Power distribution network fault positioning method, device and equipment based on target space-time diagram neural network, medium and product

Abstract

The invention discloses a power distribution network fault positioning method, device and equipment based on a target space-time diagram neural network, a medium and a product. The method comprises the following steps: acquiring a spatial connection state matrix of each node in the power distribution network and voltage data of each node in a preset time period; reconstructing the voltage data of each node in the power distribution network in a preset time period to obtain reconstructed voltage data of each node; determining a similarity coefficient matrix among the nodes according to the reconstruction voltage data of each node; inputting the space connection state matrix of each node in the power distribution network, the reconstruction voltage data of each node and the similarity coefficient matrix between the nodes into a target space-time diagram neural network to obtain a fault state of each node; and determining the fault section in the power distribution network according to the fault state of each node in the power distribution network, and through the technical scheme of the invention, the accuracy and efficiency of power distribution network fault positioning can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of communication technologies, and in particular, to a method, device, equipment, medium, and product for power distribution network fault location based on a target spatio-temporal graph neural network. Background Art

[0002] The power supply reliability of the power distribution network is closely related to the power consumption quality of users. Accurately and quickly locating faults is of great significance for ensuring power supply reliability and the safe operation of the power distribution network.

[0003] The existing power distribution network fault location methods are mainly divided into: traditional methods and optimization algorithms. The traditional power distribution network fault location methods include: impedance method, traveling wave method, and matrix method. Although the traditional fault ranging methods have simple principles and fast calculation speeds, they have poor applicability and low fault tolerance in the power distribution network fault location after the access of new energy; the optimization algorithm will have redundant iterations near the end of the calculation. Therefore, when using the optimization algorithm for fault location, there are problems of low accuracy and low solution efficiency. Summary of the Invention

[0004] The embodiments of the present invention provide a method, device, equipment, medium, and product for power distribution network fault location based on a target spatio-temporal graph neural network to improve the accuracy and efficiency of power distribution network fault location.

[0005] According to one aspect of the present invention, there is provided a method for power distribution network fault location based on a target spatio-temporal graph neural network, including:

[0006] Obtaining the spatial connection state matrix of each node in the power distribution network and the voltage data of each node within a preset time period;

[0007] Reconstructing the voltage data of each node in the power distribution network within the preset time period to obtain the reconstructed voltage data of each node;

[0008] Determining the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node;

[0009] Inputting the spatial connection state matrix of each node in the power distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into the target spatio-temporal graph neural network to obtain the fault state of each node;

[0010] Determining the fault section in the power distribution network according to the fault state of each node in the power distribution network.

[0011] According to another aspect of the present invention, there is provided a power distribution network fault location device based on a target spatio-temporal graph neural network. The power distribution network fault location device based on a target spatio-temporal graph neural network includes:

[0012] A voltage data acquisition module, configured to acquire the spatial connection status matrix of each node in the distribution network and the voltage data of each node within a preset time period;

[0013] A reconstructed voltage data determination module, configured to reconstruct the voltage data of each node in the distribution network within a preset time period to obtain the reconstructed voltage data of each node;

[0014] A similarity coefficient matrix determination module, configured to determine the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node;

[0015] A node fault status determination module, configured to input the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into a target spatio-temporal graph neural network to obtain the fault status of each node;

[0016] A fault section determination module, configured to determine the fault section in the distribution network according to the fault status of each node in the distribution network.

[0017] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network fault location method based on the target spatio-temporal graph neural network according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the distribution network fault location method based on the target spatio-temporal graph neural network according to any embodiment of the present invention when executed by a processor.

[0022] According to another aspect of the present invention, there is provided a computer program product, and the computer program implements the distribution network fault location method based on the target spatio-temporal graph neural network as described in any one of the embodiments of the present invention when executed by a processor.

[0023] In an embodiment of the present invention, first, the voltage data of each node in the distribution network within a preset time period is reconstructed to obtain the reconstructed voltage data of each node. The main features related to the distribution network fault in the voltage data can be extracted through the reconstructed voltage data. Then, the spatial connection state matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes are input into the target spatio-temporal graph neural network to obtain the fault states of each node. According to the fault states of each node in the distribution network, the fault section in the distribution network is determined. It can maximize the utilization of spatio-temporal information through the target spatio-temporal graph neural network, extract the fault location features, and solve the problems of poor applicability, low fault tolerance, low accuracy, and long positioning time of the current fault location method in the active distribution network. Furthermore, more accurate and faster fault section location is realized. A fast and accurate fault location technology can effectively shorten the fault troubleshooting time of the distribution network, reduce the power outage duration, and is of great significance for the safe and reliable operation of the power distribution system.

[0024] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 is a flowchart of a distribution network fault location method based on a target spatio-temporal graph neural network in an embodiment of the present invention;

[0027] Figure 2 is a schematic structural diagram of a time-domain convolutional layer in an embodiment of the present invention;

[0028] Figure 3 is a schematic structural diagram of a distribution network fault location device based on a target spatio-temporal graph neural network in an embodiment of the present invention;

[0029] Figure 4 is a schematic structural diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solution in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0033] Embodiment 1

[0034] Figure 1 It is a flowchart of a method for fault location of a distribution network based on a target spatio-temporal graph neural network provided by an embodiment of the present invention. This embodiment is applicable to the situation of fault location of a distribution network. This method can be executed by a distribution network fault location device based on a target spatio-temporal graph neural network in the embodiments of the present invention. The device can be implemented in a software and / or hardware manner, such as Figure 1 As shown, the method specifically includes the following steps:

[0035] S110, obtain the spatial connection state matrix of each node in the distribution network and the voltage data of each node within a preset time period.

[0036] In this embodiment, the nodes in the distribution network include: monitoring nodes of substations, switchgear stations, distribution substations, generators, loads, and other control components, etc.

[0037] In this embodiment, the size of the spatial connection status matrix of each node in the distribution network is N×N, where N is the total number of nodes in the distribution network. The spatial connection status matrix of each node in the distribution network is used to characterize the control connection status between each node in the distribution network. For example, when node i and node j are connected, the corresponding element (A i , A j ) of the matrix is 1, otherwise it is 0.

[0038] In this embodiment, the preset time period can be a preset time period, and the embodiment of the present invention does not limit the length of the preset time period.

[0039] In this embodiment, the method for obtaining the voltage data of each node in the distribution network within the preset time period can be: obtaining the voltage data of each node in the distribution network at each moment within the preset time period.

[0040] S120, reconstruct the voltage data of each node in the distribution network within the preset time period to obtain the reconstructed voltage data of each node.

[0041] In this embodiment, the reconstructed voltage data of the node includes: a residual term and at least one order of intrinsic mode function.

[0042] In this embodiment, the method for reconstructing the voltage data of each node in the distribution network within the preset time period to obtain the reconstructed voltage data of each node can be: decomposing the voltage data of the node within the preset time period to obtain multiple orders of intrinsic mode functions and a residual term; screening each order of intrinsic mode function based on the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within the preset time period to obtain the target intrinsic mode function; reconstructing the voltage data based on the residual term and the target intrinsic mode function to obtain the reconstructed voltage data of the node.

[0043] Optionally, reconstructing the voltage data of each node in the distribution network within the preset time period to obtain the reconstructed voltage data of each node includes:

[0044] Performing a reconstruction operation on the voltage data of each node within the preset time period to obtain the reconstructed voltage data of each node.

[0045] In this embodiment, the reconstruction operation includes: decomposing the voltage data of the node within the preset time period to obtain multiple orders of intrinsic mode functions and a residual term; obtaining the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within the preset time period; screening each order of intrinsic mode function based on the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within the preset time period to obtain the target intrinsic mode function; reconstructing the voltage data based on the residual term and the target intrinsic mode function to obtain the reconstructed voltage data of the node.

[0046] In this embodiment, the method of decomposing the voltage data of the decomposition node within a preset time period to obtain multi-order intrinsic mode functions and a residual term can be: decomposing the voltage data into multi-order intrinsic mode functions through improved complete ensemble empirical mode decomposition with adaptive noise to reflect the local characteristics of the voltage data in each frequency range. The decomposed voltage data can be expressed as the superposition of multi-order intrinsic mode functions and a residual term. For example, it can be:

[0047]

[0048] where U(t) is the voltage data of the node within the preset time period, is the -th order intrinsic mode function, and R(t) is the residual term.

[0049] In this embodiment, the method of obtaining the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within the preset time period can be: obtaining the covariance operator between each order of intrinsic mode function and the voltage data of the node within the preset time period; obtaining the standard deviation of each order of intrinsic mode function and the standard deviation of the voltage data of the node within the preset time period; and determining the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within the preset time period according to the covariance operator, the standard deviation of each order of intrinsic mode function, and the standard deviation of the voltage data of the node within the preset time period.

[0050] In this embodiment, the method of screening each order of intrinsic mode function based on the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within the preset time period to obtain the target intrinsic mode function can be: determining the intrinsic mode function with a correlation coefficient greater than or equal to the correlation coefficient threshold as the target intrinsic mode function; or, determining the intrinsic mode function with the largest correlation coefficient as the target intrinsic mode function; or, if all correlation coefficients are less than the correlation coefficient threshold, determining the intrinsic mode function with the largest correlation coefficient as the target intrinsic mode function.

[0051] In this embodiment, the correlation coefficient threshold can be a preset correlation coefficient. For example, the correlation coefficient threshold can be 0.2.

[0052] In this embodiment, the method of reconstructing the voltage data based on the residual term and the target intrinsic mode function to obtain the reconstructed voltage data of the node can be: the reconstructed voltage data formula is:

[0053] U new (t) = ∑E new (t) + R(t);

[0054] In this embodiment, U new (t) is the reconstructed voltage data, and E new(t) represents the target intrinsic mode functions with all correlation coefficients greater than the correlation coefficient threshold, and R(t) is the residual term. It should be noted that if there are multiple target intrinsic mode functions with correlation coefficients greater than the correlation coefficient threshold, the sum of the multiple target intrinsic mode functions is added to the residual term to obtain the reconstructed voltage data.

[0055] The technical solution provided in this embodiment can better extract the amplitude characteristics of the fault voltage data by reconstructing the voltage data. Compared with the original voltage data, the reconstructed voltage data has more obvious fault information.

[0056] Optionally, obtaining the correlation coefficients of each order of intrinsic mode functions and the voltage data of the node within a preset time period includes:

[0057] Obtaining the covariance operator of each order of intrinsic mode functions and the voltage data of the node within a preset time period.

[0058] In this embodiment, the method for obtaining the covariance operator of each order of intrinsic mode functions and the voltage data of the node within a preset time period can be: through the covariance operator function, calculate the covariance operator of each order of intrinsic mode functions and the voltage data of the node within a preset time period.

[0059] Obtain the standard deviation of each order of intrinsic mode functions and the standard deviation of the voltage data of the node within a preset time period.

[0060] According to the covariance operator, the standard deviation of each order of intrinsic mode functions, and the standard deviation of the voltage data of the node within a preset time period, determine the correlation coefficients of each order of intrinsic mode functions and the voltage data of the node within a preset time period.

[0061] In this embodiment, the method for determining the correlation coefficients of each order of intrinsic mode functions and the voltage data of the node within a preset time period according to the covariance operator, the standard deviation of each order of intrinsic mode functions, and the standard deviation of the voltage data of the node within a preset time period can be: according to the covariance operator, the standard deviation of each order of intrinsic mode functions, the standard deviation of the voltage data of the node within a preset time period, and the first formula, determine the correlation coefficients of each order of intrinsic mode functions and the voltage data of the node within a preset time period; the first formula is as follows:

[0062]

[0063] In this embodiment, is the order correlation coefficient of the intrinsic mode function and the voltage data of the node within a preset time period, cov(.) is the covariance operator function, and σ U respectively represent and the standard deviation of U(t).

[0064] In this embodiment, the correlation coefficient can be the Pearson correlation coefficient. The Pearson correlation coefficient is used to measure the linear relationship between two variables.

[0065] The technical solution provided in this embodiment uses the Pearson correlation coefficient to select the intrinsic mode functions with strong correlation with the original voltage data for voltage data reconstruction, so as to retain the main fault characteristics of the voltage data.

[0066] S130. Determine the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node.

[0067] In this embodiment, the method for determining the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node can be: determine the mean value of the reconstructed voltages of each item of each node according to the multiple reconstructed voltages of each node corresponding to each time point; determine the similarity coefficient matrix between nodes according to the multiple reconstructed voltages of each node corresponding to each time point and the mean value of the reconstructed voltages of each item of each node.

[0068] Optionally, the reconstructed voltage data of the node includes: multiple reconstructed voltages of each node corresponding to each time point;

[0069] Determining the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node includes:

[0070] Determine the mean value of the reconstructed voltages of each item of each node according to the multiple reconstructed voltages of each node corresponding to each time point;

[0071] Determine the similarity coefficient matrix between nodes according to the multiple reconstructed voltages of each node corresponding to each time point and the mean value of the reconstructed voltages of each item of each node.

[0072] In this embodiment, the method for determining the similarity coefficient matrix between nodes according to the multiple reconstructed voltages of each node corresponding to each time point and the mean value of the reconstructed voltages of each item of each node can be: determine the product of the deviations and the product of the squared deviations of each node according to the multiple reconstructed voltages of each node corresponding to each time point and the mean value of the reconstructed voltages of each item of each node; determine the similarity coefficient matrix between nodes according to the product of the deviations and the product of the squared deviations of each node.

[0073] In this embodiment, the method for determining the similarity coefficient matrix between nodes according to the multiple reconstructed voltages of each node corresponding to each time point and the mean value of the reconstructed voltages of each item of each node can be: determine the similarity coefficient matrix between nodes according to the multiple reconstructed voltages of each node corresponding to each time point, the mean value of the reconstructed voltages of each item of each node and the second formula, and the second formula is:

[0074]

[0075] In this embodiment, eij is the similarity coefficient between node i and node j; X i (p, q) represents the matrix X n The reconstructed voltage data of the p-th phase (p = 1, 2, 3 corresponding to phases A, B, and C respectively) of node i corresponding to the q-th time point (q = 1, …, T, T is the preset time period) in is the mean matrix of X i of X j (p, q) represents the matrix X n The reconstructed voltage data of the p-th phase (p = 1, 2, 3 corresponding to phases A, B, and C respectively) of node j corresponding to the q-th time point (q = 1, …, T, T is the preset time period) in is the mean matrix of X j The matrix X n = [U a , U b , U c , n is the node number, and U a is the reconstructed voltage of phase A of each node within the preset time period, and U b is the reconstructed voltage of phase B of each node within the preset time period, and U c is the reconstructed voltage of phase C of each node within the preset time period.

[0076] S140, input the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into the target spatio-temporal graph neural network to obtain the fault status of each node.

[0077] In this embodiment, the way to input the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into the target spatio-temporal graph neural network to obtain the fault status of each node can be: construct graph data according to the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes; input the graph data into the target spatio-temporal graph neural network to obtain the fault status of each node.

[0078] In this embodiment, components such as generators and loads in the distribution network are used as nodes, and the connecting lines between them are used as edges to form the topological structure of the distribution network. According to the topological structure of the distribution network and the reconstructed voltage data of the nodes, graph data G{X, E, A} is constructed, where X is a matrix composed of the reconstructed voltage data of each node; E is a matrix composed of the similarity coefficients between nodes; A is a matrix composed of the spatial connection status of each node.

[0079] In this embodiment, the target spatio-temporal graph neural network is obtained by iteratively training the neural network to be trained with the target sample set.

[0080] In this embodiment, the target spatio-temporal graph neural network can be an improved spatio-temporal graph neural network. The target spatio-temporal graph neural network sequentially includes, from input to output: an attention module, a spatio-temporal convolution module, and an output module.

[0081] In this embodiment, a graph data is constructed by combining the spatial connection state matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes. It can maximize the reflection of spatio-temporal information of the data during data construction, which is beneficial to improving the ability of the target spatio-temporal graph neural network to cope with the variable and complex topological structure of the active distribution network.

[0082] Optionally, the target spatio-temporal graph neural network sequentially includes, from input to output: an attention module, a spatio-temporal convolution module, and an output module.

[0083] Input the spatial connection state matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into the target spatio-temporal graph neural network to obtain the fault state of each node, including:

[0084] Input the reconstructed voltage data of each node into the attention module to obtain the initial feature matrix of each node.

[0085] In this embodiment, the attention module sequentially includes, from the input to the output direction: a single-layer feedforward neural sub-network and a non-linear activation layer.

[0086] In this embodiment, inputting the reconstructed voltage data of each node into the attention module to obtain the initial feature matrix of each node includes: inputting the reconstructed voltage data of each node into the single-layer feedforward neural sub-network to obtain the attention coefficients between each node and all adjacent nodes; inputting the attention coefficients between each node and all adjacent nodes and the reconstructed voltage data of each node into the non-linear activation layer to obtain the initial feature matrix of each node.

[0087] Input the initial feature matrix of each node, the similarity coefficient matrix between nodes, and the spatial connection state matrix of each node into the spatio-temporal convolution module to obtain the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes.

[0088] In this embodiment, the spatio-temporal convolution module sequentially includes, from the input to the output direction: a time-domain convolution layer and a space-domain convolution layer. It should be noted that the method of inputting the initial feature matrix of each node, the similarity coefficient matrix between nodes, and the space connection state matrix of each node into the spatio-temporal convolution module to obtain the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes can be: inputting the initial feature matrix of each node and the similarity coefficient matrix between nodes into the time-domain convolution layer to obtain the time-domain feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes; inputting the time-domain feature matrix of each node and the space connection state matrix of each node into the space-domain convolution layer to obtain the voltage feature matrix of each node.

[0089] Input the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes into the output module to obtain the fault state of each node.

[0090] In this embodiment, the output module sequentially includes, from the input to the output direction: a fully connected layer and an activation layer. The method of inputting the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes into the output module to obtain the fault state of each node can be: inputting the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes into the fully connected layer to obtain a target feature matrix, inputting the target feature matrix into the activation layer to obtain the node fault index of each node, and determining the fault state of each node according to the node fault index of each node.

[0091] In this embodiment, the output expression of node i is:

[0092]

[0093] In this embodiment, δ Re (·) is an activation function, for example, it can be a Rectified Linear Unit (ReLU) activation function, δ S (·) is a sigmoid function, and both ω1 and ω2 are coefficient matrices in the fully connected layer. is the predicted fault state of node i. indicates that there is a fault in the branch where node i is located. indicates that the branch where node i is located is in a normal working state.

[0094] Optionally, the attention module sequentially includes, from the input to the output direction: a single-layer feedforward neural sub-network and a non-linear activation layer.

[0095] Inputting the reconstructed voltage data of each node into the attention module to obtain the initial feature matrix of each node includes:

[0096] Input the reconstructed voltage data of each node into the single-layer feedforward neural sub-network to obtain the attention coefficients between each node and all its adjacent nodes.

[0097] In this embodiment, the single-layer feedforward neural sub-network performs a non-linear transformation on the input features, mapping them to a new feature space, enabling the target spatio-temporal graph neural network to capture more complex feature relationships and enhancing the feature representation ability. The single-layer feedforward neural sub-network generally includes: two fully connected layers and a non-linear activation layer, with the non-linear activation layer in the middle of the two fully connected layers.

[0098] In this embodiment, in the attention module, by assigning different weights to the input, the importance of different elements is distinguished to extract more crucial information, achieving a better effect. In this embodiment, a single-layer feedforward neural sub-network is selected to calculate the attention coefficients between node i and all adjacent nodes j.

[0099] In this embodiment, the way to input the reconstructed voltage data of each node into the single-layer feedforward neural sub-network to obtain the attention coefficients between each node and all its adjacent nodes can be: input the reconstructed voltage data of each node into the single-layer feedforward neural sub-network to obtain the attention coefficients between nodes; according to the attention coefficients between nodes and the third formula, calculate the attention coefficients between each node and all its adjacent nodes. The third formula is:

[0100] a ij = ∑exp(y i,j );

[0101] In this embodiment, a ij is the attention coefficient between node i and all adjacent nodes j;

[0102]

[0103] In this embodiment, a ij ' is the normalized attention coefficient between node i and all adjacent nodes j, y i,j is the attention coefficient between node i and node j, and ∑exp(y i,j ) is the attention coefficient between node i and all adjacent nodes j.

[0104] Input the attention coefficients between each node and all its adjacent nodes and the reconstructed voltage data of each node into the non-linear activation layer to obtain the initial feature matrix of each node.

[0105] In this embodiment, the manner of inputting the attention coefficients between each node and all adjacent nodes and the reconstructed voltage data of each node into the non-linear activation layer to obtain the initial feature matrix of each node may be: based on the non-linear activation layer, combining the attention coefficients between each node and all adjacent nodes and the reconstructed voltage data of each node to obtain the initial feature matrix of each node.

[0106] In this embodiment, the target spatio-temporal graph neural network includes an attention module, a spatio-temporal convolution module, and an output module. The modules are connected by a ReLU activation function. The attention module can enable more important nodes to obtain higher attention weights, thereby achieving better learning effects. In the attention module, by assigning different weights to the inputs, the importance of different elements is distinguished to extract more critical information. The attention module in the target spatio-temporal graph neural network can better integrate the correlation between features into the target spatio-temporal graph neural network.

[0107] Optionally, the spatio-temporal convolution module sequentially includes, from the input to the output direction: a time-domain convolution layer and a space convolution layer.

[0108] Inputting the initial feature matrix of each node, the similarity coefficient matrix between nodes, and the spatial connection state matrix of each node into the spatio-temporal convolution module to obtain the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes includes:

[0109] Inputting the initial feature matrix of each node and the similarity coefficient matrix between nodes into the time-domain convolution layer to obtain the time-domain feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes.

[0110] In this embodiment, the structure of the time-domain convolution layer is as Figure 2 shown. The time-domain convolution layer screens the input features by adding a gated linear unit in the convolutional neural network, and processes the initial feature matrix of each node and the similarity coefficient matrix between nodes in parallel;

[0111] The convolution process is shown in the following formula:

[0112] X l+1 =η(X l );

[0113]

[0114] In this embodiment, X l is the initial feature matrix of each node input to the l-th layer of the time-domain convolution layer, and E l is the similarity coefficient matrix of each node input to the l-th layer of the time-domain convolution layer; η(·) and are two one-dimensional convolution kernel functions, and η(·) is used to extract the time-domain features of the initial feature matrix of each node. is used to extract the time-domain features of the similarity coefficient matrix of each node; δ S (·) is the sigmoid activation function. represents element-wise multiplication.

[0115] It should be noted that when a fault occurs in the line, the voltage change is the main fault feature. In contrast, the similarity coefficient between nodes is not an intuitive manifestation of the fault and can be used as a secondary fault feature.

[0116] Input the time-domain feature matrix of each node and the spatial connection state matrix of each node into the spatial convolution layer to obtain the voltage feature matrix of each node.

[0117] In this embodiment, the voltage feature matrix of each node is a feature matrix after fusing spatial information.

[0118] In this embodiment, the spatial convolution layer strengthens the fault information based on the spatial topology information of the graph data, enabling the target spatio-temporal graph neural network to exhibit high generalization in different topological scenarios. The spatial convolution layer combines the spatial information in the spatial connection state matrix of each node in the graph data and extracts spatial features through spectral graph convolution based on the principle of graph Fourier transform.

[0119] Optionally, the training process of the target spatio-temporal graph neural network includes:

[0120] Obtain a target sample set.

[0121] In this embodiment, the target sample set includes: training samples and the historical fault states of each node corresponding to the training samples. The training samples include: the historical voltage data of each node in the distribution network and the historical spatial connection state matrix of each node in the distribution network.

[0122] In this embodiment, the historical voltage data of each node in the distribution network can be the historical voltage data obtained in a pre-acquired period of time. The historical spatial connection state matrix of each node in the distribution network can be determined according to the historical topological structure of the distribution network. It should be noted that the acquisition time of the historical voltage data of each node in the distribution network and the historical spatial connection state matrix of each node in the distribution network is the same. That is to say, if the acquisition time of the historical voltage data of each node in the distribution network is June 2 of the year before last, then the acquisition time of the historical spatial connection state matrix of each node in the distribution network should also be June 2 of the year before last. This is only an example and does not limit the specific acquisition time.

[0123] Reconstruct based on the historical voltage data of each node in the distribution network to obtain the reconstructed voltage data samples of each node.

[0124] In this embodiment, the method for reconstructing the historical voltage data of each node may be the same as the method for reconstructing the voltage data of each node, which will not be elaborated here.

[0125] Determine a similarity coefficient matrix sample between nodes according to the reconstructed voltage data samples of the nodes.

[0126] In this embodiment, the method for determining a similarity coefficient matrix sample between nodes according to the reconstructed voltage data samples of the nodes is the same as the method for determining a similarity coefficient matrix between nodes according to the reconstructed voltage data of the nodes, which will not be elaborated here.

[0127] Input the similarity coefficient matrix sample between nodes, the historical spatial connection status of each node in the distribution network, and the reconstructed voltage data samples of the nodes into the neural network to be trained, and obtain the predicted fault status of each node.

[0128] In this embodiment, the predicted fault status of each node may be the node fault index predicted for each node.

[0129] In this embodiment, the neural network to be trained sequentially includes, from input to output: a to-be-trained attention module, a to-be-trained spatio-temporal convolution module, and a to-be-trained output module. The to-be-trained attention module sequentially includes, from input to output direction: a to-be-trained single-layer feedforward neural sub-network and a to-be-trained non-linear activation layer; the to-be-trained spatio-temporal convolution module sequentially includes, from input to output direction: a to-be-trained time-domain convolution layer and a to-be-trained space convolution layer.

[0130] Train the parameters of the neural network to be trained according to the difference between the predicted fault status of each node and the historical fault status of each node corresponding to the training sample.

[0131] In this embodiment, the method for training the parameters of the neural network to be trained according to the difference between the predicted fault status of each node and the historical fault status of each node corresponding to the training sample may be: training the parameters of the neural network to be trained according to the predicted fault status of the nodes, the historical fault status of each node corresponding to the training sample, and a loss function; the loss function is:

[0132]

[0133] In this embodiment, Y is the actual fault status matrix of the nodes, is the predicted fault status matrix of the nodes, y i is the actual fault status of node i, is the predicted fault status of node i, and N is the total number of nodes.

[0134] S150. Determine the fault section in the distribution network according to the fault status of each node in the distribution network.

[0135] In this embodiment, the method for determining the fault section in the distribution network according to the fault status of each node in the distribution network can be: determine the fault section in the distribution network according to the location information of the nodes in the fault status in the distribution network.

[0136] In a specific example, obtain the node three-phase voltage signals in the historical fault data of the distribution network, decompose each node voltage signal using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), and then reconstruct the voltage signal according to the correlation between the decomposed signal and the original signal. Calculate the similarity coefficient matrix between nodes, generate the spatial connection status matrix of each node in the distribution network according to the distribution network topology structure, and combine the reconstructed voltage signals of each node to construct graph data. Divide all the fault samples in the graph data into a training set and a test set according to a certain proportion. Build the neural network to be trained, and set model parameters such as the input and output dimensions, learning rate, and number of iterations of each layer according to actual requirements. Convert the fault location problem into a multi-label classification problem, and use a multi-label classification loss function to train the model. First, evaluate the neural network to be trained in the test set, and select the neural network with the highest accuracy as the target spatio-temporal graph neural network for application. When applying actual fault identification, obtain the spatial connection status matrix of each node in the distribution network and the voltage data of each node within a preset time period, and after data processing, input them into the target spatio-temporal graph neural network, and determine the fault section according to the output node fault index.

[0137] In another specific example, the fault location problem can be modeled as a multi-label classification problem about nodes, that is, establish a mapping relationship, and classify the graph data according to the node numbers where the fault branches are located, as shown in the following formula:

[0138] Y = f(X, E, A);

[0139] In this embodiment, Y = [y1, y2, y3,..., y n is the fault status of each node. If there is a fault, y n is 1, otherwise it is 0. The fault section can be determined according to the node status information. n is the node number, X is the matrix composed of the reconstructed voltage data of each node; E is the matrix composed of the similarity coefficients between nodes; A is the matrix composed of the spatial connection status of each node.

[0140] The technical solution provided by the embodiments of the present invention has high generalization in different topological scenarios; at the same time, it can maximize the extraction of the spatio-temporal data information characteristics of the distribution network, and improve the efficiency and accuracy of fault location under different fault conditions and noise interference environments.

[0141] In the technical solution of this embodiment, first, the voltage data of each node in the distribution network within a preset time period is reconstructed to obtain the reconstructed voltage data of each node. Through the reconstructed voltage data, the main features related to the distribution network fault in the voltage data can be extracted. Then, the spatial connection state matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes are input into the target spatio-temporal graph neural network to obtain the fault state of each node; according to the fault state of each node in the distribution network, the fault section in the distribution network is determined. It can maximize the utilization of spatio-temporal information through the target spatio-temporal graph neural network, extract the fault location characteristics, and solve the problems of poor applicability, low fault tolerance, low accuracy, and long positioning time of the current fault location method in the active distribution network. Furthermore, more accurate and faster fault section location can be realized. The fast and accurate fault location technology can effectively shorten the fault troubleshooting time of the distribution network, reduce the power outage duration, and is of great significance to the safe and reliable operation of the distribution system.

[0142] Embodiment Two

[0143] Figure 3 It is a schematic structural diagram of a distribution network fault location device based on a target spatio-temporal graph neural network provided by the embodiments of the present invention. This embodiment is applicable to the situation of distribution network fault location. The device can be implemented in software and / or hardware, and the device can be integrated in any device that provides the function of distribution network fault location, such as Figure 3 As shown, the distribution network fault location device based on the target spatio-temporal graph neural network specifically includes: a voltage data acquisition module 310, a reconstructed voltage data determination module 320, a similarity coefficient matrix determination module 330, a node fault state determination module 340, and a fault section determination module 350.

[0144] Among them, the voltage data acquisition module is used to acquire the spatial connection state matrix of each node in the distribution network and the voltage data of each node within a preset time period;

[0145] The reconstructed voltage data determination module is used to reconstruct the voltage data of each node in the distribution network within a preset time period to obtain the reconstructed voltage data of each node;

[0146] The similarity coefficient matrix determination module is used to determine the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node;

[0147] A fault status determination module for nodes, which is configured to input the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into a target spatio-temporal graph neural network to obtain the fault status of each node;

[0148] A fault section determination module, which is configured to determine the fault section in the distribution network according to the fault status of each node in the distribution network.

[0149] The above product can execute the method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0150] Embodiment III

[0151] Figure 4 The structural schematic diagram of an electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0152] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0153] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0154] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the distribution network fault location method based on the target spatio-temporal graph neural network.

[0155] In some embodiments, the distribution network fault location method based on the target spatio-temporal graph neural network can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the distribution network fault location method based on the target spatio-temporal graph neural network described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the distribution network fault location method based on the target spatio-temporal graph neural network in any other suitable way (e.g., by means of firmware).

[0156] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] A computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0158] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0159] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0160] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0161] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0162] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0163] An embodiment of the present invention also provides a computer program product, including a computer program which, when executed by a processor, implements the distribution network fault location method based on a target spatio-temporal graph neural network according to any embodiment of the present invention.

[0164] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0165] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for fault location in a distribution network based on a target spatio-temporal graph neural network, characterized in that, Including: Obtain the spatial connection status matrix of each node in the distribution network and the voltage data of each node within a preset time period; Reconstruct the voltage data of each node in the distribution network within a preset time period to obtain the reconstructed voltage data of each node; Determine the similarity coefficient matrix between nodes according to the reconstructed voltage data of each node; Input the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into the target spatio-temporal graph neural network to obtain the fault status of each node; Determine the fault section in the distribution network according to the fault status of each node in the distribution network.

2. The method according to claim 1, characterized in that, Reconstruct the voltage data of each node in the distribution network within a preset time period to obtain the reconstructed voltage data of each node, including: Perform a reconstruction operation on the voltage data of each node within a preset time period to obtain the reconstructed voltage data of each node; The reconstruction operation includes: decomposing the voltage data of the node within a preset time period to obtain multi-order intrinsic mode functions and a residual term; Obtain the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within a preset time period; Screen each order of intrinsic mode function based on the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within a preset time period to obtain the target intrinsic mode function; Reconstruct the voltage data based on the residual term and the target intrinsic mode function to obtain the reconstructed voltage data of the node.

3. The method according to claim 2, characterized in that, Obtain the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within a preset time period, including: Obtain the covariance operator between each order of intrinsic mode function and the voltage data of the node within a preset time period; Obtain the standard deviation of each order of intrinsic mode function and the standard deviation of the voltage data of the node within a preset time period; Determine the correlation coefficient between each order of intrinsic mode function and the voltage data of the node within a preset time period according to the covariance operator, the standard deviation of each order of intrinsic mode function, and the standard deviation of the voltage data of the node within a preset time period.

4. The method according to claim 1, characterized in that, The target spatio-temporal graph neural network sequentially includes, from input to output: an attention module, a spatio-temporal convolution module, and an output module; Input the spatial connection status matrix of each node in the distribution network, the reconstructed voltage data of each node, and the similarity coefficient matrix between nodes into the target spatio-temporal graph neural network to obtain the fault status of each node, including: Input the reconstructed voltage data of each node into the attention module to obtain the initial feature matrix of each node; Input the initial feature matrix of each node, the similarity coefficient matrix between nodes, and the spatial connection status matrix of each node into the spatio-temporal convolution module to obtain the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes; Input the voltage feature matrix of each node and the time-domain feature matrix of the similarity coefficient between nodes into the output module to obtain the fault status of each node.

5. The method according to claim 4, wherein The attention module sequentially includes, from the input to output direction: a single-layer feedforward neural sub-network and a non-linear activation layer; Input the reconstructed voltage data of each node into the attention module to obtain the initial feature matrix of each node, including: Input the reconstructed voltage data of each node into the single-layer feedforward neural sub-network to obtain the attention coefficients between each node and all adjacent nodes; Input the attention coefficients between each of the nodes and all adjacent nodes and the reconstructed voltage data of each of the nodes into the non-linear activation layer to obtain the initial feature matrix of each node.

6. The method according to claim 4, characterized in that The spatio-temporal convolution module sequentially includes, from the input to the output direction: a time-domain convolution layer and a space-domain convolution layer; Input the initial feature matrix of each of the nodes, the similarity coefficient matrix between the nodes, and the spatial connection state matrix of each of the nodes into the spatio-temporal convolution module to obtain the voltage feature matrix of each of the nodes and the time-domain feature matrix of the similarity coefficients between the nodes, including: Input the initial feature matrix of each of the nodes and the similarity coefficient matrix between the nodes into the time-domain convolution layer to obtain the time-domain feature matrix of each of the nodes and the time-domain feature matrix of the similarity coefficients between the nodes; Input the time-domain feature matrix of each of the nodes and the spatial connection state matrix of each of the nodes into the space-domain convolution layer to obtain the voltage feature matrix of each of the nodes.

7. The method according to claim 1, characterized in that The training process of the target spatio-temporal graph neural network includes: Obtain a target sample set, where the target sample set includes: training samples and the historical fault states of each of the nodes corresponding to the training samples, and the training samples include: the historical voltage data of each of the nodes in the distribution network and the historical spatial connection state matrix of each of the nodes in the distribution network; Based on the historical voltage data of each of the nodes in the distribution network, perform reconstruction to obtain the reconstructed voltage data samples of each of the nodes; According to the reconstructed voltage data samples of each of the nodes, determine the similarity coefficient matrix sample between the nodes; Input the similarity coefficient matrix sample between the nodes, the historical spatial connection state of each of the nodes in the distribution network, and the reconstructed voltage data samples of each of the nodes into the neural network to be trained to obtain the predicted fault states of each of the nodes; Train the parameters of the neural network to be trained according to the difference between the predicted fault states of each of the nodes and the historical fault states of each of the nodes corresponding to the training samples.

8. The method according to claim 1, characterized in that, The reconstructed voltage data of the node includes: multiple reconstructed voltages of each of the nodes corresponding to each time point; According to the reconstructed voltage data of each of the nodes, determine the similarity coefficient matrix between the nodes, including: According to the multiple reconstructed voltages of each of the nodes corresponding to each time point, determine the mean value of the reconstructed voltages of each of the nodes; According to the multiple reconstructed voltages of each of the nodes corresponding to each time point and the mean value of the reconstructed voltages of each of the nodes, determine the similarity coefficient matrix between the nodes.

9. A distribution network fault location device based on a target spatio-temporal graph neural network, characterized in that, Including: A voltage data acquisition module, configured to acquire the spatial connection state matrix of each of the nodes in the distribution network and the voltage data of each of the nodes within a preset time period; A reconstructed voltage data determination module, configured to reconstruct the voltage data of each of the nodes in the distribution network within a preset time period to obtain the reconstructed voltage data of each of the nodes; A similarity coefficient matrix determination module, configured to determine the similarity coefficient matrix between the nodes according to the reconstructed voltage data of each of the nodes; A fault state determination module of the node, configured to input the spatial connection state matrix of each of the nodes in the distribution network, the reconstructed voltage data of each of the nodes, and the similarity coefficient matrix between the nodes into the target spatio-temporal graph neural network to obtain the fault states of each of the nodes; A fault section determination module, configured to determine the fault section in the distribution network according to the fault states of each of the nodes in the distribution network.

10. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution network fault location method based on the target spatio-temporal graph neural network according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the distribution network fault location method based on the target spatio-temporal graph neural network according to any one of claims 1-8 when executed.

12. A computer program product, characterized in that, The computer program product includes a computer program which, when executed by a processor, implements the distribution network fault location method based on the target spatio-temporal graph neural network according to any one of claims 1-8.

Images