Automatic partitioning method, device and equipment for power grid recovery after extreme disaster and medium

Abstract

The invention belongs to the technical field of power grid automatic partitioning, and particularly relates to an automatic partitioning method, device and equipment for power grid recovery after an extreme disaster and a medium, and the method comprises the steps: constructing a two-dimensional model of a region according to geographic information and meteorological information; taking a power supply building as a node in the two-dimensional model, and taking geographic information and meteorological information as attributes of the node; adding the fault condition information of the power distribution network into the attributes of the nodes to obtain a model after information fusion; clustering the nodes according to the attributes of the nodes based on the model after information fusion to obtain clusters; and taking nodes divided by each clustering center as nodes of the same region. According to the method, the power grid is automatically partitioned according to the type of the power distribution fault, rapid first-aid repair can be performed according to the type of the power distribution fault after partitioning, and the power grid recovery speed is high.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic power grid zoning, and particularly relates to a method, device, equipment and medium for automatic zoning of power grid restoration after extreme disasters. Background Art

[0002] In recent years, the occurrence frequency and intensity of extreme disasters have become more and more intense. The occurrence of various extreme disasters often brings various degrees of faults to the distribution network. As an extremely important resource in daily life, when a fault occurs in the local distribution network, in order to reduce its impact on people's normal life, it is a problem that needs to be quickly solved to restore power supply in a timely manner. However, the bearing capacity of extreme disasters in different regions is not the same, and the severity of the resulting distribution network faults is often also different.

[0003] At present, domestic and foreign scholars' research on the fault classification of distribution networks mainly focuses on fault location and diagnosis technologies, fault handling and restoration optimization, etc., and it is impossible to achieve the zoning of different types of distribution network faults after extreme disasters. Since there are various types of distribution network faults and different maintenance methods for different types of faults, the distribution network faults in the same region need to be repaired in multiple ways, resulting in slow power grid restoration and economic losses. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device, equipment and medium for automatic zoning of power grid restoration after extreme disasters, so as to solve the problem that there are multiple types of distribution network faults in the same region after zoning by the existing zoning method, which requires multiple repair methods and leads to slow power grid restoration in the background art.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions: In the first aspect of the present invention, a method for automatic zoning of power grid restoration after extreme disasters is provided, including: Constructing a two-dimensional model of the region according to geographical information and meteorological information; taking power supply buildings as nodes in the two-dimensional model, and taking geographical information and meteorological information as the attributes of the nodes; Adding the distribution network fault condition information to the attributes of the nodes to obtain a model after information fusion; Clustering the nodes based on the attributes of the nodes in the model after information fusion to obtain each cluster; taking the nodes divided by each cluster center as the nodes in the same region.

[0006] Preferably, in the step of constructing a two-dimensional model of the region according to geographical information and meteorological information, it includes: The geographical information is longitude and latitude; The meteorological information is the duration and intensity coefficient of extreme disasters endured by the power supply building in the past period of time.

[0007] Preferably, in the step of adding the distribution network fault condition information to the attributes of the nodes to obtain the information - fused model, it includes: The distribution network fault condition information is the types of distribution faults; the types of distribution faults include line break, two - phase short - circuit, and three - phase short - circuit.

[0008] Preferably, in the step of clustering the nodes according to the attributes of the nodes based on the information - fused model to obtain each cluster, the k - prototypes algorithm is used for clustering, which specifically includes: Preset the number of clusters; Set the value of k according to the preset number of clusters, and randomly select k nodes as the initial cluster centers; Calculate the distance from each node to each cluster center, and determine the clustering result of the current iteration according to the distance; Re - select the cluster centers according to the results of the previous iteration; After reaching the preset iteration termination condition, obtain the clustering result.

[0009] Preferably, in the step of obtaining the clustering result after reaching the preset iteration termination condition, the preset iteration termination condition is: The change between the new cluster center and the old cluster center is less than the convergence threshold.

[0010] Preferably, calculating the distance from each node to each cluster center specifically includes the following steps: For each node x i , x i = x i1 ,x i2 ,...,x im ,c i1 ,c i2 ,...,c in , where x im is the value of the node x i on the m - th numerical feature, c in is the value of the node x i on the n - th categorical feature; The numerical feature is the longitude and latitude data, and the distance between the node x i and each cluster center C j of the numerical feature is calculated according to the following formula:

[0011] In the formula, D num represents the distance of the numerical feature; m represents the number of numerical features; x ik represents the node x i at the k th numerical feature; represents the cluster center C j at the k th numerical feature; The category feature is the extreme disaster duration and intensity coefficient, and the type of distribution network fault. For each node x i , calculate according to the following formula x i the distance from each cluster center C j to the category feature:

[0012] In the formula, D cat represents the category feature distance; n represents the number of category features; c ik represents the node x i at the k th category feature; represents the cluster center C j at the k th category feature; δ represents the indicator function. When c ik = c jk δ = 0, otherwise δ = 1; Calculate the total distance from each node x i to each cluster center according to the following formula:

[0013] In the formula, D represents the total distance, α is the weight for balancing the numerical feature and the category feature, α ∈(0, 1).

[0014] Preferably, reselecting the cluster center according to the result of the previous round of iteration specifically includes the following steps: Update the cluster center of the numerical feature according to the following formula:

[0015] In the formula, represents the numerical feature of cluster j, C j represents the set of nodes in cluster j; | C j | represents the number of nodes in cluster j; Select the mode of the category feature according to the following formula:

[0016] In the formula, represents the category feature of cluster j, and mode represents calculating the category feature with the highest occurrence frequency; Judge whether the change of the cluster center is less than the convergence threshold according to the following formula, so as to decide whether to enter the next round of iteration:

[0017] In the formula, ε represents the convergence threshold, represents calculating the total distance between the new and old clusters. When the change of the cluster center is less than the convergence threshold, the iteration terminates.

[0018] Preferably, the extreme disaster duration and intensity coefficient μ includes high intensity, medium intensity or low intensity, where μ ∈(0, 0.3] belongs to low intensity, μ ∈(0.3, 0.6] belongs to medium intensity, μ ∈(0.6, 1) belongs to high intensity, μ corresponding to c ik .

[0019] In the second aspect of the present invention, an automatic power grid restoration and zoning device after an extreme disaster is provided, including: A construction module, which constructs a two-dimensional model of the region according to geographical information and meteorological information; uses power supply buildings as nodes in the two-dimensional model, and geographical information and meteorological information as attributes of the nodes; A fusion module, which adds the power distribution network fault condition information to the attributes of the nodes to obtain a model after information fusion; A zoning module, which clusters the nodes based on the attributes of the nodes in the model after information fusion to obtain each cluster; and regards the nodes divided by each cluster center as nodes in the same area.

[0020] In the third aspect of the present invention, an electronic device is provided, including a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement the automatic power grid restoration and zoning method after an extreme disaster.

[0021] In the fourth aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the automatic grid restoration and zoning method after extreme disasters as described above is implemented.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows: The power grid is automatically zoned according to the types of distribution faults. After zoning, it is possible to quickly repair according to the types of distribution faults, which has guiding significance for power companies to accurately divide the faulty power grid based on the criteria of clear power grid fault classification and disaster severity; prioritize the restoration of key areas or areas where fault types are concentrated, thereby improving the efficiency and effect of power grid restoration. An automatic grid restoration and zoning device, an electronic device, and a computer-readable storage medium provided by the present invention also solve the problems raised in the background art section. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The schematic diagrams in the specification forming a part of this application are used to provide a further understanding of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 is a schematic flow chart of an automatic grid restoration and zoning method after extreme disasters in Embodiment 1 of the present invention; Figure 2 is a specific implementation schematic diagram of an automatic grid restoration and zoning method after extreme disasters in Embodiment 1 of the present invention; Figure 3 is a node clustering diagram in Embodiment 1 of the present invention.

[0024] Figure 4 is a schematic diagram of an automatic grid restoration and zoning device after extreme disasters in Embodiment 2 of the present invention; Figure 5 is a schematic diagram of an electronic device in Embodiment 3 of the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS The present invention will be described in detail below with reference to the drawings and in combination with embodiments. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other.

[0025] The following detailed descriptions are all exemplary descriptions, aiming to provide further detailed descriptions of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. The terms used in the present invention are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0026] Embodiment 1 Figure 1The schematic diagram of the method flow of Embodiment 1 is given. Figure 2 The specific implementation flowchart of Embodiment 1 is given. An automatic zoning method for power grid restoration after extreme disasters includes the following steps: S1. Construct a two-dimensional model of the area according to geographical information and meteorological information; use power supply buildings as nodes in the two-dimensional model, and use geographical information and meteorological information as the attributes of the nodes. In this embodiment, geographical information is the direct object of power grid zoning, and meteorological information is the effective basis for the duration of power grid faults. Only automatic zoning for power grid restoration is carried out, so both are modeled on a two-dimensional plane.

[0027] The specific two-dimensional modeling of the area according to geographical information and meteorological information is as follows: Use all power supply buildings within the area as nodes, and model them based on geographical information system (GIS) with longitude and latitude as basic information combined with meteorological forecast results. Among them, meteorological information includes the duration and intensity of extreme disasters endured by all modeling objects within the area in the past period of time, and use power supply buildings as nodes.

[0028] S2. Add the information of the distribution network fault condition to the attributes of the nodes to obtain the model after information fusion. Affected by extreme disasters, the distribution network will have three types of faults. Although adjacent geographical locations experience the same extreme disasters, the fault types cannot be regarded as the same. Therefore, the distribution network faults occurring at each geographical location are added to the model as additional information. Limited by the multiplicity of power grid faults and the finiteness of power repair resources after extreme disasters, effectively and truly dividing the power grid faults into regions can greatly improve the repair efficiency when selecting power grid restoration strategies. Therefore, the distribution network faults are used as newly added node information, which further includes three situations: wire break, two-phase short circuit or three-phase short circuit. When calculating the distance for judging the similarity of nodes later, they represent three node attributes. If it exists, the corresponding attribute value is 1, otherwise it is 0.

[0029] S3. Cluster the nodes based on the attributes of the nodes in the model after information fusion to obtain each cluster; regard the nodes divided by each cluster center as the nodes in the same region.

[0030] The specific steps of using the K-prototypes algorithm to divide the area according to the distribution network faults in the model after information fusion are as follows: Step S11: Set the k value according to the actual usage situation, and randomly select k nodes as the initial cluster centers. Step S12: Calculate the distance from each node to each cluster center to obtain the clustering result of the current iteration. Step S13: Re-select the cluster centers according to the results of the previous iteration, and repeat Step S12.

[0031] In this embodiment, Step S12 includes the following steps: Step S21: For each node x i ( x i = x i1 , x i2 ,...,x im ,c i1 ,c i2 ,...,c in ), where x im is the value of node x i on the m-th numerical feature, where c in is the value of node x i on the n-th categorical feature. Calculate the distance between node x i and each cluster center C j for the numerical feature, and the numerical feature is longitude and latitude data: In the formula, D num represents the numerical feature distance; m represents the number of numerical features, i.e., longitude and latitude; x ik represents the value of node x i on the k -th numerical feature; represents the value of cluster center Cj on the k -th numerical feature; Step S22: Calculate the distance between node x i and each cluster center C j for the categorical feature, where the categorical feature is specifically the duration and intensity coefficient of extreme disasters and the types of distribution network faults:

[0032] In the formula, D catIndicates the category feature distance; n Indicates the number of category features, namely the extreme disaster duration and intensity coefficient, and three types of distribution network faults, a total of four; c ik Indicates a node x i At the k value of the category feature; Indicates the cluster center C j At the k value of the category feature; δ Indicates the indicator function. When c ik = c jk then δ = 0, otherwise δ = 1; Extreme disaster duration and intensity coefficient μ Includes high intensity, medium intensity or low intensity, where μ ∈(0, 0.3] belongs to low intensity, μ ∈(0.3, 0.6] belongs to medium intensity, μ ∈(0.6, 1) belongs to high intensity, μ Is equal to the corresponding one in the category features c ik； The types of distribution faults include line break, two-phase short circuit or three-phase short circuit. When it exists, the corresponding attribute value is 1, otherwise it is 0.

[0033] Step S23: Calculate the total distance from each node xi to each cluster center according to the following formula, and assign each node to the nearest cluster center C j : In the formula, D represents the total distance, α Is the weight for balancing numerical features and category features, α ∈(0, 1).

[0034] In this embodiment, step S13 includes the following steps:

[0035] Step S31: Update the cluster center of numerical features according to the following formula: In the formula, Represents the numerical feature of cluster j, C j Represents the set of nodes in cluster j; | C j | Represents the number of nodes in cluster j; Step S32: Select the mode of the categorical features according to the following formula:

[0036] In the formula, represents the categorical feature of cluster j, and mode represents calculating the categorical feature with the highest occurrence frequency; Step S33: Determine whether the change in the cluster center is less than the convergence threshold according to the following formula, so as to decide whether to enter the next iteration:

[0037] In the formula, ε represents the convergence threshold, represents calculating the total distance between the new and old clusters. When the change in the cluster center is less than the convergence threshold, the iteration terminates.

[0038] In this embodiment, furthermore, the regional division result of the entire area is specifically: The clustering result obtained after the K-prototypes algorithm exits is the final regional division result of the automatic power grid restoration sub-region.

[0039] Specifically, the value of k is 5 - 10; Preferably, the value of k is 7; In a specific embodiment, as Figure 2 shown: Establish a two-dimensional model based on meteorological information and geographical information; Establish the basic node information on the two-dimensional model; Add the distribution network fault conditions and perform node information fusion; Select the value of k; Randomly select k nodes and initialize them for the first iteration; Calculate the numerical feature distance from the node to the cluster center; Calculate the categorical feature distance from the node to the cluster center; Set the weight to calculate the total distance; Update the cluster centers of the numerical features and categorical features respectively; Judge the convergence of the cluster center; If the convergence is less than the convergence threshold, the iteration terminates and the classification result is output.

[0040] Simulation example: This embodiment analyzes a certain area in China, selects many power supply buildings as nodes, and sets the value of k to 7; Region 1 is a fault-free area, Region 2 is a low-intensity short-circuit area, Region 3 is a high-intensity two-phase open-circuit area, Region 4 is a medium-intensity short-circuit and three-phase open-circuit area, Region 5 is a low-intensity open-circuit area, Region 6 is a high-intensity two-phase open-circuit and three-phase open-circuit area, and Region 7 is a fault-free area. The specific node clustering diagram is as Figure 3 shown.

[0041] Example 2 As Figure 4 shown, based on the same inventive concept as the above embodiments, the present invention further provides an automatic zoning device for power grid restoration after extreme disasters, including: A construction module that constructs a two-dimensional model of the area according to geographical information and meteorological information; uses power supply buildings as nodes in the two-dimensional model, and geographical information and meteorological information as attributes of the nodes; A fusion module that adds power distribution network fault condition information to the attributes of the nodes to obtain a model after information fusion; A zoning module that clusters the nodes based on the attributes of the nodes in the model after information fusion to obtain each cluster; regards the nodes divided by each cluster center as nodes in the same area.

[0042] Example 3 As Figure 5 shown, the present invention further provides an electronic device 100 for implementing the automatic zoning method for power grid restoration after extreme disasters; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0043] The memory 101 can be used to store the computer program 103. The processor 102 realizes the steps of the automatic zoning method for power grid restoration after extreme disasters in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0044] The memory 101 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the electronic device 100 (such as audio data, etc.). In addition, the memory 101 can include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0045] At least one processor 102 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or the processor 102 may also be any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0046] The memory 101 in the electronic device 100 stores multiple instructions to implement an automatic zoning method for power grid restoration after extreme disasters. The processor 102 can execute the multiple instructions to achieve: Construct a two-dimensional model of the region based on geographical information and meteorological information; use the power supply buildings as nodes in the two-dimensional model, and use the geographical information and meteorological information as the attributes of the nodes; Add the distribution network fault condition information to the attributes of the nodes to obtain a model after information fusion; Cluster the nodes based on the attributes of the nodes in the model after information fusion to obtain each cluster; regard the nodes divided by each cluster center as the nodes in the same region.

[0047] Embodiment 4 If the modules / units integrated in the electronic device 100 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, and read-only memory (ROM, Read-Only Memory).

[0048] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, C D-ROM, optical storage, etc.).

[0049] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0050] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable devices provide steps for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0052] In the description of this specification, the descriptions referring to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for automatic zoning of power grid restoration after extreme disasters, characterized in that: include: Construct a two-dimensional model of the region based on geographic information and meteorological information; use power supply buildings as nodes in the two-dimensional model, and use geographic information and meteorological information as attributes of the nodes; Add the distribution network fault condition information to the node attributes to obtain the information fusion model; Based on the information fusion model, the nodes are clustered according to the attributes of the nodes to obtain clusters; the nodes divided by the centers of each cluster are regarded as nodes in the same area.

2. The method for automatic zoning of power grid restoration after extreme disasters according to claim 1 is characterized in that: The step of constructing a two-dimensional model of a region based on geographic information and meteorological information includes: Geographic information is longitude and latitude; Meteorological information is the duration and intensity coefficient of extreme disasters that power supply buildings have suffered in the past period of time.

3. The method for automatic zoning of power grid restoration after extreme disasters according to claim 2 is characterized in that: The step of adding the distribution network fault condition information to the node attributes to obtain the model after information fusion includes: The distribution network fault condition information is the type of distribution fault; the types of distribution faults include disconnection, two-phase short circuit and three-phase short circuit.

4. The method for automatic zoning of power grid restoration after extreme disasters according to claim 3 is characterized in that: The model based on information fusion clusters the nodes according to the attributes of the nodes, and in each clustering step, the k-prototypes algorithm is used for clustering, which specifically includes: Preset number of clusters; Set the k value according to the preset number of clusters, and randomly select k nodes as the initial cluster centers; Calculate the distance from each node to each cluster center, and determine the clustering result of the current iteration based on the distance; Reselect the cluster center based on the results of the previous iteration; After reaching the preset iteration termination condition, the clustering result is obtained.

5. The method for automatic zoning of power grid restoration after extreme disasters according to claim 4 is characterized in that: After reaching the preset iteration termination condition, in the step of obtaining the clustering result, the preset iteration termination condition is: The difference between the new cluster center and the old cluster center is less than the convergence threshold.

6. The method for automatic zoning of power grid restoration after extreme disasters according to claim 4 is characterized in that: Calculating the distance from each node to each cluster center specifically includes the following steps: For each node x i , x i =[ x i1 ,x i2 ,...,x im ,c i1 ,c i2 ,...,c in ],in x im For Node x i The value of the mth numerical feature, c in For Node x i The value of the n-th category feature; The numerical feature is the longitude and latitude data, and the node is calculated according to the following formula x i With each cluster center C j The distance of the numerical feature: In the formula, D num Represents the numerical feature distance; m Indicates the number of numerical features; x ik Represents a node x i In the k The value of a numerical feature; Represents the cluster center C j In the k The value of a numerical feature; The category characteristics are the duration and intensity coefficient of extreme disasters and the type of distribution network faults. x i , calculated according to the following formula x i With each cluster center C j The distance of the category feature: In the formula, D cat represents the category feature distance; n represents the number of category features; c ik Represents a node x i In the k The value of the categorical feature; Represents the cluster center C j In the k The value of the category feature; δ represents the indicator function. c ik = c jk When , δ=0, otherwise δ=1; Calculate each node according to the following formula x i The total distance to each cluster center: In the formula, D represents the total distance, α is the weight to balance the numerical features and categorical features, α ∈(0,1).

7. The method for automatic zoning of power grid restoration after extreme disasters according to claim 4 is characterized in that: Reselecting the cluster center based on the results of the previous iteration includes the following steps: Update the cluster center of the numerical feature according to the following formula: In the formula, represents the numerical feature of cluster j, C j represents the set of nodes in cluster j; | C j | represents the number of nodes in cluster j; The mode of the categorical feature is selected according to the following formula: In the formula, represents the category feature of cluster j, and mode represents the category feature with the highest frequency of calculation; According to the following formula, we can judge whether the change of cluster center is less than the convergence threshold, so as to decide whether to enter the next round of iteration: In the formula, ε represents the convergence threshold, It means calculating the total distance between the new and old clusters. When the change of the cluster center is less than the convergence threshold, the iteration terminates.

8. An automatic zoning device for power grid restoration after extreme disasters, characterized in that: include: A construction module constructs a two-dimensional model of the region based on geographic information and meteorological information; the power supply building is used as a node in the two-dimensional model, and the geographic information and meteorological information are used as attributes of the node; The fusion module adds the distribution network fault status information to the node attributes to obtain the information fusion model; The partitioning module clusters the nodes according to the attributes of the nodes based on the information fusion model to obtain clusters; the nodes divided by the centers of each cluster are regarded as nodes in the same area.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for automatic zoning of power grid restoration after extreme disasters as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the method for automatic zoning of power grid restoration after extreme disasters as described in any one of claims 1 to 7 is implemented.

Images