A grid management system for rural governance

Abstract

The present application relates to the technical field of rural power supply management, and discloses a grid management system for rural management, the system operation process comprising: performing coarse-grained division on a power supply area to obtain a power supply cluster set; generating a power supply grid unit division target function of the power supply cluster set by using a power supply grid unit division model, optimizing and solving the power supply grid unit division target function to obtain an optimal grid unit division strategy, performing grid unit division on the power supply area in the countryside, and distributing power supply maintenance tasks according to the divided grid units. The present application generates a power supply grid unit division target function of the power supply cluster set by using a power supply grid unit division model, performs grid unit division on the power supply cluster set obtained by coarse-grained division, regards all power supply areas in the grid unit as the power supply management area of the grid unit, and allocates a grid officer to each power supply management area for power supply management, thereby improving the efficiency of rural power supply management.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of rural power supply governance, and particularly relates to a grid management system for rural governance. BACKGROUND

[0002] With the advancement of urban-rural integration in China, the construction and management of rural power infrastructure have become an important guarantee for realizing rural economic development and improving the quality of life of villagers. As the foundation of rural production and life, the stability, coverage and quality of power supply directly affect the economic development and residents' life in rural areas. In recent years, the state has vigorously promoted rural power grid reconstruction and construction projects, and the level of rural power grid hardware facilities has been greatly improved. However, in terms of management and maintenance, many rural power supply governance still has many problems, such as old power supply facilities, insufficient management forces, and untimely response to sudden power outages. In addition, the geographical environment of rural areas is complex, the population distribution is relatively dispersed, the power supply line is long and difficult to maintain, and the power supply support capacity and management efficiency are generally low.

[0003] In order to cope with the above challenges, grid management is introduced into the field of rural power supply governance, so as to improve management efficiency by dividing rural power systems into small units or grids, and refining the management area. After each grid is divided, a special person or team is equipped to be responsible for the patrol, maintenance and information feedback of power supply equipment, while ensuring that power equipment failures can be handled at the first time. Grid power management can not only help reduce power maintenance costs, but also ensure the improvement of service quality and effectively guarantee power supply stability.

[0004] However, the current grid division method is mostly based on administrative regions or power grid coverage, without fully considering the actual population density, line length and power supply demand differences in different places. For example, there may be grid areas of the same size in remote mountainous areas and densely populated rural areas, but the power supply line length and population density of the former are obviously larger, resulting in uneven work burden of grid staff and difficulty in efficient maintenance of part of grid equipment. Therefore, a reasonable grid division method is still a problem to be solved in the grid governance of rural power supply. In view of this problem, the present application proposes a grid management system for rural governance to optimize the division of rural power supply grid and balance the work burden. SUMMARY

[0005] In view of the above, the present application provides a grid management system for rural governance, collects regional data of different power supply areas, uses the regional position distance between power supply areas for constraint, realizes the normalized data constraint regional distance quantization representation, and takes the average regional distance as the truncation distance for density calculation, combines the membership for fuzzy clustering, obtains the final cluster center and power supply cluster, and realizes the coarse-grained division of the power supply area.

[0006] To achieve the above object, the present application provides a grid management system for rural governance, comprising the following steps:

[0007] S1: collecting the regional position, power transmission line length, population and power load data of different power supply areas in the countryside and performing coarse-grained division on the power supply areas to obtain a power supply cluster set, wherein the multi-factor fusion fuzzy clustering is the implementation method of coarse-grained division;

[0008] S2: constructing a power grid cell division model, the power grid cell division model selects the power supply cluster as the core node of the grid cell and the adjacent power supply cluster as the edge node of the grid cell, and divides the power supply cluster into multiple grid cells;

[0009] S3: generating the power grid cell division target function of the power supply cluster set by using the power grid cell division model, optimizing and solving the power grid cell division target function to obtain the optimal grid cell division strategy, wherein the improved lion swarm algorithm is the implementation method of model optimization and solution;

[0010] S4: performing grid cell division on the power supply areas in the countryside according to the optimal grid cell division strategy, and distributing the power supply maintenance tasks according to the divided grid cells.

[0011] As a further improved method of the present application:

[0012] Optionally, the S1 step of collecting the regional position, power transmission line length, population and power load data of different power supply areas in the countryside comprises:

[0013] Collecting the regional position, power transmission line length, population and power load data of different power supply areas in the countryside, in the embodiment of the present application, the power supply areas in the countryside are buildings in the countryside, and the collected regional data set of the power supply areas is:

[0014]

[0015] wherein:

[0016] x n represents the area data of the collected nth power supply area, and N represents the total number of power supply areas in the rural area;

[0017] represents the area position, the length of the power transmission line, the population, and the power load data of the nth power supply area, respectively;

[0018] represents the length of the power transmission line between the nth power supply area and the nearest power source, wherein the power source includes a power plant and a transformer substation;

[0019] is the average daily power consumption of the power supply area;

[0020] The area data of different power supply areas is combined to perform coarse-grained division on the power supply areas, divide the power supply areas into K power supply clusters, each power supply cluster has multiple power supply areas, and a power supply cluster set is obtained.

[0021] Optionally, the area data of different power supply areas is combined to perform coarse-grained division on the power supply areas, divide the power supply areas into K power supply clusters, and obtain a power supply cluster set, comprising:

[0022] S11: Based on the area data of different power supply areas, the area distance between any two power supply areas is calculated; wherein the area distance between the nth power supply area and the qth power supply area is DIS(x n ,x q ):

[0023]

[0024] wherein:

[0025] represents the Euclidean distance between the area positions ;

[0026] exp(·) represents an exponential function with a natural constant as the base;

[0027] δ(·) represents a normalization process;

[0028] represents the minimum value of for any n, q ∈ [1, N], n ≠ q, , i ∈ {2, 3, 4};

[0029] represents the maximum value of for any n, q ∈ [1, N], n ≠ q, .

[0030] denotes the minimum value of for any n, q ∈ [1, N], n ≠ q,

[0031] denotes the maximum value of for any n, q ∈ [1, N], n ≠ q,

[0032] S12: Calculate the average area distance AVG between any two power supply areas:

[0033]

[0034] S13: In combination with the average area distance and the area distance between the power supply areas, the area density of any power supply area is calculated, wherein the area density of the nth power supply area is n :

[0035]

[0036] wherein:

[0037] S(·) denotes an indicator function;

[0038] S14: According to the area density, the cluster center index of any power supply area is calculated, wherein the cluster center index of the nth power supply area is n :

[0039] G n = τ n ρ n

[0040]

[0041] wherein:

[0042] τ n denotes the cluster center distance index of the nth power supply area, DIS max denotes a preset maximum cluster center distance index;

[0043] denotes the minimum area distance between the nth power supply area and all power supply areas with an area density greater than n ρ

[0044] S15: Select the K power supply areas with the highest cluster center index as the K cluster centers, and use fuzzy clustering to cluster the power supply areas that are not cluster centers into the power supply cluster where the cluster center is located, to obtain K power supply clusters; wherein the area data of the cluster center of the kth power supply cluster is k ,k ∈ [1, K]. ​​

[0045] Optionally, the step S2 of constructing the power grid cell division model comprises:

[0046] The power grid cell division model selects power supply clusters as core nodes of the grid cells, selects adjacent power supply clusters as edge nodes of the grid cells, and divides the power supply clusters into a plurality of grid cells, wherein the power grid cell division model comprises a core node selection layer, a grid cell generation layer, and a grid cell evaluation layer;

[0047] The process of dividing the grid cells by using the power grid cell division model is as follows:

[0048] S21: The core node selection layer selects a plurality of power supply clusters from the K power supply clusters as core nodes of the grid cells;

[0049] S22: The grid cell generation layer is configured to calculate the distance between the power supply cluster of a non-grid cell core node and the grid cell core node, and select the power supply cluster as the edge node of the grid cell of the closest grid cell core node, wherein the distance between the kth power supply cluster and the k+1th power supply cluster is DIS(c k ,c k+1 );

[0050] S23: One grid cell core node and a plurality of grid cell edge nodes around the grid cell core node are selected as one grid cell;

[0051] S24: The grid cell evaluation layer comprehensively evaluates the rationality of the grid cell to obtain a comprehensive evaluation result of the grid cell, wherein the comprehensive evaluation indexes include a population density index, an electricity consumption density index, and a regional distribution index, and the comprehensive evaluation result of the rth grid cell is V r :

[0052]

[0053] wherein:

[0054] count(r) represents the sum of the population numbers of all power supply areas in the rth grid cell;

[0055] area(r) represents the land area of the rth grid cell;

[0056] represents a population density threshold value;

[0057] ε1, ε2, and ε3 represent control parameters of the population density index, the regional distribution index, and the electricity consumption density index, respectively;

[0058] w1, w2, and w3 represent index weights of the population density index, the regional distribution index, and the electricity consumption density index, respectively; and

[0059] distance(r) represents the shortest Euclidean distance from other grid cells to the rth grid cell;

[0060] represents the regional distribution index threshold value;

[0061] μ r represents the average of all power supply cluster electricity load data in the rth grid cell;

[0062] σ r represents the standard deviation of all power supply cluster electricity load data in the rth grid cell.

[0063] Optionally, the power grid cell division target function of the power supply cluster set generated in the S3 step includes:

[0064] The power grid cell division model is used to divide the power supply cluster set into grid cells, and based on the comprehensive evaluation results of the grid cells, a power grid cell division target function of the power supply cluster set is generated, wherein the power grid cell division target function is:

[0065]

[0066] θ=(θ1,θ2,...,θ r ,...,θ R )

[0067] wherein:

[0068] θ represents the grid cell division strategy, θ1, θ2,..., θ r ,...,θ R represent the regional positions of the grid cell core nodes in the R grid cells, θ r represents the regional position of the grid cell core node in the rth grid cell, and R represents the number of grid cells to be generated;

[0069] V represents the evaluation adjustment parameter;

[0070] represents the comprehensive evaluation result of the grid cell with the regional position θ r as the grid cell core node.

[0071] Optionally, the power grid cell division target function is optimized and solved to obtain an optimal grid cell division strategy, including:

[0072] S31: The power grid cell division model is used to select R grid cell core nodes, and the regional positions of the grid cell core nodes are extracted as the first group of initial solutions θ 0(0):

[0073]

[0074] wherein:

[0075] represents the area position of the selected rth grid unit core node;

[0076] S32: iteratively mapping the first group of initial solutions to obtain H groups of initial solutions, wherein the generation formula of the hth group of initial solutions is:

[0077]

[0078] wherein:

[0079] rand(0,1) represents a random number between 0 and 1;

[0080] θ 0 (h) represents the hth group of initial solutions, h∈[1,H];

[0081] I represents a vector of 1 row and R columns, and all vector values are 0;

[0082] S33: setting the current iteration number of each group of initial solutions as b, and the maximum iteration number as B, then the bth iteration solution of the hth group of initial solutions is θ b (h), and the initial value of b is 0;

[0083] S34: normalizing each group of iteration solutions, wherein the normalization result of the iteration solution θ b (h) is The normalization processing is to convert the area position in the iteration solution to the area position of the nearest cluster center;

[0084] S35: substituting the normalized iteration solution into the power grid cell division objective function to obtain the objective function value of the iteration solution, wherein the objective function value of the iteration solution is

[0085]

[0086] and the iteration solution with the highest objective function value is taken as the optimal solution obtained by the bth iteration

[0087] S36: taking the iteration solution with an objective function value higher than a preset threshold as a lioness position coordinate, and taking other iteration solutions as lion cub position coordinates, and iteratively updating the position coordinates by using two kinds of lion group position updating methods; if is a lioness position coordinate, then the iteration formula is:

[0088]

[0089] wherein:

[0090] L represents a random number between 0 and 1;

[0091] g b (h) represents the iteration solution with the maximum objective function value in the bth iteration process of the initial solution of the hth group;

[0092] Sim b (h) represents the cub position coordinates with the highest similarity;

[0093] represents the lioness position perturbation parameter;

[0094] β b represents the iteration factor;

[0095] rand(0,1) represents a random number between 0 and 1;

[0096] If is the cub position coordinates, the iteration formula is:

[0097]

[0098] wherein:

[0099] represents the mean value of the Hth group of iteration solutions obtained in the bth iteration;

[0100] represents the cub position perturbation parameter;

[0101] S37: taking the iteration position coordinates as the iteration solution, setting b = b + 1, returning to step S34 until the maximum iteration number is reached, and substituting the normalized iteration solution at this time into the power grid cell division objective function, taking the iteration solution with the maximum objective function value as the optimal grid cell division strategy wherein represents the area position of the rth grid cell core node.

[0102] Optionally, the S4 step of performing grid cell division on the power supply area in the countryside according to the optimal grid cell division strategy and performing power supply maintenance task allocation comprises:

[0103] performing grid cell division on the power supply area in the countryside according to the optimal grid cell division strategy, wherein the grid cell division process of the power supply area is:

[0104] ​S41: Selecting R region positions according to the optimal grid unit division strategy, and taking the power supply cluster corresponding to the cluster center consistent with the R region positions as the core node of the R grid units;

[0105] S42: Selecting the power supply cluster as the edge node of the grid unit by using the power supply grid unit division model, and taking one grid unit core node and multiple grid unit edge nodes around it as one grid unit;

[0106] S43: Taking all power supply regions in the grid unit as the power supply management region of the grid unit, and assigning a grid member to each power supply management region for power supply management.

[0107] Optionally, in the S15 step, the K power supply regions with the highest cluster center indicators are selected as the K cluster centers, and the non-cluster center power supply regions are clustered into the power supply cluster where the cluster center is located by using a fuzzy clustering method, comprising:

[0108] S151: Initialize the fuzzy membership of the non-cluster center power supply region to the cluster center, wherein the fuzzy membership of the mth non-cluster center power supply region to the kth cluster center is wherein m∈[1,M], M represents the total number of non-cluster center power supply regions, and k∈[1,K];

[0109] S152: Set the current clustering iteration number of fuzzy clustering as t, and the fuzzy membership of the tth iteration result is The initial value of t is 0, and the maximum value is Max;

[0110] S153: Iterating the fuzzy membership, wherein the iteration formula of the fuzzy membership is:

[0111]

[0112] wherein:

[0113] x t (m) represents the region data of the mth non-cluster center power supply region after the tth iteration, m∈[1,M], and M represents the total number of current non-cluster center power supply regions;

[0114] represents the region data of the kth cluster center after the tth iteration; is the cluster center selected based on the cluster center indicator;

[0115] U t represents the fuzzy membership matrix composed of the fuzzy membership obtained after the tth iteration, U t is a matrix with M rows and K columns, a fuzzy membership matrix U t a value of a matrix element in the mth row and the kth column;

[0116] S154: Based on the fuzzy membership obtained by iteration, the cluster center is iterated, and the iteration formula of the kth cluster center is:

[0117]

[0118] S155: Let t=t+1, return to step S153 until the maximum iteration number is reached, and the K cluster centers obtained by the current iteration are taken as the final cluster centers, the fuzzy membership of the power supply area of the non-cluster center to the K final cluster centers is calculated, the power supply area of the non-cluster center is merged into the power supply cluster where the final cluster center with the highest fuzzy membership is located, and K power supply clusters are obtained.

[0119] To solve the above problems, the present application provides a grid management system for rural governance, the system comprises:

[0120] The power supply cluster division module is used for collecting the area position, power transmission line length, population quantity and power consumption load data of different power supply areas in the countryside and performing coarse-grained division on the power supply areas to obtain a power supply cluster set.

[0121] The grid unit division module is used for constructing a power supply grid unit division model, selecting the power supply cluster as a grid unit core node, selecting the adjacent power supply cluster as a grid unit edge node, and dividing the power supply cluster into a plurality of grid units.

[0122] The grid management device is used for generating a power supply grid unit division target function of the power supply cluster set by using the power supply grid unit division model, optimizing and solving the power supply grid unit division target function, obtaining an optimal grid unit division strategy, performing grid unit division on the power supply areas in the countryside according to the optimal grid unit division strategy, and performing power supply maintenance task distribution according to the divided grid units.

[0123] To solve the above problems, the present application further provides an electronic device, the electronic device comprises:

[0124] The memory stores at least one instruction;

[0125] The communication interface realizes the communication of the electronic device; and

[0126] The processor executes the instructions stored in the memory to realize the above-mentioned grid management system for rural governance.

[0127] In order to solve the above problems, the present application also provides a computer readable storage medium, the computer readable storage medium stores at least one instruction, the at least one instruction is executed by the processor in the electronic device to realize the grid management system for rural governance.

[0128] Compared with the prior art, the present application provides a grid management system for rural governance, which has the following advantages:

[0129] Firstly, the present application provides a power supply area coarse-grained division method, collects regional data of different power supply areas, uses regional position distance between power supply areas as a constraint, the closer the regional position distance, the greater the influence of the difference between the population quantity, the length of the power transmission line and the power load on the regional data, realizes the normalized data constraint regional distance quantization representation, and takes the average regional distance as the truncation distance to perform density calculation to obtain the density of different power supply areas, and then selects the initial cluster center of the power supply cluster, and combines the membership degree of the non-cluster center to perform membership degree iteration to obtain the final cluster center and the power supply cluster, thereby realizing coarse-grained division of the power supply area.

[0130] Meanwhile, the present application provides a grid unit generation method, calculates the evaluation result of the divided grid unit according to the population density index, the geographical distribution index and the power density index, divides the grid unit of the power supply cluster set by using the power supply grid unit division model, generates the power supply grid unit division target function of the power supply cluster set based on the comprehensive evaluation result of the grid unit, and solves the position of the grid unit core node with the optimal coverage area, power load and population density of each grid unit as the target, thereby realizing the division of the grid unit in the rural area, taking all the power supply areas in the grid unit as the power supply management area of the grid unit, and allocating a grid officer to each power supply management area for power supply governance, and optimizing the lion group optimization algorithm in the solving process, so that the mother lion position coordinate iteration is not only related to the historical optimal position coordinate of the mother lion, but also exchanges with the cubs, timely acquires and fully utilizes the effective information in the population, thereby realizing a more efficient optimization mechanism, and using the disturbance parameter to improve the diversity of the cubs position and the mother lion position, reduce the number of iterations required for convergence, and further improve the optimization speed and accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0131] Figure 1 A flowchart of a grid management system for rural governance provided by an embodiment of the present application is shown in the figure;

[0132] Figure 2 A functional module diagram of a grid management system for rural power supply governance provided by an embodiment of the present application is shown in the figure;

[0133] Figure 2The grid management system for rural governance comprises a rural power supply governance grid management system, a power supply cluster division module, a grid unit division module, and a grid management device.

[0134] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0135] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0136] Embodiments of the present application provide a grid management system for rural governance. The execution subject of the grid management system for rural governance includes but is not limited to at least one of the electronic devices capable of being configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the grid management system for rural governance can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server, or a cloud server cluster.

[0137] Embodiment 1

[0138] A grid management system for rural governance comprises the following steps:

[0139] S1: Collecting the area position, power transmission line length, population number and power load data of different power supply areas in the rural area and performing coarse-grained division on the power supply areas to obtain a power supply cluster set.

[0140] The S1 step of collecting the area position, power transmission line length, population number and power load data of different power supply areas in the rural area comprises:

[0141] The area position, power transmission line length, population number and power load data of different power supply areas in the rural area are collected. In the embodiments of the present application, the power supply areas in the rural area are buildings in the rural area, and the collected area data set of the power supply areas is:

[0142]

[0143] Wherein:

[0144] x n represents the area data of the n-th power supply area, and N represents the total number of power supply areas in the rural area;

[0145] represents the area position, power transmission line length, population number and power load data of the n-th power supply area, respectively;

[0146] This represents the length of the transmission line between the nth power supply area and the nearest power source, where the power source includes power plants and substations;

[0147] This represents the average daily power consumption in the power supply area.

[0148] By combining regional data from different power supply areas, the power supply areas are divided into K power supply clusters, with each power supply cluster containing multiple power supply areas, thus obtaining a set of power supply clusters.

[0149] The process involves combining regional data from different power supply areas to coarsely divide the power supply areas into K power supply clusters, resulting in a set of power supply clusters, including:

[0150] S11: Based on the regional data of different power supply areas, calculate the regional distance between any two power supply areas; where the regional distance between the nth power supply area and the qth power supply area is DIS(x n ,x q ):

[0151]

[0152] in:

[0153] Indicates the location of the area The Euclidean distance between them;

[0154] exp(·) denotes an exponential function with the natural constant as its base;

[0155] δ(·) represents the normalization process;

[0156] This means that for any n, q ∈ [1, N], n ≠ q. The minimum value, i∈{2,3,4};

[0157] This means that for any n, q ∈ [1, N], n ≠ q. The maximum value;

[0158] This means that for any n, q ∈ [1, N], n ≠ q. The minimum value;

[0159] This means that for any n, q ∈ [1, N], n ≠ q. The maximum value;

[0160] S12: Calculate the average area distance AVG between any two power supply areas.

[0161]

[0162] S13: Calculate the area density of any power supply area according to the average area distance and the area distance between power supply areas, wherein the area density of the nth power supply area is n :

[0163]

[0164] wherein:

[0165] S(·) represents an indicator function;

[0166] S14: Calculate the cluster center index of any power supply area according to the area density, wherein the cluster center index of the nth power supply area is G n :

[0167] G n = τ n ρ n

[0168]

[0169] wherein:

[0170] τ n represents the cluster center distance index of the nth power supply area, DIS max represents the preset maximum cluster center distance index;

[0171] represents the minimum area distance between the nth power supply area and all power supply areas with an area density greater than ρ n .

[0172] S15: Select the K power supply areas with the highest cluster center index as the K cluster centers, and use fuzzy clustering to cluster the power supply areas that are not cluster centers into the power supply cluster where the cluster center is located, to obtain K power supply clusters; wherein the area data of the cluster center of the kth power supply cluster is c k ,k∈[1,K].

[0173] S2: Construct a power supply grid unit division model, which selects a power supply cluster as a grid unit core node, selects a neighboring power supply cluster as a grid unit edge node, and divides the power supply cluster into multiple grid units.

[0174] The step S2 of constructing the power supply grid unit division model comprises:

[0175] The power supply grid unit division model selects a power supply cluster as a grid unit core node, selects an adjacent power supply cluster as a grid unit edge node, and divides the power supply cluster into multiple grid units, wherein the power supply grid unit includes a core node selection layer, a grid unit generation layer, and a grid unit evaluation layer;

[0176] The process of grid unit division using the power supply grid unit division model is as follows:

[0177] S21: The core node selection layer selects multiple power supply clusters from the K power supply clusters as grid unit core nodes;

[0178] S22: The grid unit generation layer is used to calculate the distance between the power supply cluster of the non-grid unit core node and the grid unit core node, and the power supply cluster is taken as the grid unit edge node of the nearest grid unit core node, wherein the distance between the kth power supply cluster and the k+1th power supply cluster is DIS(c k ,c k+1 );

[0179] S23: One grid unit core node and multiple grid unit edge nodes around it are taken as one grid unit;

[0180] S24: The grid unit evaluation layer comprehensively evaluates the rationality of the grid unit to obtain a comprehensive evaluation result of the grid unit, wherein the comprehensive evaluation indexes include a population density index, an electricity consumption density index, and a regional distribution index, wherein the comprehensive evaluation result of the rth grid unit is V r :

[0181]

[0182] wherein:

[0183] count(r) represents the sum of the population numbers of all power supply areas in the rth grid unit;

[0184] area(r) represents the land area of the rth grid unit;

[0185] represents a population density threshold value;

[0186] ε1, ε2, and ε3 represent control parameters of the population density index, the regional distribution index, and the electricity consumption density index, respectively;

[0187] w1, w2, and w3 represent index weights of the population density index, the regional distribution index, and the electricity consumption density index, respectively; let

[0188] distance(r) represents the shortest Euclidean distance from other grid units to the rth grid unit;

[0189] representing a regional distribution index threshold value;

[0190] μ r representing the mean of the electricity load data of all power supply clusters in the rth grid unit;

[0191] σ r representing the standard deviation of the electricity load data of all power supply clusters in the rth grid unit.

[0192] S3: generating a power grid unit division target function of the power supply cluster set using the power grid unit division model, and optimizing and solving the power grid unit division target function to obtain an optimal grid unit division strategy.

[0193] The power grid unit division target function of the power supply cluster set is generated using the power grid unit division model in the S3 step, and includes:

[0194] The power grid unit division target function of the power supply cluster set is generated using the power grid unit division model, and based on the comprehensive evaluation result of the grid unit, the power grid unit division target function is:

[0195]

[0196] θ=(θ1,θ2,...,θ r ,...,θ R )

[0197] Wherein:

[0198] θ represents the grid unit division strategy, θ1, θ2,..., θ r ,...,θ R represent the regional position of the grid unit core node in the R grid units, θ r represents the regional position of the grid unit core node in the rth grid unit, and R represents the number of grid units to be generated;

[0199] V represents an evaluation adjustment parameter;

[0200] represents the comprehensive evaluation result of the grid unit with the regional position θ r as the grid unit core node.

[0201] Optionally, the power grid unit division target function is optimized and solved to obtain an optimal grid unit division strategy, and includes:

[0202] S31: Select R grid cell core nodes using the power grid cell division model, and extract the regional position of the grid cell core node as the first group of initial solutions θ 0 (0):

[0203]

[0204] wherein:

[0205] represents the regional position of the selected rth grid cell core node;

[0206] S32: Iterative mapping of the first group of initial solutions to obtain H groups of initial solutions, wherein the generation formula of the hth group of initial solutions is:

[0207]

[0208] wherein:

[0209] rand(0,1) represents a random number between 0 and 1;

[0210] θ 0 (h) represents the hth group of initial solutions, h∈[1,H];

[0211] I represents a vector of 1 row and R columns, and all vector values are 0;

[0212] S33: Set the current iteration number of each group of initial solutions as b, and the maximum iteration number as B, then the bth iteration solution of the hth group of initial solutions is θ b (h), and the initial value of b is 0;

[0213] S34: Normalization processing is performed on each group of iteration solutions, wherein the normalization processing result of the iteration solution θ b (h) is The normalization processing is to convert the regional position in the iteration solution to the regional position of the nearest cluster center;

[0214] S35: Substitute the normalized iteration solution into the power grid cell division objective function to obtain the objective function value of the iteration solution, wherein the objective function value of the iteration solution is

[0215]

[0216] and the iteration solution with the highest objective function value is taken as the optimal solution obtained by the bth iteration

[0217] S36: The iteration solution with the target function value higher than the preset threshold is taken as the lioness position coordinate, and the other iteration solution is taken as the cub position coordinate. The position coordinate is iterated by using two kinds of lion group position updating methods respectively; if is the lioness position coordinate, the iteration formula is:

[0218]

[0219] wherein:

[0220] g b (h) represents the iteration solution with the maximum target function value in the bth iteration process of the hth group of initial solutions;

[0221] Sim b (h) represents the cub position coordinate with the highest similarity to ; wherein the calculation method of the similarity is the cosine similarity algorithm;

[0222] represents the lioness position disturbance parameter;

[0223] β b represents the iteration factor;

[0224] rand(0,1) represents a random number between 0 and 1;

[0225] L represents a random number between 0 and 1;

[0226] if is the cub position coordinate, the iteration formula is:

[0227]

[0228] wherein:

[0229] represents the mean value of the Hth group of iteration solutions obtained in the bth iteration;

[0230] S37: The iteration obtained position coordinate is taken as the iteration solution, b is set to b+1, and step S34 is returned until the maximum iteration number is reached. The normalized iteration solution at this time is substituted into the power grid cell division target function, and the iteration solution with the maximum target function value is taken as the optimal grid cell division strategy wherein represents the area position of the rth grid cell core node.

[0231] S4: The power supply area in the countryside is divided into grid cells according to the optimal grid cell division strategy, and the power supply maintenance tasks are distributed according to the divided grid cells.

[0232] The S4 step is to divide the power supply area in the countryside into grid cells according to the optimal grid cell division strategy, and to assign the power supply maintenance tasks, including:

[0233] The power supply area in the countryside is divided into grid cells according to the optimal grid cell division strategy, and the grid cell division process of the power supply area is:

[0234] S41: Select R area positions according to the optimal grid cell division strategy, and select the power supply cluster corresponding to the cluster center consistent with the R area positions as the R grid cell core node;

[0235] S42: Select the power supply cluster as the grid cell edge node using the power supply grid cell division model, and select the grid cell core node and the surrounding multiple grid cell edge nodes as a grid cell;

[0236] S43: All power supply areas in the grid cell are regarded as the power supply management area of the grid cell, and a grid worker is assigned to each power supply management area for power supply management.

[0237] Embodiment 2:

[0238] As shown in Figure 2 , it is a functional module diagram of the grid management system for rural governance provided by an embodiment of the present application, which can realize the grid management system for rural governance in embodiment 1.

[0239] The grid management system for rural governance 100 can be installed in an electronic device. According to the realized function, the grid management system for rural governance can include a power supply cluster division module 101, a grid cell division module 102, and a grid management device 103. The modules of the present application can also be called units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0240] The power supply cluster division module 101 is used to collect the area position, power transmission line length, population quantity and power load data of different power supply areas in the countryside, and to perform coarse-grained division on the power supply area to obtain a power supply cluster set;

[0241] The grid cell division module 102 is used to construct a power supply grid cell division model, select a power supply cluster as a grid cell core node, select a neighboring power supply cluster as a grid cell edge node, and divide the power supply cluster into multiple grid cells;

[0242] The grid management device 103 is configured to generate a power grid cell division target function of the power grid cell division model, optimize and solve the power grid cell division target function, obtain an optimal grid cell division strategy, divide the power supply area in the countryside according to the optimal grid cell division strategy, and distribute the power supply maintenance tasks according to the divided grid cells.

[0243] In detail, the modules in the grid management system 100 for rural governance in the embodiments of the present application use the same technical means as the grid management system for rural governance in the above Figure 1 application, and can produce the same technical effects, which will not be described here.

[0244] It should be understood that the embodiments are only for illustration, and the scope of the patent application is not limited by the structure.

[0245] It should be noted that the above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. And the terms "include", "contain" or any other variants in this paper are intended to cover non-exclusive inclusion, so that the process, device, article or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, device, article or method. Without more limitations, the element defined by the sentence "including a" does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0246] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server or network device) execute the method described in each embodiment of the present application.

[0247] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation made by using the content of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A grid-based management method for rural power supply governance, characterized in that, The method includes: S1: Collect data on the location, transmission line length, population, and electricity load of different power supply areas in rural areas, and perform coarse-grained division of power supply areas to obtain a set of power supply clusters; S2: Construct a power supply grid cell partitioning model. The power supply grid cell partitioning model selects power supply clusters as the core nodes of the grid cells and neighboring power supply clusters as the edge nodes of the grid cells, dividing the power supply clusters into multiple grid cells. S3: Use the power supply grid cell partitioning model to generate the power supply cluster set's power supply grid cell partitioning objective function, optimize the power supply grid cell partitioning objective function, and obtain the optimal grid cell partitioning strategy; S4: Divide the power supply area in the countryside into grid cells according to the optimal grid cell division strategy, and assign power supply maintenance tasks according to the divided grid cells. By combining regional data from different power supply areas, the power supply areas are coarsely divided into K power supply clusters, resulting in a set of power supply clusters, including: S11: Based on the regional data of different power supply areas, calculate the regional distance between any two power supply areas; where the regional distance between the nth power supply area and the qth power supply area is... ; S12: Calculate the average area distance between any two power supply areas. ; S13: Combining the average area distance and the area distance between power supply areas, the area density of any power supply area is calculated, where the area density of the nth power supply area is... ; S14: Based on the regional density, the cluster center index of any power supply region is calculated, where the cluster center index of the nth power supply region is... ; S15: Select the K power supply areas with the highest cluster center index as K cluster centers. Use fuzzy clustering to cluster the power supply areas that are not cluster centers into the power supply clusters where the cluster centers are located, thus obtaining K power supply clusters; where the region data of the cluster center of the kth power supply cluster is... ; Step S3 includes: A power supply cluster set is partitioned into grid cells using a power supply grid cell partitioning model. Based on the comprehensive evaluation results of the grid cells, an objective function for the power supply cluster set's grid cell partitioning is generated. The objective function for the power supply grid cell partitioning is: ； ； in: Indicates the grid cell partitioning strategy, This indicates the region location of the core node of a grid cell within R grid cells. This represents the region location of the core node of the r-th grid cell, where R represents the number of grid cells to be generated. Indicates the evaluation adjustment parameters; Indicated by regional location This is the comprehensive evaluation result of the grid cells, which are the core nodes of the grid cells.

2. The grid-based management method for rural power supply governance as described in claim 1, characterized in that, Step S1 includes: Data on the location, transmission line length, population, and electricity load of different power supply areas in rural areas were collected. The collected regional data set for the power supply areas is as follows: ； in: This represents the regional data collected for the nth power supply area, where N represents the total number of power supply areas in the rural area. The nth power supply area is represented by its location, transmission line length, population, and electricity load data. This represents the length of the transmission line between the nth power supply area and the nearest power source, where the power source includes power plants and substations.

3. The grid-based management method for rural power supply governance as described in claim 1, characterized in that, Step S2 includes: A power supply grid cell partitioning model is constructed. The power supply grid cell partitioning model selects power supply clusters as the core nodes of the grid cells and neighboring power supply clusters as the edge nodes of the grid cells, dividing the power supply clusters into multiple grid cells. The power supply grid cell includes a core node selection layer, a grid cell generation layer, and a grid cell evaluation layer. The process of mesh generation using the power supply mesh cell generation model is as follows: S21: The core node selection layer selects multiple power supply clusters from K power supply clusters as core nodes of the grid cell; S22: The mesh cell generation layer is used to calculate the distance between the power supply clusters of non-mesh cell core nodes and the mesh cell core nodes, and to designate the power supply clusters as the mesh cell edge nodes of the nearest mesh cell core node, where the distance between the k-th power supply cluster and the (k+1)-th power supply cluster is... ; S23: Treat a core node of a grid cell and multiple edge nodes of surrounding grid cells as a single grid cell; S24: The grid unit evaluation layer comprehensively evaluates the rationality of the grid units, obtaining a comprehensive evaluation result for each grid unit. The comprehensive evaluation indicators include population density, electricity density, and geographical distribution. The comprehensive evaluation result for the r-th grid unit is... .

4. The grid-based management method for rural power supply governance as described in claim 1, characterized in that, The optimization of the objective function for power supply grid cell partitioning to obtain the optimal grid cell partitioning strategy includes: S31: Select R core nodes of the grid cells using the power supply grid cell partitioning model, and extract the regional locations of the core nodes of the grid cells as the first set of initial solutions. ; S32: Iteratively map the first set of initial solutions to obtain H sets of initial solutions; S33: Let the current iteration number of each initial solution group be b, and the maximum iteration number be B. Then the b-th iteration solution of the h-th initial solution group is: The initial value of b is 0; S34: Normalize each set of iterative solutions, where the iterative solutions... The standardization result is The normalization process involves converting the region locations in the iterative solution into the locations of the nearest cluster centers. S35: Substitute the normalized iterative solution into the objective function for power grid cell partitioning to obtain the objective function value of the iterative solution, where the iterative solution... The objective function value is : ； The solution with the highest objective function value is taken as the optimal solution obtained in the b-th iteration. ; S36: Use the iterative solution with the objective function value higher than the preset threshold as the position coordinates of the mother lion, and other iterative solutions as the position coordinates of the cubs. Use two different lion pride position update methods to iterate the position coordinates. S37: Using the position coordinates obtained from the iteration as the iterative solution, let b = b + 1, return to step S34, and continue until the maximum number of iterations is reached. Then, substitute the normalized iterative solution at this point into the power grid cell partitioning objective function, and take the iterative solution with the largest objective function value as the optimal grid cell partitioning strategy. ,in This indicates the region location of the core node of the r-th grid cell.

5. A grid-based management method for rural power supply governance as described in claim 4, characterized in that, The S4 step includes: The power supply area in the rural area is divided into grid cells according to the optimal grid cell partitioning strategy. The grid cell partitioning process for the power supply area is as follows: S41: Select R region locations according to the optimal grid cell partitioning strategy, and take the power supply cluster corresponding to the cluster center that is consistent with the R region locations as the core node of the R grid cells. S42: Using the power supply grid cell partitioning model, select the power supply cluster as the edge node of the grid cell, and take a grid cell core node and multiple surrounding grid cell edge nodes as a grid cell. S43: All power supply areas within a grid cell are designated as power supply management areas for that grid cell, and grid administrators are assigned to each power supply management area to manage power supply.

6. The grid-based management method for rural power supply governance as described in claim 1, characterized in that, Step S15 includes: S151: Initialize and generate the fuzzy membership degree from the power supply region of the non-cluster center to the cluster center, where the fuzzy membership degree from the m-th non-cluster center power supply region to the k-th cluster center is: ,in , M represents the total number of power supply areas outside the cluster center. ; S152: Set the current clustering iteration number of fuzzy clustering to t, then the fuzzy membership degree... The result of the t-th iteration is The initial value of t is 0, and the maximum value is Max; S153: Iterate over the fuzzy membership degree; S154: Iterate over the cluster centers based on the fuzzy membership degrees obtained through iteration; S155: Let t=t+1, return to step S153 until the maximum number of iterations is reached, and take the K cluster centers obtained in the current iteration as the final cluster centers. Calculate the fuzzy membership degree from the power supply area of ​​the non-cluster center to the K final cluster centers, and merge the power supply area of ​​the non-cluster center into the power supply cluster where the final cluster center with the highest fuzzy membership degree is located, to obtain K power supply clusters.

7. A grid-based management system for rural power supply governance, characterized in that, The system includes: The power supply cluster segmentation module is used to collect data on the location, transmission line length, population, and electricity load of different power supply areas in rural areas, and to perform coarse-grained segmentation of the power supply areas to obtain a set of power supply clusters. The grid cell partitioning module is used to construct a power supply grid cell partitioning model. It selects power supply clusters as the core nodes of the grid cells and uses adjacent power supply clusters as the edge nodes of the grid cells to divide the power supply clusters into multiple grid cells. A grid management device is used to generate a power grid unit partitioning objective function for a power supply cluster set using a power supply grid unit partitioning model, optimize and solve the power supply grid unit partitioning objective function to obtain the optimal grid unit partitioning strategy, partition the power supply area in the countryside into grid units according to the optimal grid unit partitioning strategy, and allocate power supply maintenance tasks according to the partitioned grid units, so as to realize a grid management method for rural power supply governance as described in any one of claims 1-6. By combining regional data from different power supply areas, the power supply areas are coarsely divided into K power supply clusters, resulting in a set of power supply clusters, including: S11: Based on the regional data of different power supply areas, calculate the regional distance between any two power supply areas; where the regional distance between the nth power supply area and the qth power supply area is... ; S12: Calculate the average area distance between any two power supply areas. ; S13: Combining the average area distance and the area distance between power supply areas, the area density of any power supply area is calculated, where the area density of the nth power supply area is... ; S14: Based on the regional density, the cluster center index of any power supply region is calculated, where the cluster center index of the nth power supply region is... ; S15: Select the K power supply areas with the highest cluster center index as K cluster centers. Use fuzzy clustering to cluster the power supply areas that are not cluster centers into the power supply clusters where the cluster centers are located, thus obtaining K power supply clusters; where the region data of the cluster center of the kth power supply cluster is... ; Step S3 includes: A power supply cluster set is partitioned into grid cells using a power supply grid cell partitioning model. Based on the comprehensive evaluation results of the grid cells, an objective function for the power supply cluster set's grid cell partitioning is generated. The objective function for the power supply grid cell partitioning is: ； ； in: Indicates the grid cell partitioning strategy, This indicates the region location of the core node of a grid cell within R grid cells. This represents the region location of the core node of the r-th grid cell, where R represents the number of grid cells to be generated. Indicates the evaluation adjustment parameters; Indicated by regional location This is the comprehensive evaluation result of the grid cells, which are the core nodes of the grid cells.

Images