Power distribution network self-healing method, system and equipment based on fault evolution path and medium

Abstract

The invention discloses a power distribution network self-healing method, system and device based on a fault evolution path, and a medium, and the method comprises the steps: obtaining the operation data of a target power distribution network in real time, collecting an abnormal signal set when a fault occurs, and carrying out the analysis through combining with the topological structure of the power distribution network when at least one signal value exceeds a threshold value range, an initial node of a fault propagation path can be accurately determined, and a foundation is laid for accurate division of an initial fault isolation area in subsequent steps; when it is detected that the fault range exceeds the initial fault isolation area, the topological structure is updated based on real-time load data of the target power distribution network, evolution prediction is carried out on a fault propagation path, and therefore a second control node set is determined and used for further optimization of the fault isolation area of the power distribution network, and self-healing operation is executed; compared with an existing self-healing strategy, the isolation area can be adjusted and optimized in time based on the fault evolution condition, and the influence of fault evolution can be controlled in time and accurately.

Description

Technical Field

[0001] The present invention application relates to the field of distribution network self-healing, and particularly to a distribution network self-healing method, system, device and medium based on a fault evolution path. Background Art

[0002] The distribution network is an important part of the power system, which undertakes the core tasks of power distribution and user power supply. The stable and reliable operation of the distribution network is directly related to the social and economic operation and residents' lives. Especially when facing sudden faults, the self-healing ability of the distribution network becomes the key to ensuring power supply continuity.

[0003] However, current distribution network self-healing strategies mostly rely on passive response and post-fault repair. In this context, there is a lack of effective and timely active intervention in the initial stage of fault occurrence, which makes it difficult to limit the scope of the fault. And with the further evolution of the fault, due to the lack of means such as analysis, guidance, and adjustment of the fault path, the accuracy of isolating the fault area by the power system is relatively low, which leads to further loss of resources and extension of the recovery time and other problems. Summary of the Invention

[0004] The present invention application provides a distribution network self-healing method, system, device and medium based on a fault evolution path to solve the technical problem of how to improve the accuracy of isolating the fault area.

[0005] To solve the above technical problem, the present invention application provides a distribution network self-healing method based on a fault evolution path, including: Real-time acquiring operation data of a target distribution network, and collecting a set of abnormal signals when a fault occurs from the operation data; the set of abnormal signals includes several signal values; When at least one of the signal values exceeds a preset threshold range, acquiring the current topological structure of the target distribution network; and determining the starting node of the fault propagation path by analyzing the topological structure and the set of abnormal signals; According to the position of the starting node, acquiring the switch states of adjacent nodes; and then obtaining a first control node set based on the switch states of adjacent nodes; Dividing an initial fault isolation area based on the first control node set; When it is detected that the fault range exceeds the initial fault isolation area, updating the topological structure based on the real-time load data of the target distribution network; and performing an evolutionary prediction on the fault propagation path based on the updated topological structure to obtain a second control node set; dividing an optimized fault isolation area through the second control node set, and controlling the target distribution network to perform a self-healing operation based on the optimized isolated fault area.

[0006] As a preferred solution, the topology is updated based on the real-time load data of the target distribution network; and the fault propagation path is evolutionarily predicted based on the updated topology to obtain a second set of control nodes, including: Obtain the node loads of the key nodes in the potential fault expansion area from the real-time load data; Mark the key nodes with node loads greater than the preset load threshold as risk nodes, and update the topology according to the risk nodes; Obtain historical fault data; predict the fault propagation path based on the updated topology and the risk nodes through a preset path evolution prediction model; predict the fault propagation probability based on the updated topology and the risk nodes through the dynamic Bayesian network algorithm; Analyze to obtain a second set of control nodes based on the predicted propagation path and fault propagation probability.

[0007] As a preferred solution, through the second set of control nodes, an optimized fault isolation area is divided, and the target distribution network is controlled to perform self-healing operations based on the optimized isolated fault area, including: Analyze the historical operation records and response delays at each second control node in the second set of control nodes, where the historical operation records include the monthly operation times; Perform comprehensive analysis according to the monthly operation times, response delays, preset time window limits, and monthly operation upper limits to obtain the operation priorities of each second control node respectively; Divide an optimized fault isolation area through the second set of control nodes; and based on the operation priorities, combined with the load distribution status of the optimized fault isolation area, control the target distribution network to perform self-healing operations based on the optimized isolated fault area.

[0008] As a preferred solution, according to the operation priorities, combined with the load distribution status of the optimized fault isolation area, controlling the target distribution network to perform self-healing operations based on the optimized isolated fault area includes: Obtain the resource consumption and load transfer conditions of the switch operations corresponding to each second control node; Generate a switch operation plan with the goal of minimizing resource consumption according to the resource consumption and load transfer conditions combined with the operation priorities, and then obtain a switch operation sequence; Based on the switch operation sequence, combined with the preset parallel task processing sequence and the load distribution status of the optimized fault isolation area, control the target distribution network to perform self-healing operations based on the optimized isolated fault area.

[0009] As a preferred solution, dividing the initial fault isolation area based on the first control node set includes: Construct the load constraints of the target distribution network and the operation constraints of the first control node set, where the operation constraints include resource consumption constraints and operation frequency constraints; Based on the load constraints, resource consumption constraints, and operation frequency constraints, obtain a preliminary switch action sequence based on the first control point set; Divide the initial fault isolation area according to the preliminary switch action sequence.

[0010] As a preferred solution, obtaining the first control node set based on the switch states of neighboring nodes includes: Based on the switch states of the neighboring nodes, analyze the connection states of all nodes in the target distribution network through a graph traversal algorithm to obtain a node connection path set and a state anomaly pattern associated with the neighboring nodes; Perform clustering analysis according to the node connection path set and the state anomaly pattern to obtain a topological anomaly subset; Divide and obtain the first control node set according to the topological anomaly subset.

[0011] As a preferred solution, determining the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set includes: Use a depth-first search algorithm to traverse the topological structure and obtain the traversal result; Filter out the traversal paths in the traversal result whose signal values exceed the preset threshold range; Calculate the short-circuit risk of each node in the traversal path through the Dijkstra algorithm, and use the starting point of the path with a short-circuit risk greater than the preset risk value as the starting node of the fault propagation path.

[0012] Correspondingly, the present invention application also provides a distribution network self-healing system based on the fault evolution path, including a collection module, a node determination module, a control point determination module, a region division module, and a self-healing control module; wherein, The collection module is used to obtain the operation data of the target distribution network in real time and collect the abnormal signal set during the occurrence of a fault from the operation data; the abnormal signal set contains several signal values; The node determination module is used to obtain the current topological structure of the target distribution network when at least one of the signal values exceeds the preset threshold range; and determine the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set; The control point determination module is used to obtain the switch states of neighboring nodes according to the position of the starting node; and then obtain the first control node set based on the switch states of the neighboring nodes; The area division module is configured to divide an initial fault isolation area based on the first control node set; The self-healing control module is configured to, when detecting that the fault range exceeds the initial fault isolation area, update the topology based on the real-time load data of the target distribution network; and evolve and predict the fault propagation path based on the updated topology to obtain a second control node set; divide an optimized fault isolation area through the second control node set, and control the target distribution network to perform self-healing operations based on the optimized isolation fault area.

[0013] As a preferred solution, the self-healing control module updates the topology based on the real-time load data of the target distribution network; and evolves and predicts the fault propagation path based on the updated topology to obtain a second control node set, including: The self-healing control module obtains the node load of the key nodes in the potential fault expansion area from the real-time load data; Mark the key nodes with the node load greater than the preset load threshold as risk nodes, and update the topology according to the risk nodes; Obtain historical fault data; predict the fault propagation path based on the updated topology and the risk nodes through a preset path evolution prediction model; predict the fault propagation probability based on the updated topology and the risk nodes through a dynamic Bayesian network algorithm; Analyze to obtain a second control node set based on the predicted propagation path and fault propagation probability.

[0014] As a preferred solution, the self-healing control module divides an optimized fault isolation area through the second control node set, and controls the target distribution network to perform self-healing operations based on the optimized isolation fault area, including: The self-healing control module analyzes the historical operation records and response delays at each second control node in the second control node set, and the historical operation records include the monthly operation times; Comprehensively analyze according to the monthly operation times, response delays, preset time window limit and monthly operation upper limit to obtain the operation priorities of each second control node respectively; Divide an optimized fault isolation area through the second control node set; and control the target distribution network to perform self-healing operations based on the optimized isolation fault area according to the operation priorities in combination with the load distribution status of the optimized fault isolation area.

[0015] As a preferred solution, the self-healing control module controls the target distribution network to perform self-healing operations based on the optimized isolated fault area according to the operation priority, including: The self-healing control module obtains the resource consumption and load transfer conditions of the switch operations corresponding to each second control node; According to the resource consumption and load transfer conditions and in combination with the operation priority, a switch operation plan aiming to minimize resource consumption is generated, and then a switch operation sequence is obtained; Based on the switch operation sequence, in combination with a preset parallel task processing sequence and the load distribution state of the optimized fault isolation area, the target distribution network is controlled to perform self-healing operations based on the optimized isolated fault area.

[0016] As a preferred solution, the area division module divides the initial fault isolation area based on the first control node set, including: The area division module constructs the load constraint of the target distribution network and the operation constraints of the first control node set, and the operation constraints include resource consumption constraints and operation frequency constraints; According to the load constraint, resource consumption constraint and operation frequency constraint, a preliminary switch action sequence is obtained based on the first control point set; According to the preliminary switch action sequence, the initial fault isolation area is divided.

[0017] As a preferred solution, the control point determination module obtains the first control node set based on the switch states of adjacent nodes, including: The control point determination module analyzes the connection states of all nodes of the target distribution network through a graph traversal algorithm based on the switch states of the adjacent nodes, and obtains a node connection path set and a state anomaly pattern associated with the adjacent nodes; Cluster analysis is performed according to the node connection path set and the state anomaly pattern to obtain a topological anomaly subset; According to the topological anomaly subset, the first control node set is divided.

[0018] As a preferred solution, the node determination module determines the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set, including: The node determination module traverses the topological structure using a depth-first search algorithm to obtain a traversal result; Filter out the traversal paths whose signal values exceed the preset threshold range from the traversal result; Calculate the short - circuit risk of each node in the traversal path through the Dijkstra algorithm, and use the starting point of the path with a short - circuit risk greater than the preset risk value as the starting node of the fault propagation path.

[0019] Correspondingly, the present invention application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the self - healing method of the distribution network based on the fault evolution path is implemented.

[0020] Correspondingly, the present invention application also provides a computer - readable storage medium. The computer - readable storage medium includes a stored computer program. Wherein, when the computer program runs, it controls the device where the computer - readable storage medium is located to execute the self - healing method of the distribution network based on the fault evolution path.

[0021] Compared with the prior art, the present invention application has the following beneficial effects: The present invention application provides a distribution network self-healing method, system, device and medium based on a fault evolution path, including: obtaining the operation data of a target distribution network in real time, and collecting a set of abnormal signals when a fault occurs from the operation data; the set of abnormal signals includes several signal values; when at least one of the signal values exceeds a preset threshold range, obtaining the current topological structure of the target distribution network; and by analyzing the topological structure and the set of abnormal signals, determining the starting node of the fault propagation path; according to the position of the starting node, obtaining the switch states of adjacent nodes; and then based on the switch states of adjacent nodes, obtaining a first set of control nodes; based on the first set of control nodes, dividing an initial fault isolation area; when it is detected that the fault range exceeds the initial fault isolation area, updating the topological structure based on the real-time load data of the target distribution network; evolving and predicting the fault propagation path based on the updated topological structure to obtain a second set of control nodes; dividing an optimized fault isolation area through the second set of control nodes, and controlling the target distribution network to perform a self-healing operation based on the optimized fault isolation area. The present invention application can accurately determine the starting node of the fault propagation path by obtaining the operation data of the target distribution network in real time, collecting a set of abnormal signals when a fault occurs, and analyzing in combination with the topological structure of the distribution network when at least one signal value exceeds the threshold range, laying a foundation for the subsequent accurate division of the initial fault isolation area; when it is detected that the fault range exceeds the initial fault isolation area, updating the topological structure based on the real-time load data of the target distribution network and evolving and predicting the fault propagation path, so as to determine the second set of control nodes for further optimizing the fault isolation area of the target distribution network and performing a self-healing operation. Compared with the existing "passive response or post-fault repair" self-healing strategy, the present invention application can adjust and optimize the isolation area in a timely manner based on the fault evolution situation, timely and accurately control the impact of fault evolution, reduce the fault impact range and duration, effectively improve the reliability and safety of the operation of the target distribution network, and enhance the self-healing ability of the target distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 : It is a schematic flowchart of an embodiment of the distribution network self-healing method based on a fault evolution path provided by the present invention application.

[0023] Figure 2 : It is a schematic flowchart of a first preferred implementation manner of an embodiment of the distribution network self-healing method based on a fault evolution path provided by the present invention application.

[0024] Figure 3 : It is a schematic flowchart of a second preferred implementation manner of an embodiment of the distribution network self-healing method based on a fault evolution path provided by the present invention application.

[0025] Figure 4 : Schematic flowchart of the third preferred implementation manner of an embodiment of the distribution network self-healing method based on the fault evolution path provided by this invention application.

[0026] Figure 5 : Schematic flowchart of the fourth preferred implementation manner of an embodiment of the distribution network self-healing method based on the fault evolution path provided by this invention application.

[0027] Figure 6 : Schematic structural diagram of an embodiment of the distribution network self-healing system based on the fault evolution path provided by this invention application. Specific implementation manners

[0028] Next, the technical solutions in the embodiments of this invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this invention. Obviously, the described embodiments are only a part of the embodiments of this invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this invention without making creative efforts belong to the scope of protection of this invention.

[0029] Embodiment 1 Please refer to Figure 1 , Figure 1 : Schematic flowchart of an embodiment of the distribution network self-healing method based on the fault evolution path provided by this invention application.

[0030] The distribution network self-healing method based on the fault evolution path in this embodiment can be applied to the control system of the distribution network. The control system can be applied to computer devices, which include but are not limited to smart phones, laptop computers, tablet computers, desktop computers, as well as physical servers and cloud servers, etc.

[0031] The distribution network self-healing method based on the fault evolution path in this embodiment includes steps S101 to S105; each step is detailed as follows: Step S101, obtain the operation data of the target distribution network in real time, and collect the abnormal signal set when a fault occurs from the operation data.

[0032] In this embodiment, the operation data includes but is not limited to current data, voltage data, and switch status data, etc.

[0033] When it is determined that a fault occurs in the target distribution network, in this embodiment, the operation status information including voltage abnormal fluctuations, current abnormal values, and switch abnormal states can be obtained from multiple data acquisition sources through the distribution network data acquisition system, and the above abnormal signal set can be obtained.

[0034] The abnormal signal set contains several signal values, specifically, the above-mentioned abnormal voltage fluctuations, abnormal current values, and the duration of the abnormal switch state.

[0035] Step S102: When at least one of the signal values exceeds a preset threshold range, obtain the current topological structure of the target distribution network; and determine the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set.

[0036] In this step, when at least one of the signal values exceeds a preset threshold range, for example, when the abnormal voltage fluctuation is greater than the preset voltage fluctuation threshold, the abnormal current value is greater than the preset current threshold, or the duration of the abnormal switch state is greater than the preset time threshold, the current topological structure of the target distribution network can be obtained.

[0037] Furthermore, the above topological structure can be represented by a directed graph composed of nodes and edges.

[0038] As Figure 2 shown, in a preferred embodiment, the step of determining the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set in step S102 includes steps S201 to S203; the details of each step are as follows: Step S201: Traverse the topological structure using the depth-first search algorithm to obtain the traversal result.

[0039] Step S202: Screen out the traversal paths whose signal values exceed the preset threshold range from the traversal result.

[0040] Step S203: Calculate the short-circuit risk of each node in the traversal path using the Dijkstra algorithm, and take the starting point of the path with a short-circuit risk greater than the preset risk value as the starting node of the fault propagation path.

[0041] Exemplarily, if the abnormal signal corresponds to node A, the voltage differences of nodes B, C, and D can be calculated. For example, the voltage of node A is 240V and there is an abnormal signal at this node, the voltage of node B is 235V, and the difference from node A is 5V, the voltage of node C is 245V, and the difference from point A is 5V, the voltage of node D is 220V, and the difference from node A is 20V. Since the abnormal voltage amplitude of node C is relatively large, it is determined that node C is the main propagation direction. And the depth-first search algorithm is executed according to this rule to traverse the topological structure to obtain the traversal result.

[0042] Suppose that multiple traversal paths with signal values exceeding the preset threshold range are traversed and filtered by the above method. One of them is Node A - Node C - Node F. The propagation path between Node A and Node F can be calculated by the weighted shortest path algorithm (Dijkstra algorithm), and the weight can be based on the impedance of the line (for example, the impedance of line A - F is 0.5Ω), and the total impedance of the path is 1.2Ω. It can be further confirmed that Node A - Node C - Node F is the main fault propagation path, or it can be analyzed that Node A - Node E - Node F in another traversal path is the main fault propagation path. At this time, calculate the short - circuit risk of each node in the main fault propagation path, and use the starting point of the path with a short - circuit risk greater than the preset risk value as the starting node of the fault propagation path.

[0043] Among them, the calculation method of the node short - circuit risk can adopt the method of the existing technology. For example, the current value of a certain node (95A, exceeding the threshold by 25A) and the switch state (changing 3 times within 1 hour, the threshold is 2 times) are used to infer that there may be a short - circuit risk at this node, etc.

[0044] Step S103: According to the position of the starting node, obtain the switch states of adjacent nodes; and then, based on the switch states of adjacent nodes, obtain the first control node set.

[0045] As described above, the starting node is obtained through the analysis of the fault propagation path. Therefore, when determining the control (node) points, it can be determined by analyzing the adjacent nodes.

[0046] In some preferred embodiments, as Figure 3 shown, the step of obtaining the first control node set based on the switch states of adjacent nodes in step S103 includes steps S301 to S303; where Step S301: Based on the switch states of the adjacent nodes, analyze the connection states of all nodes in the target distribution network through a graph traversal algorithm to obtain a node connection path set and a state anomaly pattern associated with the adjacent nodes.

[0047] Step S302: Perform clustering analysis according to the node connection path set and the state anomaly pattern to obtain a topological anomaly subset.

[0048] Step S303: Divide according to the topological anomaly subset to obtain the first control node set.

[0049] Exemplarily, in this preferred embodiment, the starting node determined by step S102 is X. Neighboring node data centered on node X can be extracted from the power grid real-time database through a distributed computing framework, including relevant information of 5 directly connected nodes Y1, Y2, Y3, Y4, and Y5. For example, the switch state of node Y1 is off, Y2 is on, Y3 is off, Y4 is on, and Y5 is on. At the same time, the load data of each node is obtained. For example, the load of Y2 is 45.5 kW (normal range 30 - 50 kW), Y4 is 52.3 kW (overloaded), and Y5 is 38.7 kW, etc.

[0050] Furthermore, based on the above neighboring nodes and along the paths between nodes, the connection states of all nodes in the target distribution network are analyzed to obtain a node connection path set related to the neighboring nodes and an abnormal state pattern.

[0051] Taking different abnormal state patterns as classes of the clustering algorithm respectively, clustering analysis is performed on the node connection path set to obtain a topological abnormal subset, thereby determining relevant first control nodes and obtaining a first control node set.

[0052] Step S104, based on the first control node set, divide the initial fault isolation area.

[0053] In this embodiment, the first control node (and the second control node below) can be used to cut off the connection between the fault area and the normal operation area, preventing the fault area from extending to the normal operation area of the target distribution network. Therefore, through multiple first control nodes, the initial fault isolation area can be preliminarily determined, laying a foundation for subsequent further optimization and refined division of the fault isolation area.

[0054] In a preferred embodiment, as Figure 4 shown, step S104 of dividing the initial fault isolation area based on the first control node set includes steps S401 to S403; wherein, Step S401, construct the load constraint of the target distribution network and the operation constraint of the first control node set, and the operation constraint includes resource consumption constraint and operation frequency constraint.

[0055] Step S402, according to the load constraint, resource consumption constraint, and operation frequency constraint, obtain a preliminary switch action sequence based on the first control point set.

[0056] Step S403, according to the preliminary switch action sequence, divide the initial fault isolation area.

[0057] In this preferred embodiment, based on the constraints of load constraint, resource consumption constraint, and operation frequency constraint, combined with a preset objective function, an optimal preliminary switching action sequence can be solved, and then, according to the sequence of switching actions, the initial fault isolation area can be gradually divided.

[0058] Step S105, when it is detected that the fault range exceeds the initial fault isolation area, update the topology based on the real-time load data of the target distribution network; and evolve and predict the fault propagation path based on the updated topology to obtain a second set of control nodes; through the second set of control nodes, divide to obtain an optimized fault isolation area, and control the target distribution network to perform self-healing operations based on the optimized isolated fault area.

[0059] In some preferred embodiments, as Figure 5 shown, the step of updating the topology based on the real-time load data of the target distribution network in step S105; and evolving and predicting the fault propagation path based on the updated topology to obtain a second set of control nodes includes steps S501 to S504; wherein, Step S501, obtain the node load of the key nodes in the potential fault expansion area from the real-time load data.

[0060] Step S502, mark the key nodes with node load greater than the preset load threshold as risk nodes, and update the topology according to the risk nodes.

[0061] Step S503, obtain historical fault data; through a preset path evolution prediction model, predict the fault propagation path based on the updated topology and the risk nodes; through the dynamic Bayesian network algorithm, predict the fault propagation probability based on the updated topology and the risk nodes.

[0062] Step S504, analyze to obtain a second set of control nodes based on the predicted propagation path and fault propagation probability.

[0063] In this preferred embodiment, the potential fault expansion area is preset and analyzed in advance before step S501. By obtaining the node load of the key nodes in the potential fault expansion area from the real-time load data and marking the key nodes with node load greater than the preset load threshold as risk nodes, the topology can be updated; further, based on the updated topology and risk nodes, a preset path evolution prediction model is used to predict the fault propagation path, and the dynamic Bayesian network algorithm is used to obtain the fault propagation probability and analyze to obtain a second set of control points. Compared with the existing "passive response or post-fault repair" self-healing strategy, it can timely adjust and optimize the isolation area based on the fault evolution situation, and timely and accurately control the impact of fault evolution.

[0064] In a preferred embodiment, the method of dividing an optimized fault isolation area through the second control node set and controlling the target distribution network to perform self-healing operation based on the optimized isolated fault area includes: analyzing the historical operation records and response delays at each second control node in the second control node set, where the historical operation records include the monthly operation times; comprehensively analyzing according to the monthly operation times, response delays, preset time window limits, and monthly operation upper limits to obtain the operation priorities of each second control node respectively; dividing an optimized fault isolation area through the second control node set; and controlling the target distribution network to perform self-healing operation based on the optimized isolated fault area according to the operation priorities in combination with the load distribution status of the optimized fault isolation area.

[0065] In this preferred embodiment, by comprehensively analyzing the monthly operation times, response delays, preset time window limits, and monthly operation upper limits, the operation priorities of each second control node are obtained. Then, in combination with the load distribution status of the optimized fault isolation area, the target distribution network is controlled to perform self-healing operation based on the optimized isolated fault area, which can enable the operation priorities of the second control nodes in the self-healing process to comprehensively consider aspects such as response speed and monthly operation times, and further ensure that the distribution network still has good operation performance during the self-healing process.

[0066] Preferably, the method of controlling the target distribution network to perform self-healing operation based on the optimized isolated fault area according to the operation priorities in combination with the load distribution status of the optimized fault isolation area includes: obtaining the resource consumption and load transfer conditions of the switch operations corresponding to each second control node; generating a switch operation plan with the goal of minimizing resource consumption according to the resource consumption and load transfer conditions in combination with the operation priorities, and then obtaining a switch operation sequence; and controlling the target distribution network to perform self-healing operation based on the optimized isolated fault area according to the switch operation sequence in combination with the preset parallel task processing sequence and the load distribution status of the optimized fault isolation area. This preferred embodiment can consider the resource consumption, load transfer conditions, and operation priorities of the switch operations corresponding to the second control nodes in combination, generate a switch operation plan with the goal of minimizing resource consumption, ensure the minimum loss of the distribution network during the self-healing process, and guarantee the stable operation during the self-healing process.

[0067] Correspondingly, as Figure 6 shown, the present invention application also provides a distribution network self-healing system 600 based on a fault evolution path, including a collection module 601, a node determination module 602, a control point determination module 603, a region division module 604, and a self-healing control module 605; wherein, The acquisition module 601 is used to obtain the operation data of the target distribution network in real time, and collect the abnormal signal set when a fault occurs from the operation data; the abnormal signal set includes several signal values; The node determination module 602 is used to obtain the current topological structure of the target distribution network when at least one of the signal values exceeds the preset threshold range; and determine the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set; The control point determination module 603 is used to obtain the switch states of adjacent nodes according to the position of the starting node; and then obtain the first control node set based on the switch states of adjacent nodes; The area division module 604 is used to divide the initial fault isolation area based on the first control node set; The self-healing control module 605 is used to update the topological structure based on the real-time load data of the target distribution network when it is detected that the fault range exceeds the initial fault isolation area; and perform an evolutionary prediction on the fault propagation path based on the updated topological structure to obtain a second control node set; divide the optimized fault isolation area through the second control node set, and control the target distribution network to perform self-healing operations based on the optimized isolated fault area.

[0068] As a preferred solution, the self-healing control module 605 updates the topological structure based on the real-time load data of the target distribution network; and performs an evolutionary prediction on the fault propagation path based on the updated topological structure to obtain a second control node set, including: The self-healing control module 605 obtains the node loads of the key nodes in the potential fault expansion area from the real-time load data; Mark the key nodes with node loads greater than the preset load threshold as risk nodes, and update the topological structure according to the risk nodes; Obtain historical fault data; predict the fault propagation path based on the updated topological structure and the risk nodes through a preset path evolution prediction model; predict the fault propagation probability based on the updated topological structure and the risk nodes through a dynamic Bayesian network algorithm; Analyze to obtain a second control node set based on the predicted propagation path and fault propagation probability.

[0069] As a preferred solution, the self-healing control module 605 divides the optimized fault isolation area through the second control node set, and controls the target distribution network to perform self-healing operations based on the optimized isolated fault area, including: The self-healing control module 605 analyzes the historical operation records and response delays at each second control node in the second control node set, where the historical operation records include the monthly operation times; Based on the comprehensive analysis of the monthly operation times, response delays, preset time window limit, and monthly operation upper limit, the operation priorities of each second control node are obtained respectively; Through the second control node set, an optimized fault isolation area is divided; and based on the operation priorities, combined with the load distribution status of the optimized fault isolation area, the target distribution network is controlled to perform self-healing operations based on the optimized isolated fault area.

[0070] As a preferred solution, the self-healing control module 605 controls the target distribution network to perform self-healing operations based on the optimized isolated fault area according to the operation priorities, combined with the load distribution status of the optimized fault isolation area, including: The self-healing control module 605 obtains the resource consumption and load transfer conditions corresponding to the switch operations of each second control node; According to the resource consumption and load transfer conditions, combined with the operation priorities, a switch operation plan aiming to minimize resource consumption is generated, and then a switch operation sequence is obtained; Based on the switch operation sequence, combined with the preset parallel task processing sequence and the load distribution status of the optimized fault isolation area, the target distribution network is controlled to perform self-healing operations based on the optimized isolated fault area.

[0071] As a preferred solution, the area division module 604 divides the initial fault isolation area based on the first control node set, including: The area division module 604 constructs the load constraint of the target distribution network and the operation constraints of the first control node set, where the operation constraints include resource consumption constraint and operation frequency constraint; According to the load constraint, resource consumption constraint, and operation frequency constraint, a preliminary switch action sequence is obtained based on the first control point set; According to the preliminary switch action sequence, the initial fault isolation area is divided.

[0072] As a preferred solution, the control point determination module 603 obtains the first control node set based on the switch states of adjacent nodes, including: The control point determination module 603 analyzes the connection states of all nodes in the target distribution network through a graph traversal algorithm based on the switch states of the adjacent nodes, and obtains a node connection path set and a state anomaly pattern associated with the adjacent nodes; Cluster analysis is performed according to the node connection path set and the state anomaly pattern to obtain a topological anomaly subset; A first control node set is obtained by partitioning according to the topological anomaly subset.

[0073] As a preferred solution, the node determination module 602 determines the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set, including: The node determination module 602 traverses the topological structure using a depth-first search algorithm to obtain a traversal result; Filter out the traversal paths whose signal values exceed the preset threshold range from the traversal result; Calculate the short-circuit risk of each node in the traversal path through the Dijkstra algorithm, and use the starting point of the path with a short-circuit risk greater than the preset risk value as the starting node of the fault propagation path.

[0074] Correspondingly, the present invention application also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the self-healing method of the distribution network based on the fault evolution path is implemented.

[0075] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal and connects various parts of the entire terminal using various interfaces and lines.

[0076] The memory can be used to store the computer program. By running or executing the computer program stored in the memory and invoking the data stored in the memory, the processor can implement various functions of the terminal. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0077] Correspondingly, the present invention application also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the distribution network self-healing method based on the fault evolution path.

[0078] Among them, if the modules integrated in the distribution network self-healing system based on the fault evolution path are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0079] Compared with the prior art, the present invention application has the following beneficial effects: The present invention application provides a distribution network self-healing method, system, device and medium based on a fault evolution path, including: obtaining the operation data of a target distribution network in real time, and collecting a set of abnormal signals at the time of fault occurrence from the operation data; the set of abnormal signals includes several signal values; when at least one of the signal values exceeds a preset threshold range, obtaining the current topological structure of the target distribution network; and analyzing the topological structure and the set of abnormal signals to determine the starting node of the fault propagation path; obtaining the switch states of adjacent nodes according to the position of the starting node; and then obtaining a first control node set based on the switch states of the adjacent nodes; dividing an initial fault isolation area based on the first control node set; when it is detected that the fault range exceeds the initial fault isolation area, updating the topological structure based on the real-time load data of the target distribution network; evolving and predicting the fault propagation path based on the updated topological structure to obtain a second control node set; dividing an optimized fault isolation area through the second control node set, and controlling the target distribution network to perform a self-healing operation based on the optimized isolated fault area. The present invention application can accurately determine the starting node of the fault propagation path by obtaining the operation data of the target distribution network in real time, collecting a set of abnormal signals at the time of fault occurrence, and analyzing in combination with the topological structure of the distribution network when at least one signal value exceeds the threshold range, laying a foundation for the subsequent precise division of the initial fault isolation area; when it is detected that the fault range exceeds the initial fault isolation area, updating the topological structure based on the real-time load data of the target distribution network and evolving and predicting the fault propagation path, so as to determine the second control node set for further optimizing the fault isolation area of the target distribution network and performing a self-healing operation. Compared with the existing "passive response or post-facto repair" self-healing strategy, the present invention application can timely adjust and optimize the isolation area based on the fault evolution situation, timely and accurately control the impact of fault evolution, reduce the fault impact range and duration, and effectively improve the reliability and safety of the operation of the target distribution network and enhance the self-healing ability of the target distribution network.

[0080] The specific embodiments described above further elaborate on the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A distribution network self-healing method based on a fault evolution path, characterized in that, Including: Obtain the operation data of the target distribution network in real time, and collect the abnormal signal set when a fault occurs from the operation data; the abnormal signal set contains several signal values; When at least one of the signal values exceeds the preset threshold range, obtain the current topological structure of the target distribution network; and determine the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set; According to the position of the starting node, obtain the switch states of adjacent nodes; and then obtain the first control node set based on the switch states of adjacent nodes; Divide the initial fault isolation area based on the first control node set; When it is detected that the fault range exceeds the initial fault isolation area, update the topological structure based on the real-time load data of the target distribution network; And perform evolutionary prediction on the fault propagation path based on the updated topological structure to obtain the second control node set; Divide the optimized fault isolation area through the second control node set, and control the target distribution network to perform self-healing operation based on the optimized isolation fault area.

2. The self-healing method for a distribution network based on a fault evolution path according to claim 1, wherein The updating of the topological structure based on the real-time load data of the target distribution network; And performing evolutionary prediction on the fault propagation path based on the updated topological structure to obtain the second control node set, including: Obtain the node loads of the key nodes in the potential fault expansion area from the real-time load data; Mark the key nodes with node loads greater than the preset load threshold as risk nodes, and update the topological structure according to the risk nodes; Obtain historical fault data; predict the fault propagation path based on the updated topological structure and the risk nodes through a preset path evolution prediction model; predict the fault propagation probability based on the updated topological structure and the risk nodes through the dynamic Bayesian network algorithm; Analyze to obtain the second control node set based on the predicted propagation path and fault propagation probability.

3. The self-healing method for a distribution network based on a fault evolution path according to claim 1, characterized in that, The dividing the optimized fault isolation area through the second control node set, and controlling the target distribution network to perform self-healing operation based on the optimized isolation fault area, including: Analyze the historical operation records and response delays at each second control node in the second control node set, and the historical operation records include the monthly operation times; Perform comprehensive analysis according to the monthly operation times, response delays, preset time window limit and monthly operation upper limit to obtain the operation priorities of each second control node respectively; Divide the optimized fault isolation area through the second control node set; and control the target distribution network to perform self-healing operation based on the optimized isolation fault area according to the operation priority and in combination with the load distribution state of the optimized fault isolation area.

4. The self-healing method for a distribution network based on a fault evolution path according to claim 3, wherein The controlling the target distribution network to perform self-healing operation based on the optimized isolation fault area according to the operation priority and in combination with the load distribution state of the optimized fault isolation area, including: Obtain the resource consumption and load transfer situation of the switch operations corresponding to each second control node; Generate a switching operation plan aiming to minimize resource consumption based on the resource consumption and load transfer conditions in combination with the operation priority, and then obtain a switching operation sequence; Based on the switching operation sequence, in combination with a preset parallel task processing sequence and the load distribution status of the optimized fault isolation area, control the target distribution network to perform self-healing operations based on the optimized isolation fault area.

5. The self-healing method for a distribution network based on a fault evolution path according to claim 1, characterized in that, The division of the initial fault isolation area based on the first control node set includes: Construct the load constraint of the target distribution network and the operation constraint of the first control node set, where the operation constraint includes resource consumption constraint and operation frequency constraint; Based on the load constraint, resource consumption constraint and operation frequency constraint, obtain a preliminary switching action sequence based on the first control point set; According to the preliminary switching action sequence, divide the initial fault isolation area.

6. The self-healing method for a distribution network based on a fault evolution path according to claim 1, characterized in that The obtaining of the first control node set based on the switching states of adjacent nodes includes: Based on the switching states of adjacent nodes, analyze the connection states of all nodes in the target distribution network through a graph traversal algorithm to obtain a node connection path set and a state anomaly pattern associated with the adjacent nodes; Perform clustering analysis according to the node connection path set and the state anomaly pattern to obtain a topological anomaly subset; According to the topological anomaly subset, divide to obtain the first control node set.

7. A distribution network self-healing method based on a fault evolution path according to claim 1, characterized in that, The determination of the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set includes: Use a depth-first search algorithm to traverse the topological structure to obtain a traversal result; Filter out the traversal paths in the traversal result whose signal values exceed a preset threshold range; Calculate the short-circuit risk of each node in the traversal path through the Dijkstra algorithm, and use the starting point of the path with a short-circuit risk greater than the preset risk value as the starting node of the fault propagation path.

8. A distribution network self-healing system based on a fault evolution path, characterized in that, Including a collection module, a node determination module, a control point determination module, a region division module and a self-healing control module; among them, The collection module is used to obtain the operation data of the target distribution network in real time and collect the abnormal signal set when a fault occurs from the operation data; the abnormal signal set contains several signal values; The node determination module is used to obtain the current topological structure of the target distribution network when at least one of the signal values exceeds a preset threshold range; and determine the starting node of the fault propagation path by analyzing the topological structure and the abnormal signal set; The control point determination module is used to obtain the switching states of adjacent nodes according to the position of the starting node; and then obtain the first control node set based on the switching states of adjacent nodes; The region division module is used to divide the initial fault isolation area based on the first control node set; The self-healing control module is used to update the topology based on the real-time load data of the target distribution network when it detects that the fault range exceeds the initial fault isolation area; and evolve and predict the fault propagation path based on the updated topology to obtain a second set of control nodes; through the second set of control nodes, an optimized fault isolation area is divided, and the target distribution network is controlled to perform self-healing operations based on the optimized isolated fault area.

9. A terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the distribution network self-healing method based on the fault evolution path as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the distribution network self-healing method based on the fault evolution path as described in any one of claims 1 to 7.

Images