model, input the starting node of the fault and the fault type information, the model outputs the node sequence on the fault propagation path, indicating the path of the fault propagating from the starting node to other nodes, and propagates the fault signal to the surrounding nodes.

[0075] Step D2, propagation process simulation: For each node, the state correlation degree of each node is calculated according to the node sequence on the fault propagation path, and the fault signal is propagated according to the connection relationship between the nodes. The node state correlation degree predicted by the model is used as the propagation probability to simulate the propagation process of the fault signal.

[0076] Step D3, marking key nodes: according to the calculation results of the node influence degree, determine the nodes with the greatest influence in the fault propagation process, mark these nodes as key nodes, and count the number of key nodes. The key nodes represent the nodes that need special attention and processing in the fault propagation process.

[0077] Step D4, tracking the propagation path: During the propagation process, record the nodes and edges that the fault signal passes through, track the propagation path of the fault signal in the power grid, and calculate the time when the fault signal reaches each node, as well as the degree of impact on each node. According to the propagation path and propagation time, analyze the propagation speed and impact range of the fault signal.

[0078] Preferably, in step 104, a genetic algorithm optimization model is designed, the node marking scheme is represented as a chromosome in the genetic algorithm, a fitness function is defined according to the node influence degree analyzed in step 103, the quality of each chromosome is evaluated, and the node marking scheme is improved to make it more in line with the actual situation of the power grid fault state, thereby improving the fault elimination efficiency and the stability of the power grid. The specific steps are as follows:

[0079] Step E1, determine the chromosome encoding method: use binary encoding to represent the node marking scheme as the chromosome encoding, each chromosome represents a node marking scheme, where each gene bit represents the marking state of a node, 0 represents unmarked, and 1 represents marked.

[0080] Step E2, initializing the population: randomly generating a set of initial chromosomes to constitute the initial population of the genetic algorithm.

[0081] Step E3, fitness function: According to the node influence degree analyzed in step 103, a fitness function is designed to evaluate the fitness of each chromosome. By calculating the length of the fault propagation path, the impact range and the number of key nodes, and combining the results, the advantages and disadvantages of each chromosome are comprehensively evaluated.

[0082] Step E4: Repeat the selection, crossover, mutation, and population update operations according to the fitness of the chromosome until the stopping condition is met.

[0083] Step E5, applying optimization results: after the iterative optimization of the genetic algorithm is completed, a plurality of optimized node marking schemes are obtained, and these optimized node marking schemes are applied to the associated changes of the actual distribution network fault elimination state.

[0084] Preferably, in the fitness function of step E3, a fitness function is designed to evaluate the fitness of each chromosome, and the advantages and disadvantages of each chromosome are comprehensively evaluated by calculating the length of the fault propagation path, the impact range and the number of key nodes, and combining the results, further comprising the following steps:

[0085] E301. Calculate the fault propagation path length: Starting from the fault node, along the path in the state association model, calculate the path length to each affected node, add up all path lengths to get the total fault propagation path length. The specific calculation formula is as follows:

[0086]

[0087] Among them, L 路径 is the total fault propagation path length, L i is the path length from the faulty node to the i-th affected node, and M is the number of affected nodes.

[0088] E302. Calculate the impact range: count the number and location of all affected nodes, and calculate the distance between the affected nodes and the faulty nodes. The affected nodes refer to nodes that cannot work normally after the faulty nodes occur.

[0089] Define a list to store the positions of affected nodes. Starting from the faulty node, traverse all nodes and determine whether each node can be connected to the faulty node through the node connectivity relationship. When a node is connected to the faulty node, add the node position to the list of affected nodes and continue to traverse other nodes until all nodes have been traversed. The number of affected nodes is the number of elements in the list.

[0090] Traverse the list of affected nodes, for each affected node, use the Euclidean distance formula to calculate the distance between the node and the faulty node, and save the distance between each affected node and the faulty node. The formula is: S = (x2-x1) 2 +(y2-y1) 2 , where (x1, y1) and (x2, y2) are the coordinates of the affected node and the faulty node, respectively, and S is the distance between the affected node and the faulty node.

[0091] E303, Comprehensive evaluation: Combine the fault propagation path length, impact range and number of key nodes, and use weighted summation to comprehensively evaluate the pros and cons of each chromosome. Set different weights according to specific circumstances to balance the importance of each indicator. The specific calculation formula is as follows:

[0092] Q=ω1×L 路径 +ω2×S+ω3×P

[0093] Among them, Q represents fitness, L 路径is the total fault propagation path length, S is the distance between the affected node and the faulty node, P is the number of critical nodes, and (ω1, ω2, ω3) represents the weights corresponding to the fault propagation path length, impact range, and number of critical nodes, respectively, which are used to balance the importance of each indicator.

[0094] Preferably, in step E4, the selection, crossover, mutation, and population update operations are repeated according to the fitness of the chromosome until the stop condition is met, further comprising the following steps:

[0095] Step E401, selection operation: according to the fitness of the chromosome, use the selection operator to select excellent individuals from the population as parents for breeding the next generation.

[0096] Step E402, crossover operation: perform a crossover operation on the selected parent chromosome to generate a new daughter chromosome.

[0097] Step E403, mutation operation: performing a mutation operation on the offspring chromosomes to introduce randomness to increase the diversity of the population. The mutation operation can randomly change the marking status of some nodes in the chromosomes.

[0098] Step E404, update the population: merge the parent and offspring chromosomes to form a new population, and adopt an elite retention strategy to retain the chromosome with the highest fitness as the next generation population.

[0099] Example 2

[0100] Reference Figure 2 , which is an embodiment of the present invention, provides a system for a point-by-point marking method based on fault elimination state changes, including: a data acquisition and management module, a power grid topology model building module, a state association model building module, a fault propagation analysis module and a genetic algorithm optimization module.

[0101] The data acquisition and management module collects and manages the topological structure data, operating status data and equipment parameter data of the distribution network.

[0102] The power grid topology model building module builds a topological structure model of the power grid based on the collected data, and analyzes the topological changes under different states through equipment status simulation, draws topological diagrams, defines node attributes, converts them into network models, and verifies and corrects topological models.

[0103] The state association model building module is based on the topological model and operating status data of the power grid, establishes the association model of the states between each node of the power grid, and analyzes the fault propagation path and impact range.

[0104] The fault propagation analysis module is based on the established state association model to identify the fault propagation path, analyze the node impact degree, and mark the key nodes.

[0105] The genetic algorithm optimization module is to design the genetic algorithm optimization model, optimize the node marking scheme, and optimize the fault elimination efficiency and the stability of the power grid.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0108] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0109] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] Example 3

[0111] In this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional static topology analysis method and the method of this embodiment respectively.

[0112] In order to verify the feasibility of the method of the present invention, the genetic algorithm optimization model is combined with actual data to automatically identify the fault propagation path and analyze the node influence degree. Finally, the key nodes can be marked. The data in Table 3 are used to mark the fault propagation path and analyze the node influence degree.

[0113] Table 3 Node influence degree table

[0114]

[0115]

[0116] The distribution network data is collected as shown in Table 4, and the parameters of the genetic algorithm are set as shown in Table 5. The distribution network model and fault sample data are used to calculate the fitness of each individual, which includes the length of the fault propagation path and the sum of the node influence. The population is sorted and individuals are selected according to the fitness for crossover and mutation operations. The genetic algorithm optimization model constructed by this method can be used to calculate the point-by-point marking scheme based on the change of the fault elimination state.

[0117] Table 4 Distribution network data table

[0118]

[0119] Table 5 Parameters of genetic algorithm

[0120]

[0121]

[0122] By comparing Table 6, it can be seen that the point-by-point marking method based on the change of the defect elimination state more comprehensively considers the change of the real-time operation state than the traditional static topology analysis method, and can evaluate the influence of the node, so as to mark the key nodes more accurately.

[0123] Table 6 Scheme comparison table

[0124]

[0125] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0126] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A point-by-point marking method based on the change of defect elimination state, characterized in that: include: Collect data information of the distribution network, establish the topological model of the power grid, and analyze the topological structure changes of the power grid under different states; Based on the topological model and operating status data of the power grid, a correlation model between the states of various nodes in the power grid is established to analyze the fault propagation path and impact range; Based on the established state association model, the fault propagation path is identified, and the node impact degree is analyzed. Based on the analysis results, the key nodes are marked; Based on the point-by-point marking method, a genetic algorithm optimization model is constructed. The node marking scheme determined by point-by-point marking is represented as a chromosome in the genetic algorithm. According to the analysis of the influence of each node, a fitness function is defined to evaluate the quality of each chromosome.

2. A point-by-point marking method based on defect elimination state change as claimed in claim 1, characterized in that: The data information includes topological structure data, operation status data and equipment parameter data of the distribution network; each node in the topological map is identified and the attributes of the node are defined. The establishment of the topological model of the power grid includes drawing a topological graph of the positions and connection relationships of the nodes and lines using a topological graph drawing tool according to the collected connection relationships of the nodes and lines, converting the topological graph into a network model, using a network model in graph theory to represent the topological structure of the power grid, representing the nodes as vertices in the graph, and representing the connection relationships as edges in the graph; Based on the collected topological structure data, a topological model of the power grid is established, and through equipment status simulation, the topological structure changes of the power grid under different states are analyzed.

3. A point-by-point marking method based on defect elimination state change as claimed in claim 2, characterized in that: The analysis of the topological structure changes of the power grid under different states includes applying the real-time device status to the topological model based on the collected operating status data and device parameter data, simulating the device status of the power grid at different time points by simulating the closing and opening of switches and the connection and disconnection of transformers, updating the connection relationship between each node in the topological model according to the simulated device status changes, using a drawing tool to draw a topological diagram, and marking the status information of different devices to show the topological structure changes of the power grid under different states.

4. A point-by-point marking method based on defect elimination state change as claimed in claim 3, characterized in that: The method of establishing the association model of the states between the nodes of the power grid based on the topological model and the operation status data of the power grid includes collecting the state data of the nodes of the power grid by using sensor equipment, associating the operation status data with the topological structure model, establishing the association model of the states between the nodes of the power grid, determining the operation status data of each node, matching and associating the collected data with the corresponding node according to the location of the sensor and the connection relationship of the node, establishing the association model of the states between the nodes of the power grid by using the associated operation status data, and representing the power grid containing N nodes as an undirected graph, and the expression is: G=(V,E) Where V is the set of nodes and E is the set of edges; The state correlation degree of each node is represented as the node's feature vector, the connection relationship between nodes is represented as the adjacency matrix A, and the state data of each node in the power grid is used as features to construct a feature matrix X, which is an N×D feature matrix, where N is the number of nodes, D is the dimension of the feature, and Y is an N×1 target variable vector, which represents the state correlation degree between nodes; Define a target variable Y to represent the degree of state association between nodes. Take the feature matrix X and the target variable Y as input, train a graph convolutional network model, and learn the relationship between the feature matrix X and the target variable Y. The expression is: Z=f(A,X,θ) Among them, Z is an N×F matrix, which is the representation of the node, F is the number of hidden units, θ is the parameter of the model, f is a nonlinear activation function, X is the feature matrix, and A is the adjacency matrix; After training, a linear regression model is used to fit the relationship between the node representation Z and the target variable Y, expressed as: Y=βZ+ε Among them, β is the coefficient matrix of the model, ε is the error term, Y represents the degree of state association between nodes, and Z is the representation of the node.

5. A point-by-point marking method based on defect elimination state change as claimed in claim 4, characterized in that: Based on the established state association model, the fault propagation path is identified and the node influence degree is analyzed. Based on the analysis result, the key nodes are marked, including using the trained state association model, inputting the starting node of the fault and the fault type information, and the model outputs the node sequence on the fault propagation path, which represents the path of the fault propagating from the starting node to other nodes, and propagating the fault signal to the surrounding nodes. For each node, according to the node sequence on the fault propagation path, the state association degree of each node is calculated, and the fault signal is propagated according to the connection relationship between the nodes. According to the calculation result of the node influence degree, the node with the greatest influence in the fault propagation process is determined, the node is marked as the key node, and the number of key nodes is counted. During the propagation process, the nodes and edges passed by the fault signal are recorded, the propagation path of the fault signal in the power grid is tracked, and the time when the fault signal arrives at each node and the degree of influence on each node are calculated. According to the propagation path and propagation time, the propagation speed and influence range of the fault signal are analyzed.

6. A point-by-point marking method based on defect elimination state change as claimed in claim 5, characterized in that: The construction of the genetic algorithm optimization model includes using binary coding to represent the node marking scheme as the coding of chromosomes, each chromosome represents a node marking scheme, wherein each gene bit represents the marking state of a node, 0 represents unmarked, and 1 represents marked, a group of initial chromosomes are randomly generated to form the initial population of the genetic algorithm, and a fitness function is designed to evaluate the fitness of each chromosome according to the influence degree of the node, and the length of the fault propagation path, the influence range and the number of key nodes are calculated, and the results are combined to comprehensively evaluate the advantages and disadvantages of each chromosome; According to the fitness of the chromosome, selection, crossover, mutation, and population update operations are repeated until the stopping condition is met. After the iterative optimization of the genetic algorithm is completed, multiple optimized node marking schemes are obtained, and the optimized node marking schemes are applied to the associated changes of the actual distribution network fault elimination state.

7. A point-by-point marking method based on defect elimination state change as claimed in claim 6, characterized in that: The comprehensive evaluation of the quality of each chromosome includes starting from the fault node, following the path in the state association model, calculating the path length to each affected node, adding up all path lengths, and obtaining the total fault propagation path length, which is expressed as: Among them, L 路径 is the total fault propagation path length, L i is the path length from the faulty node to the i-th affected node, and M is the number of affected nodes; Count the number and location of all affected nodes, and use the Euclidean distance formula to calculate the distance between the affected nodes and the faulty nodes. The expression is: Where (x1, y1) and (x2, y2) are the coordinates of the affected node and the faulty node, respectively, and S is the distance between the affected node and the faulty node; The fault propagation path length, impact range, and number of key nodes are combined, and the weighted summation method is used to comprehensively evaluate the quality of each chromosome. The expression is: Q=ω1×L 路径 +ω2×S+ω3×P Among them, Q represents fitness, L 路径 is the total fault propagation path length, S is the distance between the affected node and the faulty node, P is the number of critical nodes, and (ω1, ω2, ω3) represent the weights corresponding to the fault propagation path length, impact range, and number of critical nodes, respectively.

8. A system using a point-by-point marking method based on the change of the defect elimination state as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition and management module, power grid topology model building module, state association model building module, fault propagation analysis module and genetic algorithm optimization module; The data acquisition and management module collects and manages the topological structure data, operation status data and equipment parameter data of the distribution network; The power grid topology model building module builds a topology model of the power grid based on the collected data, and analyzes the topology changes under different states through device state simulation, draws a topology diagram, defines node attributes, converts into a network model, and verifies and corrects the topology model; The state association model building module is based on the topological model and operation state data of the power grid, establishes the association model between the states of each node of the power grid, and analyzes the fault propagation path and impact range; The fault propagation analysis module identifies the fault propagation path, analyzes the node impact degree, and marks the key nodes based on the established state association model; The genetic algorithm optimization module is used to design a genetic algorithm optimization model, optimize the node marking scheme, and optimize the fault elimination efficiency and the stability of the power grid.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a point-by-point marking method based on defect elimination state change described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a point-by-point marking method based on defect elimination state change described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Power grid operation weak point identification method and system based on transmission and distribution network topological structure

    CN119646718A

  • Method and system for identifying weak points in power grid operation based on transmission and distribution network topology

    CN119646718B

  • Low-voltage cabinet distributed control method and system based on multi-source data fusion

    CN120934182A