Methods, devices, and storage media for generating fault inspection strategies for power distribution networks

Abstract

This invention discloses a method, apparatus, and storage medium for generating a fault inspection strategy for a distribution network. The method includes: acquiring single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network when the distribution network is in a fault condition; determining the initial topology of the distribution network based on the single-line diagram data and geographical location data; inputting the initial topology and initial state data into a target topology model of the distribution network for analysis to obtain multiple areas and devices to be inspected; inspecting the areas and devices based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network to obtain inspection results; and generating a fault inspection strategy for the distribution network based on the inspection results. This invention solves the technical problem of low efficiency in fault inspection of distribution networks.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, and more specifically, to a method, apparatus, and storage medium for generating a fault inspection strategy for a power distribution network. Background Technology

[0002] When a power distribution line trips due to a fault, maintenance personnel need to conduct fault inspections of the power distribution network in order to ensure the normal operation of the power distribution line and the normal power supply of users' electrical equipment.

[0003] Currently, during fault inspections, maintenance personnel are typically dispatched randomly to the site to check for external damage to the lines and to assess their electrical performance using relevant testing equipment. However, when maintenance personnel are not familiar enough with the structure of the distribution network and the geographical environment of the equipment, they cannot quickly and effectively plan inspection routes, leading to the technical problem of low efficiency in distribution network fault inspections.

[0004] There is currently no effective solution to the technical problem of low fault inspection efficiency in the aforementioned power distribution network. Summary of the Invention

[0005] This invention provides a method, apparatus, and storage medium for generating fault inspection strategies for power distribution networks, thereby at least solving the technical problem of low efficiency in fault inspection of power distribution networks.

[0006] According to one aspect of the invention, a method for generating a fault inspection strategy for a distribution network is provided. The method includes: when the distribution network is in a fault condition, acquiring single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network, wherein the single-line diagram data is obtained through the electrical connection diagram of the distribution network; determining the initial topology of the distribution network based on the single-line diagram data and geographical location data, wherein the initial topology is used to characterize the connection relationships between the multiple hardware devices; inputting the initial topology and initial state data into a target topology model of the distribution network for analysis to obtain multiple areas to be inspected and equipment to be inspected, wherein the target topology model is used to predict fault points in the distribution network; inspecting the areas to be inspected and equipment to be inspected based on target inspection resource information, target inspection constraints, and target inspection functions of the distribution network to obtain inspection results, wherein the target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through target inspection constraints, and the target inspection function is used to characterize the inspection objectives required to be achieved in inspecting the areas to be inspected and equipment to be inspected; and generating a fault inspection strategy for the distribution network based on the inspection results.

[0007] Optionally, based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, the area to be inspected and the equipment to be inspected are inspected to obtain inspection results, including: generating multiple inspection groups and multiple target inspection paths of the distribution network based on the target inspection resource information, target inspection constraints, and target inspection function; and inspecting the area to be inspected and the equipment to be inspected based on the multiple inspection groups and multiple target inspection paths to obtain inspection results.

[0008] Optionally, the initial topology and initial state data are input into the target topology model of the distribution network for analysis to obtain multiple distribution network areas and equipment to be inspected. This includes: inputting the initial topology and initial state data into the feature representation layer of the target topology model to obtain first structural feature data and first state feature data; inputting the first structural feature data and first state feature data into the embedding layer of the target topology model to obtain second structural feature data and second state feature data; inputting the second structural feature data and second state feature data into the attention mechanism of the target topology model to obtain third structural feature data and third state feature data; and determining multiple areas and equipment to be inspected based on the third structural feature data, third state feature data, and the target topology model.

[0009] Optionally, based on the third structural feature data, the third state feature data, and the target topology model, multiple areas to be inspected and equipment to be inspected are determined, including: inputting the third structural feature data and the third state feature data into the target topology model to obtain multiple initial inspection areas; using the target topology model to obtain multiple fault occurrence probabilities of multiple initial inspection equipment in the initial inspection areas; and determining multiple areas to be inspected and equipment to be inspected based on the multiple fault occurrence probabilities.

[0010] Optionally, based on multiple failure probabilities, multiple areas to be inspected and multiple equipment to be inspected are determined, including: selecting multiple target inspection equipment from multiple initial inspection equipment based on multiple failure probabilities; and determining multiple equipment to be inspected and multiple areas to be inspected corresponding to the multiple equipment to be inspected based on the multiple target inspection equipment.

[0011] Optionally, the method further includes: extracting features from the initial topology to obtain topology feature information of the initial topology; updating the initial topology model of the distribution network using the topology feature information to obtain the target topology model, wherein the initial topology model is obtained through the historical topology of the distribution network and the historical state data of each hardware device.

[0012] Optionally, the initial topology includes: device information of the hardware devices and connection information of the hardware devices.

[0013] According to one aspect of the present invention, an apparatus for generating a fault inspection strategy for a distribution network is provided. The apparatus further includes: a first acquisition unit, configured to acquire single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network when the distribution network is in a fault condition, wherein the single-line diagram data is obtained from the electrical connection diagram of the distribution network; a determination unit, configured to determine an initial topology of the distribution network based on the single-line diagram data and geographical location data, wherein the initial topology is used to characterize the connection relationships between the multiple hardware devices; and an input unit, configured to input the initial topology and initial state data into a target topology model of the distribution network. The analysis process involves several steps: first, an analysis unit to obtain multiple distribution network areas and equipment to be inspected; second, an acquisition unit to inspect the areas and equipment based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, obtaining inspection results; third, a generation unit to generate a fault inspection strategy for the distribution network based on the inspection results.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program, when run by a processor, controls the device where the storage medium is located to execute the method of the present invention.

[0015] According to another aspect of the present invention, a processor is also provided for running a program, wherein the program executes the methods of the present invention during runtime.

[0016] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the method of the present invention.

[0017] According to another aspect of the present invention, an electronic device is also provided, comprising a processor and a memory for storing processor-executable instructions. The processor is configured to execute instructions to implement the methods of the embodiments of the present invention.

[0018] In this embodiment of the invention, when the distribution network is in a fault condition, single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network are acquired. The single-line diagram data is obtained from the electrical connection diagram of the distribution network. Based on the single-line diagram data and geographical location data, the initial topology of the distribution network is determined, whereby the initial topology is used to characterize the connection relationships between multiple hardware devices. The initial topology and initial state data are input into the target topology model of the distribution network for analysis to obtain multiple areas to be inspected and devices to be inspected. The target topology model is used to predict fault points in the distribution network. Based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, the areas to be inspected and devices to be inspected are inspected to obtain inspection results. The target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through target inspection constraints, and the target inspection function is used to characterize the inspection objectives required to be achieved in inspecting the areas to be inspected and devices to be inspected. Based on the inspection results, a fault inspection strategy for the distribution network is generated. In other words, in the case of a fault in the distribution network, this embodiment of the invention can first acquire the single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network. Then, based on the single-line diagram data and geographical location data, the initial topology of the distribution network can be determined. The obtained initial topology results and initial state data are then input into the target topology model of the distribution network for analysis to obtain multiple areas and devices to be inspected. Based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, the obtained areas and devices to be inspected can be inspected to obtain inspection results. Finally, based on the inspection results, the purpose of generating a fault inspection strategy for the distribution network can be achieved. Since the initial topology of the distribution network is determined based on the obtained single-line diagram data and geographical location data, multiple areas and equipment to be inspected can be obtained based on the initial topology and initial state data, and using the target topology model. Then, based on the target inspection resource information, target inspection constraints, and target inspection function, the areas and equipment to be inspected can be inspected, thereby achieving the purpose of determining the fault inspection strategy of the distribution network. This solves the technical problem of low fault inspection efficiency in the distribution network and achieves the technical effect of improving the fault inspection efficiency of the distribution network. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0020] Figure 1This is a flowchart of a method for generating a fault inspection strategy for a power distribution network according to an embodiment of the present invention;

[0021] Figure 2 This is a flowchart of a fault inspection and dispatching method based on a graph neural network according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of a fault inspection and dispatch system based on a graph neural network according to an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of a device for generating a fault inspection strategy for a power distribution network according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of the present invention, a method for generating a fault inspection strategy for a power distribution network is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] The following describes the method for generating a fault inspection strategy for a distribution network according to an embodiment of the present invention.

[0028] Figure 1This is a flowchart of a method for generating a fault inspection strategy for a distribution network according to an embodiment of the present invention, such as... Figure 1 As shown, the method for generating the fault inspection strategy for this distribution network may include the following steps:

[0029] Step S101: In the event of a fault in the distribution network, obtain the single-line diagram data, geographical location data, and initial status data of multiple hardware devices in the distribution network.

[0030] In the technical solution provided by step S101 of the present invention, when the distribution network is in a fault condition, single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network can be obtained. The initial state data of the multiple hardware devices can be the device status data of each device after a fault trip in the distribution network, such as the opening and closing status of switches, and the current and voltage conditions of lines. The hardware devices can be simply referred to as equipment.

[0031] Optionally, the single-line diagram data is obtained from the electrical connection diagram of the power distribution network. The hardware equipment can be electrical equipment within the power distribution network. Geographic location data can be obtained through geographic location information, which can be obtained through Geographic Information System (GIS) maps. Geographic location data can be simply referred to as GIS data.

[0032] For example, collecting electrical connection diagrams of the power distribution network typically includes multiple devices (such as transformers, switches, cables, etc.) and the connection relationships between these devices, thus obtaining single-line diagram data of the power distribution network; at the same time, acquiring the geographical location information of the relevant devices in the power distribution network, including latitude, longitude, altitude, etc., as well as the spatial relationships between the devices, thus obtaining GIS data of the power distribution network.

[0033] Step S102: Determine the initial topology of the distribution network based on the single-line diagram data and geographical location data.

[0034] In the technical solution provided by step S102 of the present invention, the initial topology of the distribution network can be determined based on the obtained single-line diagram data and geographical location data. The initial topology is used to characterize the connection relationship between multiple hardware devices and can be the distribution network topology data after the trip when a fault occurs in the distribution network.

[0035] Optionally, the obtained single-line map data and geographic location data are integrated to obtain integrated data; the integrated data is preprocessed to obtain preprocessed integrated data; based on the preprocessed integrated data, an initial topology is determined, wherein the initial topology can be called a graph data structure, in which nodes can be used to represent devices and edges can be used to represent connections between devices.

[0036] For example, single-line map data is integrated with GIS data to ensure that each device has both electrical connection information and geographical location information in the map; the integrated data is preprocessed, including cleaning, noise reduction, and standardization, to ensure data quality, thus obtaining preprocessed integrated data; based on the preprocessed integrated data, a unified graph data structure is created, where nodes in the graph data structure represent devices, and edges represent connections between devices (electrical connections or spatial proximity relationships).

[0037] Step S103: Input the initial topology and initial state data into the target topology model of the distribution network for analysis to obtain multiple distribution network areas to be inspected and equipment to be inspected.

[0038] In the technical solution provided by step S103 of the present invention, after obtaining the initial topology and initial state data, the initial topology and initial state data can be input into the target topology model of the distribution network for analysis, so as to obtain the inspection areas and equipment of multiple distribution networks.

[0039] Optionally, the target topology model is used to predict fault points in the distribution network. The target topology model can be called a target graph neural network (GNN) model. The area to be inspected can be the area affected by the fault. The equipment to be inspected can be the equipment affected by the fault.

[0040] Alternatively, a graph neural network is a deep learning framework that uses neural networks to process graph-structured data. It aims to extract and discover features and patterns from complex graph-structured data to meet the needs of various graph learning tasks, such as clustering, classification, prediction, segmentation, and generation.

[0041] For example, when a fault trip occurs, the distribution network topology data of the section after the trip and the equipment status data of each device in the section after the trip are obtained. The distribution network topology data and equipment status data of the section after the trip are input into the target graph neural network model in order to obtain the area and equipment affected by the fault.

[0042] It should be noted that this is only a preferred embodiment for obtaining multiple distribution network areas and equipment to be inspected. The process and method for obtaining multiple distribution network areas and equipment to be inspected are not specifically limited. As long as the initial topology and initial state data are input into the target topology model for analysis to obtain multiple areas and equipment to be inspected, the process and method are within the protection scope of this invention and will not be listed here.

[0043] Step S104: Based on the target inspection resource information of the distribution network, the target inspection constraints of the distribution network, and the target inspection function of the distribution network, the inspection area and the equipment to be inspected are inspected to obtain the inspection results.

[0044] In the technical solution provided in step S104 of the present invention, based on the target inspection resource information of the distribution network, the target inspection constraints of the distribution network, and the target inspection function of the distribution network, the area to be inspected and the equipment to be inspected can be inspected, thereby obtaining the inspection results. Inspection refers to checking the operating status and environmental changes of distribution lines, promptly identifying problems that may threaten the safe and stable operation of the power grid, and preventing faults.

[0045] Optionally, the inspection results are used to characterize the operating status of the distribution network and the health status of the equipment. These inspection results can help maintenance personnel to promptly identify problems in the distribution network and take measures to solve them, thereby ensuring the normal operation of the distribution network and the safe and stable operation of the equipment.

[0046] Optionally, the target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through target inspection constraints, and the target inspection function is used to characterize the inspection target to be achieved when inspecting the area to be inspected and the equipment to be inspected.

[0047] Optionally, the initial inspection resource information can be the decision variables set initially. Specifically, it refers to the areas and equipment that need to be inspected after a power outage, as well as the availability of different human and material resources. For example, available human resources (such as the number and skill level of inspection personnel), material resources (such as the number, type, and load capacity of vehicles, the number and endurance of drones, etc.), terrain features, road conditions, and traffic restrictions of the inspection area. Based on the decision variables obtained above, a reasonable route can be planned.

[0048] Optionally, the target inspection constraints can be pre-set inspection constraints, which can be simply referred to as constraints. For example, each group needs at least two maintenance personnel, each group needs a corresponding vehicle, each group must inspect both overhead lines (sky) and underground cables, with overhead lines inspected by drones and cables by humans, each group needs at least one maintenance personnel skilled in controlling drones, time limits (e.g., inspection tasks must be completed within a certain time), and safety restrictions (e.g., avoiding dangerous areas). It should be noted that the vehicle corresponding to each group is only a means of transportation, used to transport maintenance personnel to the area to be inspected.

[0049] Optionally, the target inspection function can be a pre-defined target inspection function, which can be simply referred to as the target function. Examples include minimizing the total inspection time, maximizing inspection efficiency, or balancing the workload of each team (i.e., each team completes the inspection work within the same timeframe). It should be noted that this is only an example of a target inspection function and does not impose any specific limitations on it.

[0050] Step S105: Based on the inspection results, generate a fault inspection strategy for the distribution network.

[0051] In the technical solution provided by step S105 of the present invention, after obtaining the inspection results, a fault inspection strategy for the power distribution network can be generated, wherein the inspection results are used to characterize whether the area to be inspected and the equipment to be inspected are fault points.

[0052] Optionally, in response to the inspection result that the area to be inspected and the equipment to be inspected are fault points, a fault inspection strategy needs to be generated so that the fault points can be accurately inspected, thereby improving the fault inspection efficiency of the distribution network.

[0053] In the present invention, steps S101 to S105 can, when the distribution network is in a fault condition, first acquire the single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network. Then, based on the single-line diagram data and geographical location data, the initial topology of the distribution network can be determined. The obtained initial topology results and initial state data are then input into the target topology model of the distribution network for analysis to obtain multiple areas and devices to be inspected. Based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, the obtained areas and devices to be inspected can be inspected to obtain inspection results. Finally, based on the inspection results, the purpose of generating a fault inspection strategy for the distribution network can be achieved. Since the initial topology of the distribution network is determined based on the obtained single-line diagram data and geographical location data, multiple areas and equipment to be inspected can be obtained based on the initial topology and initial state data, and using the target topology model. Then, based on the target inspection resource information, target inspection constraints, and target inspection function, the areas and equipment to be inspected can be inspected, thereby achieving the purpose of determining the fault inspection strategy of the distribution network. This solves the technical problem of low fault inspection efficiency in the distribution network and achieves the technical effect of improving the fault inspection efficiency of the distribution network.

[0054] The method described in this embodiment will be further described below.

[0055] As an optional implementation method, based on the target inspection resource information of the distribution network, the target inspection constraints of the distribution network, and the target inspection function of the distribution network, the area to be inspected and the equipment to be inspected are inspected to obtain inspection results, including: generating multiple inspection groups and multiple target inspection paths of the distribution network based on the target inspection resource information, target inspection constraints, and target inspection function; and inspecting the area to be inspected and the equipment to be inspected based on the multiple inspection groups and multiple target inspection paths to obtain inspection results.

[0056] In this embodiment, a heuristic optimization algorithm is used to generate multiple inspection groups for the power distribution network and multiple target inspection paths corresponding to the inspection groups, based on the target inspection resource information, target inspection constraints, and target inspection functions. Then, based on the multiple inspection groups and multiple target inspection paths obtained above, the inspection of the area to be inspected and the equipment to be inspected can be carried out in order to obtain the inspection results.

[0057] Optionally, one target algorithm can be selected from multiple algorithms as the heuristic optimization algorithm, such as genetic algorithm, particle swarm optimization, ant colony optimization, etc. Since the problem of task allocation and path planning involves complex combinatorial optimization and requires significant computation, a heuristic optimization algorithm is suitable, as it can find an approximate optimal solution to the problem within a reasonable time.

[0058] Optionally, the inspection group can be simply referred to as a group. The target inspection path can be called the inspection route. The target inspection path of an inspection group can be the optimal inspection route corresponding to that inspection group.

[0059] Optionally, heuristic optimization algorithms can be used to perform inspection division of labor and path planning based on decision variables, constraints and objective functions, resulting in multiple groups and the optimal inspection route for each group, thereby achieving the goal of obtaining inspection results.

[0060] In this embodiment, after identifying potential fault points, and considering current manpower and material resources, it is determined how many groups should be divided to jointly inspect these potential fault points, with each group having a corresponding optimal inspection route. For example, three groups might be divided: Group A inspects fault points 1-3, Group B inspects fault points 4-7, and Group C inspects fault points 8-10. The process is as follows: a certain number of initial solutions (i.e., inspection division of labor and path planning schemes) are randomly generated; each initial solution is evaluated based on the objective function and constraints, and its fitness value is calculated.

[0061] Furthermore, after obtaining the fitness value of each initial solution, iterative optimization can be performed. The iterative optimization process includes: selection operation: selecting some excellent solutions as parents based on their fitness values; crossover (or mutation) operation: performing crossover (or mutation) on the parent solutions to generate new child solutions; fitness re-evaluation: evaluating the fitness of the newly generated child solutions; and updating the solution set: comparing the newly generated child solutions with the solutions in the current solution set and retaining the solutions with higher fitness.

[0062] In addition, after updating the solution set, it is necessary to determine whether the iteration count parameter meets the termination condition. When the iteration count parameter reaches the preset number of iterations or the quality of the current solution no longer improves significantly, the algorithm terminates. The optimal solution found by the heuristic optimization algorithm is examined, namely the optimal inspection division of labor and path planning scheme, and the optimal solution is verified according to the actual situation, and fine-tuned if necessary. According to the final determined inspection division of labor and path planning scheme, the corresponding maintenance personnel are assigned to carry out the corresponding inspection work.

[0063] As an optional implementation, the initial topology and initial state data are input into the target topology model of the distribution network for analysis to obtain multiple distribution network areas and equipment to be inspected. This includes: inputting the initial topology and initial state data into the feature representation layer of the target topology model to obtain first structural feature data and first state feature data; inputting the first structural feature data and first state feature data into the embedding layer of the target topology model to obtain second structural feature data and second state feature data; inputting the second structural feature data and second state feature data into the attention mechanism of the target topology model to obtain third structural feature data and third state feature data; and determining multiple areas and equipment to be inspected based on the third structural feature data, the third state feature data, and the target topology model.

[0064] In this embodiment, after obtaining the initial topology and initial state data, the initial topology and initial state data can be input into the feature representation layer of the target topology model to obtain first structural feature data and first state feature data. Then, the first structural feature data and first state feature data are input into the embedding layer of the target topology model to perform low-dimensional processing on the first structural feature data and first state feature data to obtain second structural feature data and second state feature data. The second structural feature data and second state feature data are then input into the attention mechanism of the target topology model to obtain third structural feature data and third state feature data. Finally, based on the third structural feature data, third state feature data, and target topology model, multiple areas to be inspected and equipment to be inspected can be determined.

[0065] Optionally, the feature representation layer can be a feature extraction layer, used to perform feature extraction processing on the initial topology and initial state data to obtain the corresponding first structural feature data and first state feature data. The first structural feature data includes node features (such as device type, capacity, geographical location, etc.) and edge features (such as connection type, distance, etc.). The first state feature data can be the state data of hardware devices, such as the on / off state of a switch. It should be noted that this is only an example of the first structural feature data and first state feature data.

[0066] For example, the distribution network topology data and equipment status data after the trip are input into the target graph neural network model. The target graph neural network model performs feature extraction processing on the distribution network topology data and equipment status data after the trip to obtain the corresponding feature data, such as node features (including equipment type, capacity, geographical location, etc.) and edge features (including connection type, distance, etc.). Then, the embedding layer in the target graph neural network model is used to convert these features into low-dimensional vector representations for subsequent processing.

[0067] Furthermore, under the influence of graph convolutional layers or attention mechanisms in the target graph neural network model, the features of nodes and edges will be propagated and aggregated within the network. Specifically, each node aggregates information from its neighbors (including direct neighbors and indirect neighbors reached through multiple layers of propagation) to update its own node representation. This process is repeated multiple times to capture the complex relationships and deep features in the distribution network.

[0068] For another example, the target graph neural network model analyzes the impact range of a fault trip on the distribution network, thereby obtaining the fault impact analysis results. For instance, by comparing the changes in node and edge representations before and after the fault, multiple areas and devices affected by the fault can be identified.

[0069] As an optional implementation method, multiple inspection areas and equipment to be inspected are determined based on third structural feature data, third state feature data, and target topology model, including: inputting the third structural feature data and third state feature data into the target topology model to obtain multiple initial inspection areas; using the target topology model to obtain multiple failure probabilities of multiple initial inspection equipment in the initial inspection areas; and determining multiple inspection areas and equipment to be inspected based on the multiple failure probabilities.

[0070] In this embodiment, the obtained third structural feature data and third state feature data are input into the target topology model to obtain multiple initial inspection areas. Then, using the target topology model, multiple failure probabilities of multiple initial inspection devices in the initial inspection areas can be obtained. Based on the obtained multiple failure probabilities, multiple areas to be inspected and devices to be inspected can be determined. These multiple areas to be inspected and devices to be inspected are the finally determined areas and devices that need to be inspected.

[0071] For example, based on the fault impact analysis results obtained above, the target graph neural network model will determine which areas are affected by the fault trip. These areas may include a collection of equipment such as lines, switches, and transformers near the fault point. Then, using the target graph neural network model, the probability of fault occurrence of multiple hardware devices can be determined. Based on the probability of fault occurrence, the areas and equipment that need to be inspected can be finally determined.

[0072] As an optional implementation method, multiple areas to be inspected and multiple devices to be inspected are determined based on multiple failure occurrence probabilities, including: selecting multiple target inspection devices from multiple initial inspection devices based on multiple failure occurrence probabilities; and determining multiple devices to be inspected and multiple areas to be inspected corresponding to the multiple devices to be inspected based on the multiple target inspection devices.

[0073] In this embodiment, after obtaining multiple failure probabilities, multiple target inspection devices can be selected from multiple initial inspection devices. Then, based on these target inspection devices, multiple devices to be inspected and their corresponding inspection areas can be determined. The target inspection devices can be referred to as key inspection devices.

[0074] Optionally, the multiple failure probabilities are sorted from largest to smallest to obtain the sorted failure probabilities; from the sorted failure probabilities, the target inspection equipment corresponding to the top target number of failure probabilities is selected, where the target number can be a preset number. For example, when the target number is 3, the equipment corresponding to the top 3 failure probabilities can be selected as the key inspection equipment from the sorted failure probabilities.

[0075] Optionally, after the target graph neural network model determines which areas are affected by the fault trip, it further filters out the equipment within those areas that requires priority inspection. This equipment may be the direct cause of the fault or a potential risk point, requiring maintenance personnel to prioritize its inspection and handling. For example, it identifies the probability of fault occurrence for each device within the area and then selects the devices with the highest probability of fault occurrence as those requiring priority inspection. Through this process, the areas and equipment requiring inspection after the trip are finally determined.

[0076] For another example, suppose there are multiple target graph neural network models. Each target graph neural network model outputs the areas and equipment that need to be inspected after a trip. By combining the areas and equipment that need to be inspected after a trip output by each target graph neural network model, the final areas and equipment that need to be inspected can be obtained. For example, from the areas and equipment that need to be inspected after a trip output by each target graph neural network model, the areas and equipment with higher prediction probabilities can be selected as the final areas and equipment that need to be inspected.

[0077] As an optional embodiment, the method further includes: extracting features from the initial topology to obtain topology feature information of the initial topology; updating the initial topology model of the distribution network using the topology feature information to obtain a target topology model, wherein the initial topology model is obtained through the historical topology of the distribution network and the historical state data of each hardware device.

[0078] In this embodiment, features can be extracted from the initial topology to obtain topology feature information of the initial topology. Then, the obtained topology feature information can be used to update the initial topology model of the distribution network to obtain the target topology model.

[0079] Optionally, feature extraction is performed on the node and edge information in the initial topology. Features are extracted for each node (device), such as device type, device capacity, device status (operating or under maintenance), and geographical location (latitude and longitude); features are extracted for each edge (connection), such as connection type (electrical connection or spatial connection), connection distance (spatial connection), and current / voltage level (electrical connection).

[0080] Optionally, the topological structure feature information includes node feature information and edge feature information. Node feature information can be simply referred to as node features, and edge feature information can be simply referred to as edge features. The initial topological model can be an untrained graph neural network model, and the target topological model can be a trained graph neural network model, such as a graph convolutional network (GCN), a graph attention network (GAT), or a graph isomorphism network (GIN). It should be noted that this is only an example of a graph neural network model.

[0081] Optionally, after obtaining the node (device) features and edge (connection) features, a suitable graph neural network model is selected and iteratively trained to obtain a trained graph neural network model. For example, the node (device) features and edge (connection) features are input into the selected graph neural network model. Through multiple layers of graph convolutional layers or attention mechanisms in the selected graph neural network model, the node (device) features and edge (connection) features are learned and embedded to capture the complex topology of the distribution network and the deep relationships between devices. After multiple rounds of training, a trained graph neural network model can be obtained. In this model, each node and edge updates its representation in the network using information from its neighbors (connected nodes or edges).

[0082] Furthermore, by fine-tuning the parameters of the trained graph neural network model, a target graph neural network model can be obtained, which can be used for fault prediction. It should be noted that, to ensure the accuracy of fault prediction, different types of target graph neural network models can be trained based on different types of graph neural network models.

[0083] As an optional implementation, the initial topology includes: device information of the hardware devices and connection information of the hardware devices.

[0084] In this embodiment, the initial topology may include: device information of the hardware devices and connection information of the hardware devices, wherein the device information of the hardware devices may be node information, and the connection information of the hardware devices may be edge information.

[0085] Optionally, equipment information may include: equipment type, equipment capacity, equipment status (operating or under maintenance), and geographical location (latitude and longitude). Connection information may include: connection type (electrical connection or spatial connection), connection distance (spatial connection), and current or voltage level (electrical connection). It should be noted that the equipment information and connection information provided here are merely illustrative examples and do not impose specific limitations on the equipment information and connection information.

[0086] In this embodiment, when the distribution network is in a fault condition, the single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network are first obtained. Then, based on the single-line diagram data and geographical location data, the initial topology of the distribution network can be determined. The obtained initial topology results and initial state data are then input into the target topology model of the distribution network for analysis to obtain multiple areas and devices to be inspected. Based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, the obtained areas and devices to be inspected can be inspected to obtain inspection results. Finally, based on the inspection results, the purpose of generating a fault inspection strategy for the distribution network is achieved. Since the initial topology of the distribution network is determined based on the obtained single-line diagram data and geographical location data, multiple areas and equipment to be inspected can be obtained based on the initial topology and initial state data, and using the target topology model. Then, based on the target inspection resource information, target inspection constraints, and target inspection function, the areas and equipment to be inspected can be inspected, thereby achieving the purpose of determining the fault inspection strategy of the distribution network. This solves the technical problem of low fault inspection efficiency in the distribution network and achieves the technical effect of improving the fault inspection efficiency of the distribution network.

[0087] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0088] There are various reasons why power distribution lines trip due to faults. These mainly include overload operation causing the current to exceed the rated carrying capacity of the line or equipment, such as high current surges caused by short circuit faults, leakage current due to insulation aging or damage, line breaks caused by natural environmental factors (lightning strikes), and damage to the line caused by human factors (such as construction errors or animal activity). These factors can all cause protection equipment to detect abnormal conditions and automatically disconnect the circuit, i.e., trip, to prevent more serious consequences such as equipment damage or fire.

[0089] Therefore, when a power distribution line trips due to a fault, in order to ensure the normal operation of the power distribution line and the normal power supply of users' electrical equipment, maintenance personnel need to conduct fault inspections of the power distribution network in order to quickly find and isolate the fault point and restore power supply.

[0090] Currently, during fault inspections, maintenance personnel are typically dispatched randomly to the site to check for external damage to the lines and to assess their electrical performance, including insulation and grounding status, using relevant testing equipment. Simultaneously, close attention is paid to the surrounding environment for potential safety hazards. However, when maintenance personnel are not familiar enough with the structure of the distribution network and the geographical environment of the equipment, they cannot quickly and effectively plan inspection routes, leading to the technical problem of low efficiency in distribution network fault inspections.

[0091] Therefore, in order to solve the above problems, this invention proposes a fault inspection dispatching method based on graph neural networks. This method can determine which equipment is a possible fault point that needs to be inspected after a fault occurs, based on the single-line diagram of the line and the equipment location information. Then, according to the current personnel and material situation, appropriate groups are established. Finally, the optimal inspection route is planned for each group (ideally, each group completes the inspection work in the same amount of time) in order to reduce the fault investigation time, thereby solving the technical problem of low fault inspection efficiency in the distribution network and achieving the technical effect of improving the fault inspection efficiency of the distribution network.

[0092] In this embodiment, Figure 2 This is a flowchart of a fault inspection and dispatching method based on a graph neural network according to an embodiment of the present invention. The fault inspection and dispatching method based on a graph neural network mainly includes the following steps:

[0093] Step S201: Based on the single-line diagram and geographic information system diagram of the distribution network, the topology of the distribution network is learned by using graph neural network modeling.

[0094] In this embodiment, single-line diagrams and geographic information system (GIS) maps of the power distribution network can be collected, and the topology of the power distribution network can be determined using graph neural networks based on the obtained single-line diagrams and GIS maps.

[0095] Optionally, electrical connection diagrams of the distribution network are collected, which typically include multiple devices (such as transformers, switches, cables, etc.) and the connection relationships between multiple devices, thereby obtaining single-line diagram data of the distribution network; at the same time, the geographical location information of the relevant devices in the distribution network, including latitude, longitude, altitude, etc., as well as the spatial relationships between devices, are obtained, thereby obtaining GIS data of the distribution network.

[0096] Optionally, the single-line graph data is integrated with GIS data to ensure that each device has both electrical connection information and geographical location information in the graph; the integrated data is preprocessed, including cleaning, noise reduction, and standardization, to ensure data quality, thereby obtaining preprocessed integrated data; based on the preprocessed integrated data, a unified graph data structure is created, where nodes in the graph data structure represent devices, and edges represent connections between devices (electrical connections or spatial proximity relationships).

[0097] Optionally, features are extracted for each node (device) to obtain node features, such as device type, device capacity, device status (operating or under maintenance), geographical location (latitude and longitude), etc.; features are extracted for each edge (connection) to obtain edge features, such as connection type (electrical connection or spatial connection), connection distance (spatial connection), current / voltage level (electrical connection), etc.

[0098] Optionally, a suitable graph neural network model can be selected, such as GCN, GAT, or GIN. It should be noted that these graph neural network models typically include multiple graph convolutional layers to learn feature representations of nodes and edges.

[0099] Optionally, after obtaining the node (device) features and edge (connection) features, a suitable graph neural network model is selected and iteratively trained to obtain a trained graph neural network model. For example, the node (device) features and edge (connection) features are input into the selected graph neural network model. Through multiple layers of graph convolutional layers or attention mechanisms in the selected graph neural network model, the node (device) features and edge (connection) features are learned and embedded to capture the complex topology of the distribution network and the deep relationships between devices. After multiple rounds of training, a trained graph neural network model can be obtained. In this model, each node and edge updates its representation in the network using information from its neighbors (connected nodes or edges).

[0100] Optionally, the trained graph neural network model can be optimized to obtain a target graph neural network model, which can be used for fault prediction. It should be noted that, to ensure the accuracy of fault prediction, different types of target graph neural network models can be trained based on different types of graph neural network models.

[0101] Step S202: When a fault trip occurs, the topology of the distribution network is analyzed to determine the areas and equipment that need to be inspected after the trip.

[0102] In this embodiment, after obtaining the topology, the topology of the distribution network can be analyzed to determine the areas and equipment that need to be inspected after a trip.

[0103] Optionally, when a fault trip occurs, the topology data of the distribution network downstream of the trip (where nodes represent equipment such as transformers, switches, and lines, and edges represent the electrical connections or spatial proximity between these devices) and the equipment status data of each device downstream of the trip, such as the opening and closing status of switches and the current and voltage status of lines, can be obtained.

[0104] Optionally, the distribution network topology data and equipment status data after the trip are input into the target graph neural network model. The target graph neural network model performs feature extraction processing on the distribution network topology data and equipment status data after the trip to obtain corresponding feature data, such as node features (including equipment type, capacity, geographical location, etc.) and edge features (including connection type, distance, etc.). Then, the embedding layer in the target graph neural network model is used to convert these features into low-dimensional vector representations for subsequent processing.

[0105] Furthermore, under the influence of graph convolutional layers or attention mechanisms in the target graph neural network model, the features of nodes and edges will be propagated and aggregated within the network. Specifically, each node aggregates information from its neighbors (including direct neighbors and indirect neighbors reached through multiple layers of propagation) to update its own node representation. This process is repeated multiple times to capture the complex relationships and deep features in the distribution network.

[0106] Optionally, the target graph neural network model analyzes the impact range of a fault trip on the distribution network, thereby obtaining fault impact analysis results. For example, by comparing the changes in node and edge representations before and after the fault, multiple areas and devices affected by the fault can be identified.

[0107] Optionally, based on the fault impact analysis results obtained above, the target graph neural network model will determine which areas are affected by the fault trip. These areas may include a collection of equipment such as lines, switches, and transformers near the fault point. After determining the areas affected by the fault, the target graph neural network model will further filter out the equipment within these areas that requires priority inspection. These devices may be the direct cause of the fault or potential risk points, requiring priority inspection and handling by maintenance personnel. For example, the model can identify the probability of fault occurrence for each device in the area, and then select the devices with the highest probability of fault occurrence as the devices requiring priority inspection. Through this process, the areas and equipment that need to be inspected after the trip are finally determined.

[0108] For example, suppose there are multiple target graph neural network models. Each target graph neural network model outputs the areas and equipment that need to be inspected after a trip. By combining the areas and equipment that need to be inspected after a trip output by each target graph neural network model, the final areas and equipment that need to be inspected can be obtained. For example, from the areas and equipment that need to be inspected after a trip output by each target graph neural network model, the areas and equipment with higher prediction probabilities can be selected as the final areas and equipment that need to be inspected.

[0109] Step S203: Based on different human and material resources, use a heuristic optimization algorithm to divide the inspection work and plan the route for the power distribution network, and determine the best group assignment and inspection route.

[0110] In this embodiment, based on different human and material resources, and using heuristic optimization algorithms, the inspection of the power distribution network can be divided into tasks and routes can be planned to determine the optimal group assignment and inspection route.

[0111] Optionally, heuristic optimization algorithms can be used to perform inspection division of labor and path planning based on decision variables, constraints and objective functions, resulting in multiple groups and the optimal inspection route for each group.

[0112] In this embodiment, after identifying potential fault points, and considering current manpower and material resources, it is determined how many groups should be divided to jointly inspect these potential fault points, with each group having a corresponding optimal inspection route. For example, three groups might be divided: Group A inspects fault points 1-3, Group B inspects fault points 4-7, and Group C inspects fault points 8-10. The process is as follows: a certain number of initial solutions (i.e., inspection division of labor and path planning schemes) are randomly generated; each initial solution is evaluated based on the objective function and constraints, and its fitness value is calculated.

[0113] Furthermore, after obtaining the fitness value of each initial solution, iterative optimization can be performed. The iterative optimization process includes: selection operation: selecting some excellent solutions as parents based on their fitness values; crossover (or mutation) operation: performing crossover (or mutation) on the parent solutions to generate new child solutions; fitness re-evaluation: evaluating the fitness of the newly generated child solutions; and updating the solution set: comparing the newly generated child solutions with the solutions in the current solution set and retaining the solutions with higher fitness.

[0114] In addition, after updating the solution set, it is necessary to determine whether the iteration count parameter meets the termination condition. When the iteration count parameter reaches the preset number of iterations or the quality of the current solution no longer improves significantly, the algorithm terminates. The optimal solution found by the heuristic optimization algorithm is examined, namely the optimal inspection division of labor and path planning scheme, and the optimal solution is verified according to the actual situation, and fine-tuned if necessary. According to the final determined inspection division of labor and path planning scheme, the corresponding maintenance personnel are assigned to carry out the corresponding inspection work.

[0115] Optionally, constraints can be set. For example, each group must have at least two maintenance personnel, each group must have a corresponding vehicle, each group must inspect both overhead lines (sky) and underground cables (underground), with overhead lines inspected by drones and cables by personnel, each group must have at least one maintenance personnel skilled in drone operation, time limits (e.g., inspection tasks must be completed within a certain time), and safety restrictions (e.g., avoiding dangerous areas). It should be noted that the vehicle assigned to each group is only a means of transportation, used to transport maintenance personnel to the areas requiring inspection.

[0116] Optionally, decision variables can be set, specifically referring to the areas and equipment that need to be inspected after a power outage, as well as the availability of different human and material resources. These include available human resources (such as the number and skill level of inspection personnel), material resources (such as the number, type, and load capacity of vehicles, the number and endurance of drones, etc.), the terrain features, road conditions, and traffic restrictions of the inspection area. Based on these decision variables, a reasonable route can be planned.

[0117] Optionally, an objective function can be set, such as minimizing the total inspection time, maximizing inspection efficiency, or balancing the workload of each group (i.e., each group completes the inspection work in the same amount of time).

[0118] Optionally, a suitable heuristic optimization algorithm can be selected, such as a genetic algorithm, particle swarm optimization, or ant colony optimization. Since the problem of task allocation and path planning involves complex combinatorial optimization and requires significant computation, a heuristic optimization algorithm is suitable, as it can find an approximate optimal solution within a reasonable timeframe.

[0119] In an embodiment of the present invention, Figure 3 This is a schematic diagram of a fault inspection and dispatch system based on a graph neural network according to an embodiment of the present invention, as shown below. Figure 3 As shown, the system includes a main unit 301 and a secondary unit 302.

[0120] Host 301 is used for data storage and computation.

[0121] Extension 302 is used to view the work assignment plan and optimal patrol route for this group.

[0122] Alternatively, the extension unit may be referred to as a Personal Digital Assistant (PDA) extension unit.

[0123] In this embodiment, each maintenance worker can be assigned a dedicated PDA extension. Furthermore, the algorithm is encapsulated within the host computer. Simply importing the single-line diagram and GIS map of the power distribution network into the host's Secure Digital (SD) card allows for offline path planning and task allocation. The specific internal implementation process is the same as the aforementioned fault inspection and dispatch method based on graph neural networks. Moreover, the host computer can send the corresponding paths and tasks to the corresponding maintenance worker's PDA extension, allowing the worker to view the dispatch plan and optimal inspection path for their group at any time via their PDA extension.

[0124] In this embodiment, when the distribution network is in a fault condition, the single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network are first obtained. Then, based on the single-line diagram data and geographical location data, the initial topology of the distribution network can be determined. The obtained initial topology results and initial state data are then input into the target topology model of the distribution network for analysis to obtain multiple areas and devices to be inspected. Based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, the obtained areas and devices to be inspected can be inspected to obtain inspection results. Finally, based on the inspection results, the purpose of generating a fault inspection strategy for the distribution network is achieved. Since the initial topology of the distribution network is determined based on the obtained single-line diagram data and geographical location data, multiple areas and equipment to be inspected can be obtained based on the initial topology and initial state data, and using the target topology model. Then, based on the target inspection resource information, target inspection constraints, and target inspection function, the areas and equipment to be inspected can be inspected, thereby achieving the purpose of determining the fault inspection strategy of the distribution network. This solves the technical problem of low fault inspection efficiency in the distribution network and achieves the technical effect of improving the fault inspection efficiency of the distribution network.

[0125] According to an embodiment of the present invention, an apparatus for generating a fault inspection strategy for a distribution network is provided. It should be noted that this apparatus for generating a fault inspection strategy for a distribution network can be used to execute a method for generating a fault inspection strategy for a distribution network as described in Embodiment 1.

[0126] Figure 4 This is a schematic diagram of a fault inspection strategy generation device for a distribution network according to an embodiment of the present invention, as shown below. Figure 4 As shown, a fault inspection strategy generation device 400 for a power distribution network may include: a first acquisition unit 401, a determination unit 402, an input unit 403, a second acquisition unit 404, and a generation unit 405.

[0127] The first acquisition unit 401 is used to acquire single-line diagram data, geographical location data, and initial status data of multiple hardware devices in the distribution network when the distribution network is in a fault situation. The single-line diagram data is obtained through the electrical connection diagram of the distribution network.

[0128] The determination unit 402 is used to determine the initial topology of the distribution network based on single-line diagram data and geographical location data, wherein the initial topology is used to characterize the connection relationship between multiple hardware devices.

[0129] The input unit 403 is used to input the initial topology and initial state data into the target topology model of the distribution network for analysis, so as to obtain multiple distribution network areas to be inspected and equipment to be inspected. The target topology model is used to predict the fault points of the distribution network.

[0130] The second acquisition unit 404 is used to inspect the area to be inspected and the equipment to be inspected based on the target inspection resource information of the distribution network, the target inspection constraint conditions of the distribution network, and the target inspection function of the distribution network, and to obtain the inspection results. The target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through the target inspection constraint conditions, and the target inspection function is used to characterize the inspection target that needs to be achieved when inspecting the area to be inspected and the equipment to be inspected.

[0131] The generation unit 405 is used to generate a fault inspection strategy for the distribution network based on the inspection results.

[0132] Optionally, the second acquisition unit 404 includes: a generation module, used to generate multiple inspection groups of the distribution network and multiple target inspection paths based on target inspection resource information, target inspection constraints and target inspection functions; and an inspection module, used to inspect the area to be inspected and the equipment to be inspected based on the multiple inspection groups and multiple target inspection paths, and obtain inspection results.

[0133] Optionally, the input unit 403 includes: a first input module for inputting the initial topology and initial state data into the feature representation layer of the target topology model to obtain first structural feature data and first state feature data; a second input module for inputting the first structural feature data and first state feature data into the embedding layer of the target topology model to obtain second structural feature data and second state feature data; a third input module for inputting the second structural feature data and second state feature data into the attention mechanism of the target topology model to obtain third structural feature data and third state feature data; and a determination module for determining multiple areas to be inspected and equipment to be inspected based on the third structural feature data, the third state feature data, and the target topology model.

[0134] Optionally, the determining module may include: an input submodule, used to input the third structural feature data and the third state feature data into the target topology model to obtain multiple initial inspection areas; an acquisition submodule, used to use the target topology model to obtain multiple failure probabilities of multiple initial inspection devices in the initial inspection areas; and a determining submodule, used to determine multiple areas to be inspected and devices to be inspected based on the multiple failure probabilities.

[0135] Optionally, the determination submodule is also used to select multiple target inspection devices from multiple initial inspection devices based on multiple failure occurrence probabilities; and to determine multiple devices to be inspected, and multiple inspection areas corresponding to the multiple devices to be inspected, based on the multiple target inspection devices.

[0136] Optionally, the device further includes: a third acquisition unit, used to extract features from the initial topology to obtain topology feature information of the initial topology; and an update unit, used to update the initial topology model of the distribution network using the topology feature information to obtain a target topology model, wherein the initial topology model is obtained through the historical topology of the distribution network and the historical state data of each hardware device.

[0137] Optionally, the initial topology includes: device information of the hardware devices and connection information of the hardware devices.

[0138] In this embodiment, when the distribution network is in a fault condition, the first acquisition unit acquires single-line diagram data, geographical location data, and initial state data of multiple hardware devices in the distribution network. The single-line diagram data is obtained from the electrical connection diagram of the distribution network. The determination unit determines the initial topology of the distribution network based on the single-line diagram data and geographical location data. The initial topology is used to characterize the connection relationships between the multiple hardware devices. The input unit inputs the initial topology and initial state data into the target topology model of the distribution network for analysis, obtaining multiple areas of the distribution network to be inspected and equipment to be inspected. The target topology model is used for prediction. The fault points of the distribution network are identified. A second acquisition unit, based on the target inspection resource information, target inspection constraints, and target inspection function of the distribution network, inspects the area to be inspected and the equipment to be inspected, obtaining inspection results. The target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through target inspection constraints. The target inspection function characterizes the inspection objectives required to be achieved in inspecting the area to be inspected and the equipment to be inspected. A generation unit, based on the inspection results, generates a fault inspection strategy for the distribution network to address the technical problem of low fault inspection efficiency in the distribution network, thereby improving the technical effect of fault inspection efficiency.

[0139] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is run by a processor, it controls the device where the readable storage medium is located to execute the method for generating a fault inspection strategy for the power distribution network in the embodiment.

[0140] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the method for generating a fault inspection strategy for a power distribution network in the embodiment.

[0141] According to an embodiment of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the method for generating a fault inspection strategy for a power distribution network according to an embodiment of the present invention.

[0142] According to embodiments of the present invention, an electronic device is also provided, comprising a processor and a memory for storing processor-executable instructions. The processor is configured to execute instructions to implement the method for generating a fault inspection strategy for a power distribution network according to embodiments of the present invention.

[0143] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0144] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0145] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0146] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0148] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0149] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for generating a fault inspection strategy for a distribution network, characterized in that, include: In the event of a fault in the power distribution network, the single-line diagram data, geographical location data, and initial status data of multiple hardware devices in the power distribution network are obtained. The single-line diagram data is obtained through the electrical connection diagram of the power distribution network. Based on the single-line diagram data and the geographical location data, the initial topology of the power distribution network is determined, wherein the initial topology is used to characterize the connection relationship between multiple hardware devices; The initial topology and initial state data are input into the target topology model of the distribution network for analysis to obtain multiple areas and equipment to be inspected in the distribution network. The target topology model is used to predict the fault points of the distribution network. Based on the target inspection resource information of the distribution network, the target inspection constraints of the distribution network, and the target inspection function of the distribution network, the area to be inspected and the equipment to be inspected are inspected to obtain inspection results. The target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through the target inspection constraints. The target inspection function is used to characterize the inspection target to be achieved when inspecting the area to be inspected and the equipment to be inspected. Based on the inspection results, a fault inspection strategy for the power distribution network is generated. The process involves inputting the initial topology and initial state data into a target topology model of the distribution network for analysis to obtain multiple areas and devices to be inspected. This includes: inputting the initial topology and initial state data into the feature representation layer of the target topology model to obtain first structural feature data and first state feature data; inputting the first structural feature data and first state feature data into the embedding layer of the target topology model to obtain second structural feature data and second state feature data; inputting the second structural feature data and second state feature data into the attention mechanism of the target topology model to obtain third structural feature data and third state feature data; and determining multiple areas and devices to be inspected based on the third structural feature data, the third state feature data, and the target topology model. Based on the third structural feature data, the third state feature data, and the target topology model, multiple inspection areas and equipment to be inspected are determined, including: inputting the third structural feature data and the third state feature data into the target topology model to obtain multiple initial inspection areas; using the target topology model to obtain multiple fault occurrence probabilities of multiple initial inspection equipment in the initial inspection areas; and determining multiple inspection areas and equipment to be inspected based on the multiple fault occurrence probabilities. Based on the multiple failure occurrence probabilities, determining multiple areas to be inspected and multiple devices to be inspected includes: selecting multiple target inspection devices from multiple initial inspection devices based on the multiple failure occurrence probabilities; and determining multiple devices to be inspected and multiple areas to be inspected corresponding to the multiple devices to be inspected based on the multiple target inspection devices.

2. The method according to claim 1, characterized in that, Based on the target inspection resource information of the distribution network, the target inspection constraints of the distribution network, and the target inspection function of the distribution network, the area to be inspected and the equipment to be inspected are inspected to obtain inspection results, including: Based on the target inspection resource information, the target inspection constraints, and the target inspection function, multiple inspection groups and multiple target inspection paths are generated for the power distribution network. Based on multiple inspection groups and multiple target inspection paths, the area to be inspected and the equipment to be inspected are inspected to obtain the inspection results.

3. The method according to claim 1, characterized in that, The method further includes: Feature extraction is performed on the initial topology to obtain the topological feature information of the initial topology; The initial topology model of the distribution network is updated using the topology feature information to obtain the target topology model, wherein the initial topology model is obtained by using the historical topology of the distribution network and the historical state data of each hardware device.

4. The method according to claim 1, characterized in that, The initial topology includes: device information of the hardware device and connection information of the hardware device.

5. A device for generating a fault inspection strategy for a power distribution network, characterized in that, include: The first acquisition unit is used to acquire single-line diagram data, geographical location data, and initial status data of multiple hardware devices in the distribution network when the distribution network is in a fault situation. The single-line diagram data is obtained through the electrical connection diagram of the distribution network. A determining unit is configured to determine the initial topology of the power distribution network based on the single-line diagram data and the geographical location data, wherein the initial topology is used to characterize the connection relationship between multiple hardware devices; The input unit is used to input the initial topology and the initial state data into the target topology model of the distribution network for analysis, so as to obtain multiple areas to be inspected and equipment to be inspected in the distribution network, wherein the target topology model is used to predict the fault points of the distribution network; The second acquisition unit is used to inspect the area to be inspected and the equipment to be inspected based on the target inspection resource information of the distribution network, the target inspection constraints of the distribution network, and the target inspection function of the distribution network, and to obtain inspection results. The target inspection resource information is obtained by constraining the initial inspection resource information of the distribution network through the target inspection constraints, and the target inspection function is used to characterize the inspection target to be achieved by inspecting the area to be inspected and the equipment to be inspected. A generation unit is used to generate a fault inspection strategy for the power distribution network based on the inspection results. The input unit is configured to input the initial topology and the initial state data into the feature representation layer of the target topology model to obtain first structural feature data and first state feature data; input the first structural feature data and the first state feature data into the embedding layer of the target topology model to obtain second structural feature data and second state feature data; input the second structural feature data and the second state feature data into the attention mechanism of the target topology model to obtain third structural feature data and third state feature data; and determine multiple areas to be inspected and equipment to be inspected based on the third structural feature data, the third state feature data, and the target topology model. The input unit is further configured to input the third structural feature data and the third state feature data into the target topology model to obtain multiple initial inspection areas; use the target topology model to obtain multiple failure probabilities of multiple initial inspection devices in the initial inspection areas; and determine multiple areas to be inspected and devices to be inspected based on the multiple failure probabilities. The input unit is further configured to select multiple target inspection devices from multiple initial inspection devices based on multiple failure occurrence probabilities; and to determine multiple devices to be inspected and multiple inspection areas corresponding to the multiple devices to be inspected based on the multiple target inspection devices.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein when the program is run by a processor, it controls the device in which the storage medium is located to perform the method of any one of claims 1 to 4.

7. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method of any one of claims 1 to 4.

Images