Power distribution network partitioning method and apparatus, computer device, and storage medium

Abstract

This application relates to a distribution network partitioning method, apparatus, computer equipment, and storage medium. The method includes: dividing each grid into multiple initial clusters based on the grid density of the load-centralized data samples corresponding to each planned area; determining a density partitioning factor based on the number of grids corresponding to the maximum, minimum, and target grid densities; determining the neighborhood radius of the initial clusters based on the density partitioning factor and the density waveforms corresponding to the initial clusters; determining the minimum number of sample points based on the number of peaks in the density waveforms corresponding to the initial clusters; and then partitioning the distribution network in the planned area according to the neighborhood radius and the minimum number of sample points of each initial cluster to obtain each distribution network partition. This eliminates the need for manually setting and adjusting the neighborhood radius and minimum number of sample points of the initial clusters, improving the accuracy of distribution network partitioning.

Description

Technical Field

[0001] This application relates to the field of power grid planning technology, and in particular to a distribution network zoning method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the large-scale integration of high-energy-density renewable energy sources such as wind and solar power into the power system, traditional power systems face enormous challenges. To ensure the safe and stable operation of the power grid, distribution network planning requires comprehensive consideration. Due to the random and intermittent nature of high-energy-density renewable energy, its power generation is difficult to predict, leading to more frequent and complex load changes, placing enormous pressure on distribution equipment and increasing the risk of failure. Therefore, it is necessary to plan and upgrade the traditional distribution network to adapt to the impact of high-energy-density renewable energy integration on grid operational stability. In the distribution network planning process, the division of planning areas is crucial and forms the basis for all subsequent planning work.

[0003] In traditional technologies, clustering algorithms such as K-means, PSO, and DBSCAN are typically used to classify distribution networks into categories such as load-intensive areas and load-short-peak areas based on their load characteristics.

[0004] However, the model parameters of the clustering algorithm usually need to be set and adjusted manually. Therefore, the current clustering algorithm has the problem of poor zoning effect when used to partition the power distribution network. Summary of the Invention

[0005] Therefore, it is necessary to provide a distribution network partitioning method, device, computer equipment, and storage medium that can generate model parameters for clustering algorithms based on the characteristics of the dataset itself, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for dividing a power distribution network. The method includes:

[0007] Based on the grid density of each grid, multiple initial clusters are obtained by dividing each grid into its corresponding load concentration data samples for the area to be planned.

[0008] The density partitioning factor is determined based on the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density; the target grid density includes grid densities greater than the preset grid density.

[0009] For each initial cluster, the neighborhood radius of the initial cluster is determined based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0010] The minimum number of sample points is determined based on the number of peaks in the density waveform corresponding to the initial cluster.

[0011] Based on the neighborhood radius and minimum number of sample points of each initial cluster, the power distribution network in the area to be planned is partitioned to obtain each power distribution network partition.

[0012] In one embodiment, determining the neighborhood radius of each initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster includes:

[0013] Determine a first straight line whose grid density is equal to the first density partition factor, and determine the first intersection point of the first straight line with the density waveform in the first direction corresponding to the initial cluster;

[0014] For each initial cluster, based on the first intersection point and the first zero-density interval of the density waveform in the first direction corresponding to the initial cluster, the first neighborhood radius in the first direction corresponding to the initial cluster is determined; the first zero-density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters;

[0015] Determine a second straight line whose grid density is equal to the second density partition factor, and determine a second intersection point of the second straight line with the density waveform in the second direction corresponding to the initial cluster;

[0016] For each initial cluster, based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster, the second neighborhood radius in the second direction corresponding to the initial cluster is determined; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster.

[0017] The neighborhood radius of the initial cluster is determined based on the first neighborhood radius and the second neighborhood radius.

[0018] In one embodiment, determining the first neighborhood radius in the first direction corresponding to the initial cluster based on the first intersection point and the first zero-density interval of the density waveform in the first direction corresponding to the initial cluster includes:

[0019] Based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster, the radius of the first right neighbor in the first direction corresponding to the initial cluster is determined.

[0020] Based on the x-coordinate of the leftmost first intersection point and the first zero-density interval before the initial cluster, the radius of the first left neighbor in the first direction corresponding to the initial cluster is determined.

[0021] The first neighborhood radius corresponding to the initial cluster in the first direction is determined based on the first left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the first direction.

[0022] In one embodiment, determining the second neighborhood radius in the second direction corresponding to the initial cluster based on the second intersection point and the second zero-density interval of the density waveform in the second direction corresponding to the initial cluster includes:

[0023] Based on the x-coordinate of the rightmost second intersection point and the second zero-density interval located after the initial cluster, the radius of the second right neighbor in the second direction corresponding to the initial cluster is determined.

[0024] Based on the x-coordinate of the leftmost intersection point and the second zero-density interval located before the initial cluster, the radius of the second left neighborhood in the second direction corresponding to the initial cluster is determined.

[0025] The second neighborhood radius corresponding to the initial cluster is determined based on the second left neighborhood radius and / or right neighborhood radius in the second direction.

[0026] In one embodiment, the method further includes:

[0027] For each distribution network zone, a distribution network zone planning scheme is obtained by planning the distribution network zone, and the cost of the distribution network zone planning scheme is determined.

[0028] For each distribution network zone, the scenarios within that distribution network zone are analyzed to determine the target scenarios for that distribution network zone; these target scenarios include atypical operating scenarios and / or typical operating scenarios.

[0029] Based on the cost of the power distribution network zoning plan and the target scenario, a feasibility analysis of the power distribution network zoning plan is conducted, and the analysis results are obtained.

[0030] In one embodiment, the feasibility analysis of the distribution network zoning plan is performed based on the cost of the distribution network zoning plan and the target scenario to obtain the analysis results, including:

[0031] Power flow calculations were performed on the target scenario to obtain the calculation results.

[0032] Based on the calculation results, a feasibility analysis of the power distribution network zoning plan was conducted to obtain the analysis results.

[0033] Secondly, this application also provides a power distribution network zoning device. The device includes:

[0034] The partitioning module is used to divide each grid into multiple initial clusters based on the grid density of each grid; the grid is obtained by partitioning the load-concentrated data samples corresponding to the area to be planned.

[0035] The first determining module is used to determine the density partitioning factor based on the maximum grid density, the minimum grid density, and the number of grids corresponding to the target grid density; the target grid density includes grid densities greater than the preset grid density.

[0036] The second determining module is used to determine the neighborhood radius of each initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0037] The third determining module is used to determine the minimum number of sample points based on the number of peaks in the density waveform corresponding to the initial cluster.

[0038] The partitioning module is used to partition the distribution network in the area to be planned based on the neighborhood radius and minimum number of sample points of each initial cluster to obtain each distribution network partition.

[0039] Thirdly, this application also provides a computer device, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of any of the above methods.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above methods.

[0041] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above methods.

[0042] The aforementioned distribution network zoning method, device, computer equipment, and storage medium divide each grid into multiple initial clusters based on the grid density obtained from the load concentration data samples corresponding to each planned area. A density zoning factor is determined based on the number of grids corresponding to the maximum, minimum, and target grid densities. The target grid density includes grid densities greater than a preset density. For each initial cluster, the neighborhood radius is determined based on the density zoning factor and the density waveform corresponding to the initial cluster. The minimum number of sample points is determined based on the number of peaks in the density waveform corresponding to the initial cluster. Then, based on the neighborhood radius and minimum number of sample points of each initial cluster, the distribution network in the planned area is zoned to obtain each distribution network zone. This eliminates the need for manually setting and adjusting the neighborhood radius and minimum number of sample points of the initial clusters, improving the accuracy of distribution network zoning. Attached Figure Description

[0043] Figure 1 This is an internal structure diagram of a computer device provided in an embodiment of this application;

[0044] Figure 2 This is a flowchart illustrating a power distribution network zoning method provided in an embodiment of this application;

[0045] Figure 3 This is a grid density distribution map in the horizontal direction provided in an embodiment of this application;

[0046] Figure 4 This is a flowchart illustrating a method for determining the radius of a domain provided in an embodiment of this application;

[0047] Figure 5 This is a flowchart illustrating a method for determining the radius of a first domain provided in an embodiment of this application;

[0048] Figure 6 This is a flowchart illustrating a method for determining the radius of a second domain provided in an embodiment of this application;

[0049] Figure 7 This is a flowchart illustrating a method for determining analysis results provided in an embodiment of this application;

[0050] Figure 8 This is a flowchart illustrating another method for determining analysis results provided in an embodiment of this application;

[0051] Figure 9 This is a flowchart of a distribution network zoning planning method based on the adaptive gridded DBSCAN algorithm provided in an embodiment of this application;

[0052] Figure 10 This is a structural block diagram of a user behavior analysis device provided in an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0054] With the large-scale integration of high-energy-density renewable energy sources such as wind and solar power into the power system, traditional power systems face enormous challenges. To ensure the safe and stable operation of the power grid, distribution network planning requires comprehensive consideration. Due to the random and intermittent nature of high-energy-density renewable energy, its power generation is difficult to predict, leading to more frequent and complex load changes, placing enormous pressure on distribution equipment and increasing the risk of failure. Therefore, it is necessary to plan and upgrade the traditional distribution network to adapt to the impact of high-energy-density renewable energy integration on grid operational stability. In the distribution network planning process, the division of planning areas is crucial and forms the basis for all subsequent planning work.

[0055] In traditional technologies, clustering algorithms such as K-means, PSO, and DBSCAN are typically used to classify distribution networks into categories such as load-intensive areas and load-short-peak areas based on their load characteristics.

[0056] However, the model parameters of the clustering algorithm usually need to be set and adjusted manually. Therefore, the current clustering algorithm has the problem of poor zoning effect when used to partition the power distribution network.

[0057] The power distribution network zoning method provided in this application can be applied to, for example... Figure 1 The application environment shown. Figure 1 This is an internal structure diagram of a computer device provided in an embodiment of this application. The computer device may be a server, and its internal structure diagram may be as follows: Figure 1 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a power distribution network zoning method.

[0058] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0059] In one embodiment, such as Figure 2 As shown, Figure 2 This is a flowchart illustrating a power distribution network zoning method provided in an embodiment of this application. This method can be applied to... Figure 1The method, using a computer device, includes the following steps:

[0060] S201, based on the grid density of each grid, divide each grid into multiple initial clusters; the grid is obtained by dividing the load concentration data samples corresponding to the area to be planned.

[0061] Specifically, the area to be planned is divided into equally spaced and non-intersecting intervals in both the horizontal and vertical directions. The entire area to be planned is then divided into multiple different grids based on these intervals.

[0062] For example, the side length d of the grid in the horizontal direction x It can be done through formula Calculated. Where, Ub x Lb represents the minimum horizontal boundary of the area to be planned. x is the maximum horizontal boundary of the area to be planned, and k is the number of concentrated load samples corresponding to the area to be planned.

[0063] Specifically, the grid density of each grid can be determined using a Gaussian kernel function. The calculation is obtained. Where dis(i,j) represents the load sample point x. i and x j The Euclidean distance between them, d x,y It can be done through formula Calculated.

[0064] Calculate the grid density for each grid cell. Based on the grid density of each grid cell, obtain the density waveforms of the load set in the horizontal and vertical directions. Grids belonging to the same density waveform are grouped into an initial cluster. Taking the horizontal direction as an example for further explanation... Figure 3 As shown, Figure 3 This is a grid density distribution map in the horizontal direction provided in an embodiment of this application. From Figure 3 It can be seen that grid a and grid b belong to the same density waveform A, while grid c belongs to another density waveform B. Therefore, grid a and grid b belong to the same initial cluster, while grid c belongs to another initial cluster.

[0065] S202, determine the density partitioning factor based on the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density; the target grid density includes grid densities greater than the preset grid density.

[0066] For example, the density zoning factor in the horizontal direction can be expressed by the formula The calculation yields the result. Where max(ρ(x)) i )) represents the maximum grid density in the horizontal direction, min(ρ(x) i)) represents the minimum grid density in the horizontal direction, N ρ(xi)>0 This indicates the number of grids with a grid density greater than 0, that is, the number of grids corresponding to the target grid density mentioned above.

[0067] S203, for each initial cluster, determine the neighborhood radius of the initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0068] Optionally, the neighborhood radius of the initial cluster can be determined based on the density partitioning factor and the density waveform corresponding to the initial cluster in the following ways: Determine the first neighborhood radius in the first direction corresponding to the initial cluster, and use the first neighborhood radius as the neighborhood radius of the initial cluster. Alternatively, determine the second neighborhood radius in the second direction corresponding to the initial cluster, and use the second neighborhood radius as the neighborhood radius of the initial cluster. Or, determine the first neighborhood radius in the first direction and the second neighborhood radius in the second direction corresponding to the initial cluster, and calculate the neighborhood radius of the initial cluster based on the first and second neighborhood radii.

[0069] S204. Determine the minimum number of sample points based on the number of peaks in the density waveform corresponding to the initial cluster.

[0070] Specifically, the number of peaks in the density waveform corresponding to the initial cluster is taken as the minimum number of sample points corresponding to the initial cluster.

[0071] Taking the first direction as an example, such as Figure 3 As shown, density waveform A has two peaks, so the minimum number of sample points for the initial cluster corresponding to density waveform A is 2.

[0072] S205. Based on the neighborhood radius and minimum number of sample points of each initial cluster, the power distribution network in the planning area is partitioned to obtain each power distribution network partition.

[0073] Specifically, a subset of load sample points are randomly selected from each initial cluster as initial core points, according to the formula... Calculate the Euclidean distance from all remaining load sample points (excluding the initial core point) to the initial core point. Where A is a non-initial core point and B is the initial core point, then (x... a ,y a (x) represents the coordinates of load sample point A. b ,y b Let N(a,b) be the coordinates of load sample point B, and dist(a,b) be the Euclidean distance from the non-initial core point A to the initial core point B. The type of load sample point is determined based on the Euclidean distance of each load sample point, the neighborhood radius of the initial cluster corresponding to each load sample point, and the minimum number of sample points. For load sample point a, if N... R(a) ≥ min Pts, then the load sample point a is a target core point; for the load sample point b, if N R (b) < min Pts and dis(a, b) ≤ R, then the load sample point b is a reachable point of the target core point a; for the load sample point c, if N R (c) < min Pts and dis(a, c) > R, then the load sample point c is an outlier of the target core point a. Where, N R is the number of load sample points contained within the neighborhood radius corresponding to the load sample point. For example, N R (a) is the number of load sample points contained within the neighborhood radius corresponding to the load sample point a, min Pts is the minimum number of sample points, and R is the neighborhood radius. Determine the target clustering clusters according to the target core points, add the reachable points of the target core points to the corresponding target clustering clusters, and repeat the iterative calculation until no new points can be added to the existing target clustering clusters, so as to perform zoning processing on the distribution network in the to-be-planned area to obtain each distribution network zone.

[0074] In the embodiments of the present application, multiple initial clustering clusters are obtained by dividing each grid according to the grid density of the grid obtained by dividing the load concentration data samples corresponding to the to-be-planned areas. The density partition factor is determined according to the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density. The target grid density includes grid densities greater than the preset grid density. For each initial clustering cluster, based on the density partition factor and the density waveform corresponding to the initial clustering cluster, the neighborhood radius of the initial clustering cluster is determined. The minimum number of sample points is determined according to the number of peaks in the density waveform corresponding to the initial clustering cluster. Then, according to the neighborhood radius and the minimum number of sample points of each initial clustering cluster, zoning processing is performed on the distribution network in the to-be-planned area to obtain each distribution network zone, thereby eliminating the need for manual setting and adjustment of the neighborhood radius and the minimum number of sample points of the initial clustering cluster, and improving the accuracy of the distribution network zoning.

[0075] Refer to Figure 4 , Figure 4 is a schematic flow chart of a method for determining the neighborhood radius provided by the embodiments of the present application. This embodiment relates to a possible implementation manner of how to determine the neighborhood radius of each initial clustering cluster based on the density partition factor and the density waveform corresponding to the initial clustering cluster. On the basis of the above embodiment, the above S203 includes the following steps:

[0076] S401, determine the first straight line with the grid density equal to the first density partition factor, and determine the first intersection point of the first straight line and the density waveform in the first direction corresponding to the initial clustering cluster.

[0077] In the embodiments of the present application, the first direction may be, for example, the horizontal direction or the vertical direction.

[0078] For example, such as Figure 3 As shown, if the first direction is horizontal and the first density partitioning factor α in the horizontal direction is 0.1, then a first straight line with a grid density ρ = 0.1 is determined. Based on this first straight line, the first intersection point between the first straight line and the density waveforms A and B in the horizontal direction corresponding to the initial clusters A and B is determined. The first intersection point between the first straight line and the density waveform A may include... Figure 3 The first intersection points 31, 32, 33, and 34 are shown in the figure.

[0079] S402, for each initial cluster, based on the first intersection point and the first zero density interval of the density waveform in the first direction corresponding to the initial cluster, determine the first neighborhood radius in the first direction corresponding to the initial cluster; the first zero density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters.

[0080] In one possible implementation, if the initial cluster is Figure 3 The initial cluster corresponding to the leftmost density waveform A can be determined based on the x-coordinate of the rightmost first intersection point and the first zero-density interval following the initial cluster. The first right neighbor radius in the first direction corresponding to the initial cluster can then be used as the first neighbor radius in the first direction corresponding to the initial cluster. For example, it can be based on... Figure 3 The x-coordinate of the rightmost first intersection point 32 of the medium-density waveform A and the first zero-density interval following the initial cluster are used to determine the first right neighbor radius in the horizontal direction corresponding to the initial cluster A. This first right neighbor radius is then used as the first neighbor radius in the horizontal direction corresponding to the initial cluster. The first zero-density interval following the initial cluster is the distance between the first intersection point 32 and the first intersection point 33.

[0081] In another possible implementation, if the initial cluster is Figure 3 The initial cluster corresponding to the rightmost density waveform B can be determined based on the x-coordinate of the leftmost first intersection point and the first zero-density interval preceding the initial cluster. The first left neighbor radius in the first direction corresponding to the initial cluster can then be used as the first neighbor radius in the first direction corresponding to the initial cluster. For example, it can be based on... Figure 3The x-coordinate of the leftmost first intersection point 33 of the medium-density waveform B and the first zero-density interval preceding the initial cluster are used to determine the first left neighbor radius in the horizontal direction corresponding to the initial cluster B. This first left neighbor radius is then used as the first neighbor radius in the horizontal direction corresponding to the initial cluster. The first zero-density interval preceding the initial cluster is the distance between the first intersection point 32 and the first intersection point 33.

[0082] In another possible implementation, if the initial cluster is not the initial cluster corresponding to the rightmost and leftmost density waveforms, that is, if the density waveform corresponding to the initial cluster is adjacent to a density waveform on both the left and right sides, the first right neighbor radius corresponding to the initial cluster in the first direction can be determined based on the x-coordinate of the rightmost first intersection point and the first zero density interval after the initial cluster. The first left neighbor radius corresponding to the initial cluster in the first direction can be determined based on the x-coordinate of the leftmost first intersection point and the first zero density interval before the initial cluster. The smaller of the first right neighbor radius and the first left neighbor radius is taken as the first neighbor radius corresponding to the initial cluster in the first direction.

[0083] S403, determine the second straight line whose grid density is equal to the second density partition factor, and determine the second intersection point of the second straight line with the density waveform in the second direction corresponding to the initial cluster.

[0084] In this embodiment of the application, the second direction can be, for example, a horizontal direction or a vertical direction.

[0085] For example, if the second direction is vertical and the second density partitioning factor α in the vertical direction is 0.3, then a second straight line with grid density ρ = 0.3 is determined, and the first intersection point of the second straight line and the density waveform in the vertical direction corresponding to the initial cluster is determined based on the second straight line.

[0086] S404, for each initial cluster, based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster, determine the second neighborhood radius in the second direction corresponding to the initial cluster; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster.

[0087] In one possible implementation, similar to the implementation of S402 above, if the initial cluster is the initial cluster corresponding to the leftmost density waveform, the second right neighbor radius corresponding to the initial cluster in the second direction can be determined based on the abscissa of the rightmost second intersection point and the second zero density interval located after the initial cluster, and the second right neighbor radius is used as the second neighbor radius corresponding to the initial cluster in the second direction.

[0088] In another possible implementation, similar to the implementation of S402 above, if the initial cluster is the initial cluster corresponding to the rightmost density waveform, the second left neighbor radius corresponding to the initial cluster in the second direction can be determined based on the abscissa of the second intersection point on the leftmost side and the second zero density interval located before the initial cluster, and the second left neighbor radius is used as the second neighbor radius corresponding to the initial cluster in the second direction.

[0089] In another possible implementation, if the initial cluster is not the initial cluster corresponding to the rightmost and leftmost density waveforms, that is, if the density waveform corresponding to the initial cluster is adjacent to a density waveform on both the left and right sides, the second right neighbor radius corresponding to the initial cluster in the second direction can be determined based on the abscissa of the rightmost second intersection point and the second zero density interval located after the initial cluster. The second left neighbor radius corresponding to the initial cluster in the second direction can be determined based on the abscissa of the leftmost second intersection point and the second zero density interval located before the initial cluster. The smaller of the second right neighbor radius and the second left neighbor radius is taken as the second neighbor radius corresponding to the initial cluster in the second direction.

[0090] S405, determine the neighborhood radius of the initial cluster based on the first neighborhood radius and the second neighborhood radius.

[0091] Specifically, formulas can be used. The neighborhood radius of the initial cluster is calculated. Where R... A The neighborhood radius of the initial cluster. The radius of the first neighborhood is 1. The radius of the second neighborhood.

[0092] In this embodiment, a first straight line with a grid density equal to a first density partitioning factor is determined, and a first intersection point of the first straight line with the density waveform in a first direction corresponding to the initial cluster is determined. For each initial cluster, a first neighborhood radius in the first direction corresponding to the initial cluster is determined based on the first intersection point of the density waveform in the first direction corresponding to the initial cluster and a first zero-density interval. The first zero-density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, where the first and second initial clusters are adjacent initial clusters. A second straight line with a grid density equal to a second density partitioning factor is determined, and a second intersection point of the second straight line with the density waveform in a second direction corresponding to the initial cluster is determined. For each initial cluster, a second neighborhood radius in the second direction corresponding to the initial cluster is determined based on the second intersection point of the density waveform in the second direction corresponding to the initial cluster and a second zero-density interval. The second zero-density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster. Then, based on the first and second neighborhood radii, the neighborhood radius of the initial cluster is determined. Since the neighborhood radius of the initial cluster is determined based on the density partitioning factor and the density waveform corresponding to the initial cluster in this embodiment, there is no need to manually set the neighborhood radius, thus improving the accuracy of distribution network partitioning.

[0093] Reference Figure 5 , Figure 5 This is a flowchart illustrating a method for determining the radius of a first neighborhood according to an embodiment of this application. This embodiment relates to a possible implementation of determining the radius of a first neighborhood in the first direction corresponding to an initial cluster based on the first intersection point and the first zero-density interval of the density waveforms in the first direction corresponding to the initial cluster. Based on the above embodiment, step S402 includes the following steps:

[0094] S501, based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster, determine the radius of the first right neighbor in the first direction corresponding to the initial cluster.

[0095] For example, such as Figure 3 As shown, assuming initial cluster A is the first initial cluster and initial cluster B is the second initial cluster, and initial cluster A precedes initial cluster B, then the distance between the rightmost first intersection point of initial cluster A and the leftmost first intersection point of initial cluster B can be used as the first zero-density interval. Based on the rightmost first intersection point of initial cluster A and the first zero-density interval, the formula is used... The radius of the first right neighbor in the first direction corresponding to the initial cluster A is calculated. Where, x bLet x be the x-coordinate of the first intersection point on the rightmost side of the initial cluster A. b+gap / 2 The x-coordinate is the position at halfway point of the first zero-density interval.

[0096] S502, based on the x-coordinate of the leftmost first intersection point and the first zero-density interval before the initial cluster, determine the radius of the first left neighbor in the first direction corresponding to the initial cluster.

[0097] For example, such as Figure 3 As shown, assuming initial cluster A is the first initial cluster and initial cluster B is the second initial cluster, and initial cluster B is located after initial cluster A, then the distance between the rightmost first intersection point of initial cluster A and the leftmost first intersection point of initial cluster B can be used as the first zero-density interval. Based on the leftmost first intersection point of initial cluster B and the first zero-density interval, the formula is used... The radius of the first left neighbor in the first direction corresponding to the initial cluster B is calculated. Where, x b Let x be the x-coordinate of the first intersection point on the leftmost side of the initial cluster B. b+gap / 2 The x-coordinate is the position at halfway point of the first zero-density interval.

[0098] The radius of the first right neighbor of the initial cluster A is equal to the radius of the first left neighbor of the initial cluster B. That is,

[0099] S503, determine the first neighborhood radius in the first direction corresponding to the initial cluster based on the first left neighborhood radius and / or the first right neighborhood radius in the first direction corresponding to the initial cluster.

[0100] Optionally, the radius of the first left neighbor in the first direction corresponding to the initial cluster can be used as the radius of the first neighbor in the first direction corresponding to the initial cluster. Alternatively, the radius of the first right neighbor in the first direction corresponding to the initial cluster can be used as the radius of the first neighbor in the first direction corresponding to the initial cluster. Or, the smaller of the radius of the first left neighbor and the radius of the first right neighbor in the first direction corresponding to the initial cluster can be used as the radius of the first neighbor in the first direction corresponding to the initial cluster.

[0101] In this embodiment, the first right neighbor radius corresponding to the initial cluster in the first direction is determined based on the abscissa of the rightmost first intersection point and the first zero-density interval following the initial cluster. The first left neighbor radius corresponding to the initial cluster in the first direction is determined based on the abscissa of the leftmost first intersection point and the first zero-density interval preceding the initial cluster. Finally, the first neighborhood radius corresponding to the initial cluster in the first direction is determined based on the first left neighbor radius and / or the first right neighbor radius. Therefore, the first neighborhood radius corresponding to the initial cluster in the first direction is determined based on the first intersection point and the first zero-density interval of the density waveform in the first direction, eliminating the need for manually setting the neighborhood radius and improving the accuracy of distribution network zoning.

[0102] Reference Figure 6 , Figure 6 This is a flowchart illustrating a method for determining a second neighborhood radius according to an embodiment of this application. This embodiment relates to a possible implementation of determining the second neighborhood radius in the second direction corresponding to an initial cluster based on the second intersection point and the second zero-density interval of the density waveforms in the second direction corresponding to the initial cluster. Based on the above embodiment, S404 includes the following steps:

[0103] S601, based on the x-coordinate of the rightmost second intersection point and the second zero-density interval located after the initial cluster, determine the second right neighbor radius in the second direction corresponding to the initial cluster.

[0104] For example, assuming initial cluster A is the first initial cluster and initial cluster B is the second initial cluster, and initial cluster A precedes initial cluster B, then the distance between the rightmost first intersection point of initial cluster A and the leftmost second intersection point of initial cluster B can be used as the second zero-density interval. Based on the rightmost second intersection point of initial cluster A and the second zero-density interval, the formula is used... The radius of the second right neighbor in the second direction corresponding to the initial cluster A is calculated. Where, x b Let x be the x-coordinate of the second intersection point on the rightmost side of the initial cluster A. b+gap / 2 It is the x-coordinate corresponding to the halfway point of the second zero-density interval.

[0105] S602, based on the x-coordinate of the leftmost second intersection point and the second zero-density interval located before the initial cluster, determine the second left neighbor radius corresponding to the initial cluster in the second direction.

[0106] For example, assuming initial cluster A is the first initial cluster and initial cluster B is the second initial cluster, and initial cluster B is located after initial cluster A, then the distance between the rightmost second intersection point of initial cluster A and the leftmost second intersection point of initial cluster B can be used as the second zero-density interval. Based on the leftmost second intersection point of initial cluster B and the second zero-density interval, the formula is used... The radius of the second left neighbor in the second direction corresponding to the initial cluster B is calculated. Among them, y b Let y be the x-coordinate of the second intersection point on the leftmost side of the initial cluster B. b+gap / 2 It is the x-coordinate corresponding to the halfway point of the second zero-density interval.

[0107] The radius of the second right neighbor of the initial cluster A is equal to the radius of the second left neighbor of the initial cluster B. That is,

[0108] S603, determine the second neighborhood radius in the second direction corresponding to the initial cluster based on the second left neighborhood radius and / or right neighborhood radius in the second direction corresponding to the initial cluster.

[0109] Optionally, the radius of the second left neighbor in the second direction corresponding to the initial cluster can be used as the radius of the second neighbor in the second direction corresponding to the initial cluster. Alternatively, the radius of the second right neighbor in the second direction corresponding to the initial cluster can be used as the radius of the second neighbor in the second direction corresponding to the initial cluster. Or, the smaller of the radius of the second left neighbor and the radius of the second right neighbor in the second direction corresponding to the initial cluster can be used as the radius of the second neighbor in the second direction corresponding to the initial cluster.

[0110] In this embodiment, the second right neighbor radius corresponding to the initial cluster in the second direction is determined based on the abscissa of the rightmost second intersection point and the second zero-density interval following the initial cluster. The second left neighbor radius corresponding to the initial cluster in the second direction is determined based on the abscissa of the leftmost second intersection point and the second zero-density interval preceding the initial cluster. Finally, the second neighbor radius corresponding to the initial cluster in the second direction is determined based on the second left neighbor radius and / or the second right neighbor radius. Therefore, the second neighbor radius corresponding to the initial cluster in the second direction is determined based on the second intersection point and the second zero-density interval of the density waveform in the second direction, eliminating the need for manually setting the neighbor radius and improving the accuracy of distribution network zoning.

[0111] Reference Figure 7 , Figure 7 This is a flowchart illustrating a method for determining analysis results provided in an embodiment of this application. Based on the above embodiment, the method further includes the following steps:

[0112] S701: For each distribution network zone, a distribution network zone planning scheme is obtained by planning the distribution network zone and the cost of the distribution network zone planning scheme is determined.

[0113] Specifically, the cost of a power distribution network zoning plan includes construction costs and operating costs.

[0114] Construction cost is the same as the upper-level investment cost, and the objective function for construction cost is C. build =min(∑C line +∑C ES ). Where, ∑C line It is the total cost of line expansion, ∑C ES This represents the total cost of energy storage construction. To minimize the aforementioned construction cost, the total cost of line expansion and the total cost of energy storage construction must satisfy construction variable constraints, distribution network connectivity constraints, and line radial configuration constraints. The construction variable constraints are as follows: in, For the expansion variable of line ij, Let be the construction variable for energy storage at node j. The distribution network connectivity constraint is... The radial constraint of the line is Among them, L ij,t Let be the commissioning variable for line ij.

[0115] Operating cost refers to the operating cost over the entire lifecycle of the distribution network. The objective function for operating cost is: Where, ∑C SP For the cost of electricity purchased by the superior, ∑C DG For the operating costs of distributed renewable energy, For the cost of curtailment of distributed renewable energy, ∑C loss This refers to the operating loss cost of the distribution network. To minimize the above operating costs, it is necessary to satisfy node power balance constraints, power flow constraints, operating voltage constraints, operating current constraints, and energy storage operating constraints.

[0116] Node power balance constraints are expressed as Current flow constraints are represented as Where N represents a node in the power grid. The voltage magnitude and phase angle of node i at time t are respectively, r ij ,x ij P represents the resistance and reactance between nodes ij, respectively. ij,t Q ij,t P represents the power transmitted on line ij at time t; i,t and Q i,tLet U represent the active power and reactive power injected at node i at time t, respectively. The operating voltage constraint is represented by U. imin ≤U i,j ≤U imax Let i = 1, 2, ..., N. The operating current constraint is expressed as... Energy storage operation constraints are expressed as SOC i,min ≤SOC i,t ≤SOC i,max SOC i,0 =SOC i,T .in, and These are the upper and lower limits of the active power of the nth energy storage unit, respectively, and the State of Charge (SOC). i,min and SOC i,max These represent the lower and upper limits of the state of charge (SOC) of the energy storage system, where η is the battery efficiency and Δt is the time step. and SOC i,t Let $t$ be the remaining charge and state of charge of the $i$-th ES at time $t$.

[0117] S702, for each distribution network zone, analyze the scenarios in the distribution network zone and determine the target scenarios of the distribution network zone; the target scenarios include atypical operating scenarios and / or typical operating scenarios.

[0118] Specifically, for each distribution network zone, a set of joint operation scenarios for distributed renewable energy and loads is constructed. Since fluctuations in renewable energy output and load can impact grid operation to varying degrees, and larger power fluctuations are more likely to cause local grid faults, it is necessary to assess the impact of distributed renewable energy and loads with different levels of fluctuation on grid operational stability. Renewable energy output and load can be treated as variables, and the impact can be assessed using formulas... Calculate the entropy value of each variable. Where S i Let i be the entropy value of the i-th variable (new energy power plant or load), i = 1, 2, ..., N. DG +N load ,β i,t Let be the power proportion of the i-th variable at time segment t. Calculate the entropy weight coefficients for each variable based on their entropy values. Wherein, the entropy weight coefficients... After assigning weights to each variable, i.e., multiplying each variable by an entropy weight coefficient, the K-means algorithm is used to extract typical and atypical operating scenarios in each distribution network zone.

[0119] S703, based on the cost and target scenario of the distribution network zoning planning scheme, conducts a feasibility analysis of the distribution network zoning planning scheme and obtains the analysis results.

[0120] Specifically, the cost of the distribution network zoning plan is determined to be greater than a preset cost threshold. If the cost exceeds the threshold, the plan is infeasible; if it is less than or equal to the threshold, it is feasible. Based on atypical operating scenarios within the target environment, the plan's tolerance to extreme conditions is assessed. If the tolerance is less than or equal to a preset threshold, the plan is infeasible; if it exceeds the threshold, it is feasible.

[0121] In this embodiment, for each distribution network zone, the cost of the distribution network zone planning scheme is determined, the scenarios in the distribution network zone are analyzed, and the atypical and typical operating scenarios of the distribution network zone are determined. Based on the cost of the distribution network zone planning scheme, the typical operating scenarios and the atypical operating scenarios, a feasibility analysis of the distribution network zone planning scheme is conducted to obtain the analysis results. Thus, the distribution network zone planning scheme can be determined based on the analysis results of the feasibility analysis, thereby reducing the cost of distribution network planning and improving the reliability of the distribution network zone planning scheme.

[0122] Reference Figure 8 , Figure 8 This is a flowchart illustrating another method for determining analysis results provided in this application embodiment. This embodiment relates to a possible implementation of how to conduct a feasibility analysis of a distribution network zoning planning scheme based on its cost and target scenario to obtain the analysis results. Based on the above embodiment, S703 includes the following steps:

[0123] S801 performs power flow calculations on the target scenario to obtain the calculation results.

[0124] Optionally, the voltage and current of the distribution network in atypical scenarios can be obtained through power flow calculations, and these voltages and currents can be used as the calculation results. Alternatively, the voltage and current of the distribution network in typical scenarios can be obtained through power flow calculations, and these voltages and currents can be used as the calculation results. Alternatively, the voltage and current of the distribution network in both atypical and typical scenarios can be obtained through power flow calculations, and these voltages and currents can be used as the calculation results.

[0125] S802, based on the calculation results, a feasibility analysis of the power distribution network zoning planning scheme is conducted to obtain the analysis results.

[0126] Specifically, based on the calculation results, it is determined whether there are voltage or current overruns in the distribution network in the target scenario. If there are voltage overruns in the distribution network in the target scenario, the distribution network zoning plan is not feasible; if there are current overruns in the distribution network in the target scenario, the distribution network zoning plan is not feasible; if there are both voltage and current overruns in the distribution network in the target scenario, the distribution network zoning plan is not feasible.

[0127] In this embodiment of the application, power flow calculation is performed on the target scenario to obtain the calculation results. Based on the calculation results, a feasibility analysis is performed on the distribution network zoning planning scheme to obtain the analysis results. This allows for the assessment of the distribution network zoning's capacity to withstand extreme scenarios, thereby improving the reliability of the distribution network zoning planning scheme.

[0128] Reference Figure 9 , Figure 9 This is a flowchart illustrating a distribution network zoning planning method based on the adaptive gridded DBSCAN algorithm provided in an embodiment of this application. The method includes the following steps:

[0129] S901, Data Preprocessing.

[0130] S902, based on the grid density of each grid, divide each grid into multiple initial clusters.

[0131] S903 determines the density partitioning factor based on the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density.

[0132] S904: For each initial cluster, determine the neighborhood radius of the initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0133] S905, determine the minimum number of sample points based on the number of peaks in the density waveform corresponding to the initial cluster.

[0134] S906, based on the neighborhood radius and minimum number of sample points of each initial cluster, the distribution network in the planning area is partitioned to obtain each distribution network partition.

[0135] S907: For each distribution network zone, a distribution network zone planning scheme is obtained by planning the distribution network zone and the cost of the distribution network zone planning scheme is determined.

[0136] S908 analyzes the scenarios within each distribution network zone to determine the atypical and / or typical operating scenarios of the distribution network zone.

[0137] S909 performs power flow calculations on the target scenario to obtain the calculation results.

[0138] S910, based on the cost and calculation results of the distribution network zoning planning scheme, a feasibility analysis of the distribution network zoning planning scheme is conducted to obtain the analysis results.

[0139] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0140] Based on the same inventive concept, this application also provides a distribution network partitioning device for implementing the distribution network partitioning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more distribution network partitioning device embodiments provided below can be found in the limitations of the distribution network partitioning method described above, and will not be repeated here.

[0141] In one embodiment, such as Figure 10 As shown, Figure 10 This is a structural block diagram of a user behavior analysis device provided in an embodiment of this application. The device 1000 includes:

[0142] The partitioning module 1001 is used to partition each grid according to the grid density of each grid to obtain multiple initial clusters; the grid is obtained by partitioning the load concentration data samples corresponding to the area to be planned.

[0143] The first determining module 1002 is used to determine the density partitioning factor based on the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density; the target grid density includes grid densities greater than the preset grid density.

[0144] The second determining module 1003 is used to determine the neighborhood radius of each initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0145] The third determining module 1004 is used to determine the minimum number of sample points based on the number of peaks in the density waveform corresponding to the initial cluster.

[0146] The partitioning module 1005 is used to partition the distribution network in the planning area according to the neighborhood radius and minimum number of sample points of each initial cluster to obtain each distribution network partition.

[0147] In one embodiment, the second determining module 1003 includes:

[0148] The first determining unit is used to determine a first straight line whose grid density is equal to the first density partition factor, and to determine the first intersection point of the first straight line and the density waveform in the first direction corresponding to the initial cluster.

[0149] The second determining unit is used to determine the first neighborhood radius in the first direction corresponding to each initial cluster based on the first intersection point and the first zero density interval of the density waveform in the first direction corresponding to the initial cluster; the first zero density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters.

[0150] The third determining unit is used to determine the second straight line whose grid density is equal to the second density partition factor, and to determine the second intersection point of the second straight line and the density waveform in the second direction corresponding to the initial cluster.

[0151] The fourth determining unit is used to determine the second neighborhood radius in the second direction corresponding to each initial cluster based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster.

[0152] The fifth determining unit is used to determine the neighborhood radius of the initial cluster based on the first neighborhood radius and the second neighborhood radius.

[0153] In one embodiment, the second determining unit includes:

[0154] The first determining sub-unit is used to determine the first right neighbor radius in the first direction corresponding to the initial cluster based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster.

[0155] The second determining subunit is used to determine the first left neighbor radius in the first direction corresponding to the initial cluster based on the x-coordinate of the leftmost first intersection point and the first zero-density interval located before the initial cluster.

[0156] The third determining subunit is used to determine the first neighborhood radius in the first direction corresponding to the initial cluster based on the first left neighborhood radius and / or right neighborhood radius in the first direction corresponding to the initial cluster.

[0157] In one embodiment, the fourth determining unit includes:

[0158] The fourth determining sub-unit is used to determine the second right neighbor radius in the second direction corresponding to the initial cluster based on the abscissa of the rightmost second intersection point and the second zero density interval located after the initial cluster.

[0159] The fifth determining sub-unit is used to determine the second left neighborhood radius in the second direction corresponding to the initial cluster based on the x-coordinate of the leftmost second intersection point and the second zero density interval located before the initial cluster.

[0160] The sixth determining subunit is used to determine the second neighborhood radius in the second direction corresponding to the initial cluster based on the second left neighborhood radius and / or right neighborhood radius in the second direction corresponding to the initial cluster.

[0161] In one embodiment, the device 1000 further includes:

[0162] The fourth module is used to plan the distribution network zones for each distribution network zone to obtain a distribution network zone planning scheme and determine the cost of the distribution network zone planning scheme.

[0163] The fifth determination module is used to analyze the scenarios in each distribution network zone and determine the target scenarios for each distribution network zone; the target scenarios include atypical operating scenarios and / or typical operating scenarios.

[0164] The analysis module is used to perform a feasibility analysis on the distribution network zoning planning scheme based on the cost and target scenario, and obtain the analysis results.

[0165] In one embodiment, the analysis module is specifically used to perform power flow calculations on the target scenario to obtain calculation results, and to perform feasibility analysis on the distribution network zoning planning scheme based on the calculation results to obtain analysis results.

[0166] Each module in the aforementioned power distribution network zoning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0167] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0168] Based on the grid density of each grid, multiple initial clusters are obtained by dividing each grid into grids; the grids are obtained by dividing the load concentration data samples corresponding to the area to be planned.

[0169] The density partitioning factor is determined based on the number of grids corresponding to the maximum, minimum, and target grid densities; the target grid density includes grid densities greater than the preset grid density.

[0170] For each initial cluster, the neighborhood radius of the initial cluster is determined based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0171] The minimum number of sample points is determined based on the number of peaks in the density waveform corresponding to the initial cluster.

[0172] Based on the neighborhood radius and minimum number of sample points of each initial cluster, the power distribution network in the area to be planned is partitioned to obtain each power distribution network partition.

[0173] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0174] Determine the first straight line whose grid density is equal to the first density partition factor, and determine the first intersection point of the first straight line with the density waveform in the first direction corresponding to the initial cluster;

[0175] For each initial cluster, based on the first intersection point and the first zero density interval of the density waveform in the first direction corresponding to the initial cluster, the first neighborhood radius in the first direction corresponding to the initial cluster is determined; the first zero density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters;

[0176] Determine the second straight line whose grid density is equal to the second density partition factor, and determine the second intersection point of the second straight line with the density waveform in the second direction corresponding to the initial cluster;

[0177] For each initial cluster, the second neighborhood radius in the second direction corresponding to the initial cluster is determined based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster.

[0178] The neighborhood radius of the initial cluster is determined based on the first neighborhood radius and the second neighborhood radius.

[0179] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0180] Based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster, determine the radius of the first right neighbor in the first direction corresponding to the initial cluster;

[0181] Based on the x-coordinate of the leftmost first intersection point and the first zero-density interval located before the initial cluster, determine the radius of the first left neighbor in the first direction corresponding to the initial cluster;

[0182] The first neighborhood radius corresponding to the initial cluster in the first direction is determined based on the first left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the first direction.

[0183] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0184] Based on the x-coordinate of the rightmost second intersection point and the second zero-density interval located after the initial cluster, determine the second right neighbor radius in the second direction corresponding to the initial cluster;

[0185] Based on the x-coordinate of the leftmost intersection point and the second zero-density interval located before the initial cluster, determine the radius of the second left neighborhood in the second direction corresponding to the initial cluster;

[0186] The second neighborhood radius corresponding to the initial cluster in the second direction is determined based on the second left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the second direction.

[0187] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0188] For each distribution network zone, a distribution network zone planning scheme is obtained by planning the distribution network zone, and the cost of the distribution network zone planning scheme is determined.

[0189] For each distribution network zone, the scenarios within the distribution network zone are analyzed to determine the target scenarios for the distribution network zone; the target scenarios include atypical operating scenarios and / or typical operating scenarios.

[0190] Based on the cost and target scenarios of the power distribution network zoning planning scheme, a feasibility analysis of the power distribution network zoning planning scheme is conducted to obtain the analysis results.

[0191] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0192] Power flow calculations are performed on the target scenario to obtain the calculation results;

[0193] Based on the calculation results, a feasibility analysis of the power distribution network zoning planning scheme was conducted, and the analysis results were obtained.

[0194] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0195] Based on the grid density of each grid, multiple initial clusters are obtained by dividing each grid into grids; the grids are obtained by dividing the load concentration data samples corresponding to the area to be planned.

[0196] The density partitioning factor is determined based on the number of grids corresponding to the maximum, minimum, and target grid densities; the target grid density includes grid densities greater than the preset grid density.

[0197] For each initial cluster, the neighborhood radius of the initial cluster is determined based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0198] The minimum number of sample points is determined based on the number of peaks in the density waveform corresponding to the initial cluster.

[0199] Based on the neighborhood radius and minimum number of sample points of each initial cluster, the power distribution network in the area to be planned is partitioned to obtain each power distribution network partition.

[0200] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0201] Determine the first straight line whose grid density is equal to the first density partition factor, and determine the first intersection point of the first straight line with the density waveform in the first direction corresponding to the initial cluster;

[0202] For each initial cluster, based on the first intersection point and the first zero density interval of the density waveform in the first direction corresponding to the initial cluster, the first neighborhood radius in the first direction corresponding to the initial cluster is determined; the first zero density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters;

[0203] Determine the second straight line whose grid density is equal to the second density partition factor, and determine the second intersection point of the second straight line with the density waveform in the second direction corresponding to the initial cluster;

[0204] For each initial cluster, the second neighborhood radius in the second direction corresponding to the initial cluster is determined based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster.

[0205] The neighborhood radius of the initial cluster is determined based on the first neighborhood radius and the second neighborhood radius.

[0206] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0207] Based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster, determine the radius of the first right neighbor in the first direction corresponding to the initial cluster;

[0208] Based on the x-coordinate of the leftmost first intersection point and the first zero-density interval located before the initial cluster, determine the radius of the first left neighbor in the first direction corresponding to the initial cluster;

[0209] The first neighborhood radius corresponding to the initial cluster in the first direction is determined based on the first left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the first direction.

[0210] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0211] Based on the x-coordinate of the rightmost second intersection point and the second zero-density interval located after the initial cluster, determine the second right neighbor radius in the second direction corresponding to the initial cluster;

[0212] Based on the x-coordinate of the leftmost intersection point and the second zero-density interval located before the initial cluster, determine the radius of the second left neighborhood in the second direction corresponding to the initial cluster;

[0213] The second neighborhood radius corresponding to the initial cluster in the second direction is determined based on the second left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the second direction.

[0214] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0215] For each distribution network zone, a distribution network zone planning scheme is obtained by planning the distribution network zone, and the cost of the distribution network zone planning scheme is determined.

[0216] For each distribution network zone, the scenarios within the distribution network zone are analyzed to determine the target scenarios for the distribution network zone; the target scenarios include atypical operating scenarios and / or typical operating scenarios.

[0217] Based on the cost and target scenarios of the power distribution network zoning planning scheme, a feasibility analysis of the power distribution network zoning planning scheme is conducted to obtain the analysis results.

[0218] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0219] Power flow calculations are performed on the target scenario to obtain the calculation results;

[0220] Based on the calculation results, a feasibility analysis of the power distribution network zoning planning scheme was conducted, and the analysis results were obtained.

[0221] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0222] Based on the grid density of each grid, multiple initial clusters are obtained by dividing each grid into grids; the grids are obtained by dividing the load concentration data samples corresponding to the area to be planned.

[0223] The density partitioning factor is determined based on the number of grids corresponding to the maximum, minimum, and target grid densities; the target grid density includes grid densities greater than the preset grid density.

[0224] For each initial cluster, the neighborhood radius of the initial cluster is determined based on the density partitioning factor and the density waveform corresponding to the initial cluster.

[0225] The minimum number of sample points is determined based on the number of peaks in the density waveform corresponding to the initial cluster.

[0226] Based on the neighborhood radius and minimum number of sample points of each initial cluster, the power distribution network in the area to be planned is partitioned to obtain each power distribution network partition.

[0227] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0228] Determine the first straight line whose grid density is equal to the first density partition factor, and determine the first intersection point of the first straight line with the density waveform in the first direction corresponding to the initial cluster;

[0229] For each initial cluster, based on the first intersection point and the first zero density interval of the density waveform in the first direction corresponding to the initial cluster, the first neighborhood radius in the first direction corresponding to the initial cluster is determined; the first zero density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters;

[0230] Determine the second straight line whose grid density is equal to the second density partition factor, and determine the second intersection point of the second straight line with the density waveform in the second direction corresponding to the initial cluster;

[0231] For each initial cluster, the second neighborhood radius in the second direction corresponding to the initial cluster is determined based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster.

[0232] The neighborhood radius of the initial cluster is determined based on the first neighborhood radius and the second neighborhood radius.

[0233] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0234] Based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster, determine the radius of the first right neighbor in the first direction corresponding to the initial cluster;

[0235] Based on the x-coordinate of the leftmost first intersection point and the first zero-density interval located before the initial cluster, determine the radius of the first left neighbor in the first direction corresponding to the initial cluster;

[0236] The first neighborhood radius corresponding to the initial cluster in the first direction is determined based on the first left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the first direction.

[0237] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0238] Based on the x-coordinate of the rightmost second intersection point and the second zero-density interval located after the initial cluster, determine the second right neighbor radius in the second direction corresponding to the initial cluster;

[0239] Based on the x-coordinate of the leftmost intersection point and the second zero-density interval located before the initial cluster, determine the radius of the second left neighborhood in the second direction corresponding to the initial cluster;

[0240] The second neighborhood radius corresponding to the initial cluster in the second direction is determined based on the second left neighborhood radius and / or right neighborhood radius corresponding to the initial cluster in the second direction.

[0241] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0242] For each distribution network zone, a distribution network zone planning scheme is obtained by planning the distribution network zone, and the cost of the distribution network zone planning scheme is determined.

[0243] For each distribution network zone, the scenarios within the distribution network zone are analyzed to determine the target scenarios for the distribution network zone; the target scenarios include atypical operating scenarios and / or typical operating scenarios.

[0244] Based on the cost and target scenarios of the power distribution network zoning planning scheme, a feasibility analysis of the power distribution network zoning planning scheme is conducted to obtain the analysis results.

[0245] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0246] Power flow calculations are performed on the target scenario to obtain the calculation results;

[0247] Based on the calculation results, a feasibility analysis of the power distribution network zoning planning scheme was conducted, and the analysis results were obtained.

[0248] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0249] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0250] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for dividing a power distribution network, characterized in that, The method includes: Based on the grid density of each grid, multiple initial clusters are obtained by dividing each grid into the load-centralized data samples corresponding to the area to be planned. The density partitioning factor is determined based on the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density; the target grid density includes grid densities greater than a preset grid density; the density partitioning factor includes a first density partitioning factor in a first direction and a second density partitioning factor in a second direction. For each initial cluster, the neighborhood radius of the initial cluster is determined based on the density partitioning factor and the density waveform corresponding to the initial cluster. The minimum number of sample points is determined based on the number of peaks in the density waveform corresponding to the initial cluster. Based on the neighborhood radius and minimum number of sample points of each initial cluster, the power distribution network in the area to be planned is partitioned to obtain each power distribution network partition; Specifically, determining the neighborhood radius of each initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster includes: Determine a first straight line whose grid density is equal to the first density partition factor, and determine the first intersection point of the first straight line with the density waveform in the first direction corresponding to the initial cluster; For each initial cluster, based on the first intersection point and the first zero-density interval of the density waveform in the first direction corresponding to the initial cluster, the first neighborhood radius in the first direction corresponding to the initial cluster is determined; the first zero-density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters; Determine a second straight line whose grid density is equal to the second density partition factor, and determine a second intersection point between the second straight line and the density waveform in the second direction corresponding to the initial cluster; For each initial cluster, based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster, the second neighborhood radius in the second direction corresponding to the initial cluster is determined; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster. The neighborhood radius of the initial cluster is determined based on the first neighborhood radius and the second neighborhood radius.

2. The method according to claim 1, characterized in that, The step of determining the first neighborhood radius in the first direction corresponding to the initial cluster based on the first intersection point and the first zero-density interval of the density waveform in the first direction corresponding to the initial cluster includes: Based on the x-coordinate of the rightmost first intersection point and the first zero-density interval located after the initial cluster, the radius of the first right neighbor in the first direction corresponding to the initial cluster is determined. Based on the x-coordinate of the leftmost first intersection point and the first zero-density interval located before the initial cluster, the radius of the first left neighbor in the first direction corresponding to the initial cluster is determined; The first neighborhood radius in the first direction corresponding to the initial cluster is determined based on the first left neighborhood radius and / or the first right neighborhood radius in the first direction corresponding to the initial cluster.

3. The method according to claim 1 or 2, characterized in that, The step of determining the second neighborhood radius in the second direction corresponding to the initial cluster based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster includes: Based on the x-coordinate of the rightmost second intersection point and the second zero-density interval located after the initial cluster, the second right neighbor radius corresponding to the initial cluster in the second direction is determined; Based on the x-coordinate of the leftmost second intersection point and the second zero-density interval located before the initial cluster, the second left neighborhood radius corresponding to the initial cluster in the second direction is determined; The second neighborhood radius corresponding to the initial cluster in the second direction is determined based on the second left neighborhood radius and / or the second right neighborhood radius corresponding to the initial cluster in the second direction.

4. The method according to any one of claims 1-2, characterized in that, The method further includes: For each of the aforementioned distribution network zones, a distribution network zone planning scheme is obtained by planning the distribution network zone, and the cost of the distribution network zone planning scheme is determined. For each of the aforementioned distribution network zones, the scenarios within the distribution network zones are analyzed to determine the target scenarios for each distribution network zone; the target scenarios include atypical operating scenarios and / or typical operating scenarios; Based on the cost of the proposed power distribution network zoning plan and the target scenario, a feasibility analysis of the proposed power distribution network zoning plan is conducted to obtain the analysis results.

5. The method according to claim 4, characterized in that, The step of conducting a feasibility analysis of the distribution network zoning planning scheme based on the cost of the scheme and the target scenario to obtain the analysis results includes: Power flow calculations are performed on the target scenario to obtain the calculation results; Based on the calculation results, a feasibility analysis of the power distribution network zoning planning scheme was conducted to obtain the analysis results.

6. A distribution network zoning device, characterized in that, The device includes: The partitioning module is used to divide each grid into multiple initial clusters based on the grid density of each grid; the grids are obtained by partitioning the load-centralized data samples corresponding to the area to be planned; The first determining module is used to determine the density partitioning factor based on the number of grids corresponding to the maximum grid density, the minimum grid density, and the target grid density; the target grid density includes grid densities greater than a preset grid density; the density partitioning factor includes a first density partitioning factor in a first direction and a second density partitioning factor in a second direction. The second determining module is used to determine the neighborhood radius of each initial cluster based on the density partitioning factor and the density waveform corresponding to the initial cluster. The third determining module is used to determine the minimum number of sample points based on the number of peaks in the density waveform corresponding to the initial cluster. The partitioning module is used to partition the power distribution network in the area to be planned based on the neighborhood radius and minimum number of sample points of each initial cluster to obtain each power distribution network partition. The second determining module includes: The first determining unit is used to determine a first straight line whose grid density is equal to the first density partitioning factor, and to determine the first intersection point of the first straight line and the density waveform in the first direction corresponding to the initial cluster. The second determining unit is configured to, for each initial cluster, determine the first neighborhood radius in the first direction corresponding to the initial cluster based on the first intersection point and the first zero density interval of the density waveform in the first direction corresponding to the initial cluster; the first zero density interval is the distance between the rightmost first intersection point of the first initial cluster and the leftmost first intersection point of the second initial cluster, and the first initial cluster and the second initial cluster are two adjacent initial clusters; The third determining unit is used to determine a second straight line whose grid density is equal to the second density partition factor, and to determine a second intersection point of the second straight line and the density waveform in the second direction corresponding to the initial cluster. The fourth determining unit is used to determine, for each initial cluster, a second neighborhood radius in the second direction corresponding to the initial cluster, based on the second intersection point and the second zero density interval of the density waveform in the second direction corresponding to the initial cluster; the second zero density interval is the distance between the rightmost second intersection point of the first initial cluster and the leftmost second intersection point of the second initial cluster. The fifth determining unit is used to determine the neighborhood radius of the initial cluster based on the first neighborhood radius and the second neighborhood radius.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images