Method and device for optimally dividing grids of power distribution network

Abstract

The invention provides a power distribution network grid optimization division method and device, and relates to the field of power distribution network planning. The method comprises the following steps: acquiring geographic coordinates, electrical loads and operation data of each power supply unit in a target power supply area; constructing a power supply grid division model by using the operation data, and solving the power supply grid division model based on a genetic algorithm to obtain an initial grid division scheme; the power supply grid division model takes the minimum sum of variances of the operation data as an optimization target; based on the geographic coordinate of each power supply unit, calculating the geographic coordinate similarity of each power supply unit in each preliminarily divided power supply grid; based on the electrical load of each power supply unit, respectively calculating the regional function of each power supply unit in each preliminarily divided power supply grid; and determining an optimal grid division scheme based on all power supply units in each power supply grid and the corresponding geographic coordinate similarity and regional function. According to the invention, intelligence and refinement of power supply grid division can be improved.

Description

Technical Field

[0001] The present application relates to the field of distribution network planning, and particularly to a method and device for optimizing the division of distribution network grids. Background Art

[0002] In the current power system, the division of power supply grids is of great significance for ensuring power supply reliability and improving the operation efficiency of the power grid. As an important power supply area, the power supply system in the southern grid of Hebei faces multiple challenges such as uneven load distribution between urban and rural areas, aging equipment, and complex geographical conditions. Traditional methods for dividing power supply grids often rely on empirical judgments and are difficult to accurately reflect the actual operation conditions and future development needs of the power grid.

[0003] Based on the actual work of the southern grid of Hebei, clarifying the division principles of power supply areas, power supply grids, and power supply units in urban and rural areas, and standardizing the division granularity of power supply grids and power supply units are the keys to improving the power grid management level. At the same time, combining the latest national land space planning and the adjustment requirements of power supply areas in each city to formulate a scientific and reasonable power supply area division table is of great significance for ensuring the sustainable development of the power grid.

[0004] However, most of the existing division methods lack intelligent and refined means and are difficult to adapt to the complexity and dynamic changes of the power grid. Therefore, an innovative method for optimizing the division of power supply grids is needed to achieve intelligent and refined division of the power grid. Summary of the Invention

[0005] The present application provides a method and device for optimizing the division of distribution network grids to solve the problem of insufficient intelligence and refinement in the division of distribution network grids in the prior art.

[0006] In a first aspect, the present application provides a method for optimizing the division of distribution network grids, including:

[0007] Obtaining the geographical coordinates, electricity consumption loads, and operation data of each power supply unit in the target power supply area;

[0008] Constructing a power supply grid division model using the operation data of each power equipment, and solving the power supply grid division model based on a genetic algorithm to obtain an initial grid division plan; the power supply grid division model takes the minimum sum of variances of operation data as the optimization goal, and the initial grid division plan includes each initially divided power supply grid in the target power supply area and all power supply units existing in each power supply grid;

[0009] Based on the geographical coordinates of each power supply unit, calculating the geographical coordinate similarity of each power supply unit in each initially divided power supply grid respectively;

[0010] Based on the power consumption load of each power supply unit, calculate the regional functions of each power supply unit in each preliminarily divided power supply grid respectively;

[0011] Based on all the power supply units in each power supply grid and the geographical coordinate similarity and regional functions of the corresponding power supply units, determine the optimal grid division scheme for the target power supply area.

[0012] In a second aspect, the present application provides a device for optimizing the grid division of a distribution network, including:

[0013] A data acquisition module, configured to acquire the geographical coordinates, power consumption load and operation data of each power supply unit in the target power supply area;

[0014] A preliminary division module, configured to construct a power supply grid division model by using the operation data of each power equipment, and solve the power supply grid division model based on a genetic algorithm to obtain an initial grid division scheme; the power supply grid division model takes the minimum sum of variances of the operation data as the optimization objective, and the initial grid division scheme includes each preliminarily divided power supply grid in the target power supply area and all the power supply units existing in each power supply grid;

[0015] A similarity calculation module, configured to calculate the geographical coordinate similarity of each power supply unit in each preliminarily divided power supply grid respectively based on the geographical coordinates of each power supply unit;

[0016] A regional function calculation module, configured to calculate the regional functions of each power supply unit in each preliminarily divided power supply grid respectively based on the power consumption load of each power supply unit;

[0017] A scheme optimal division module, configured to determine the optimal grid division scheme for the target power supply area based on all the power supply units in each power supply grid and the geographical coordinate similarity and regional functions of the corresponding power supply units.

[0018] The present application provides a method and device for optimizing the division of a distribution network grid. By obtaining the geographical coordinates, power consumption loads, and operation data of each power supply unit within a target power supply area; constructing a power supply grid division model using the operation data of each power equipment, and based on the genetic algorithm, solving the power supply grid division model to obtain an initial grid division plan; the power supply grid division model takes the minimum sum of variances of the operation data as the optimization objective, and the initial grid division plan includes each power supply grid initially divided within the target power supply area and all power supply units existing in each power supply grid; based on the geographical coordinates of each power supply unit, calculate the geographical coordinate similarity of each power supply unit in each initially divided power supply grid respectively; based on the power consumption load of each power supply unit, calculate the regional function of each power supply unit in each initially divided power supply grid respectively; based on all power supply units in each power supply grid and the corresponding geographical coordinate similarity and regional function of the power supply units, determine the optimal grid division plan for the target power supply area. The present application realizes the refined division of the distribution network grid through the power supply grid division model, geographical coordinate similarity, and regional function; and by using the power supply grid division model and the genetic algorithm, it can improve the intelligence and automation of the distribution network grid division, provide strong support for constructing a safer, more efficient, and greener intelligent distribution network, thereby enhancing the flexibility and scalability of the entire power grid system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 is the implementation flowchart of the method for optimizing the division of a distribution network grid provided by an embodiment of the present application;

[0021] Figure 2 is the structural schematic diagram of the device for optimizing the division of a distribution network grid provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are presented in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0024] Figure 1 The following is a flowchart for implementing the power distribution network grid optimization and division method provided by the embodiments of this application:

[0025] In step 101, obtain the geographical coordinates, power consumption load, and operation data of each power supply unit within the target power supply area.

[0026] In the embodiments of this application, use the internal terminal devices connected to each power supply unit in the target power supply area to obtain the geographical coordinates, power consumption load, and operation data of each power supply unit. Among them, the operation data includes the annual failure times, operation years, power supply line length, and annual failure operation and maintenance costs of power equipment.

[0027] In a possible implementation manner, before obtaining the geographical coordinates, power consumption load, and operation data of each power supply unit within the target power supply area, the method may further include:

[0028] Obtain the power consumption load of each power supply unit within the target power supply area and the total area of the target power supply area;

[0029] Use the power consumption load of each power supply unit within the target power supply area and the total area of the target power supply area to calculate the saturated load density of the target power supply area;

[0030] Use the saturated load density of the target power supply area to determine the regional power consumption nature of the target power supply area.

[0031] Among them, the saturated load density is a quantitative parameter representing the density of load distribution. It is the average power consumption value per square kilometer, measured in MW / km 2 For measurement.

[0032] Optionally, obtain the power consumption load of each power supply unit within the target power supply area. Here, the power consumption load refers to the average of the historical annual power consumption loads of each power supply unit. And obtain the total area of the target power supply area. Here, the total area is the total occupied area of the target power supply area. Then calculate the sum of the power consumption loads of each power supply unit within the target power supply area, and use the ratio of the sum of the power consumption loads to the total area as the saturated load density of the target power supply area. Finally, use the saturated load density to determine the regional power consumption nature of the target power supply area. Among them, the regional power consumption nature can be divided into the city center of a municipality directly under the Central Government or provincial capital city, urban areas at or above the prefecture level, urban areas at or above the county level, town areas, rural areas, and pastoral areas.

[0033] In addition, in this embodiment, the saturation load density prediction model can also be used to obtain the predicted values of the saturation load density of each power supply unit, and then the predicted values of the saturation load density of each power supply unit are added to determine the saturation load density of the target power supply area.

[0034] The saturation load density prediction model is constructed based on the Deep Belief Network (DBN) model, and the training process is as follows:

[0035] Obtain the historical land use information of each power supply unit, where the historical land use information includes the historical saturation load density and historical geospatial information of each power supply unit;

[0036] Use the Deep Belief Network (DBN) model to construct the saturation load density prediction model;

[0037] Take the geospatial information of each power supply unit as the input and the historical saturation load density of the corresponding power supply unit as the output to train the saturation load density prediction model.

[0038] Preferably, by calculating the saturation load density of the target power supply area, the embodiments of the present application can deeply understand the power demand potential and future development trend of this area. This helps to formulate a more accurate regional electricity use plan, ensure the rational allocation and efficient utilization of power resources. At the same time, it also provides strong data support for subsequent power grid construction and transformation.

[0039] Then, by determining the regional electricity use nature (such as residential area, industrial area, commercial area, etc.) of the target power supply area, the embodiments of the present application help to fully consider the electricity use characteristics and demands of different areas during grid division. Through a differentiated grid division strategy, it can better adapt to the electricity load distribution and change rules of different areas, and improve the rationality and scientific nature of the power grid layout.

[0040] Secondly, after understanding the saturation load density and regional electricity use nature of the target power supply area, the embodiments of the present application can make a forward-looking plan for the power grid based on this information. This includes aspects such as reserving sufficient power capacity, optimizing the power grid structure, and improving equipment performance. In this way, even when the electricity load increases or the electricity use nature changes in the future, the power grid can quickly adapt and maintain stable operation, enhancing the adaptability and flexibility of the power grid.

[0041] Furthermore, by comprehensively considering information such as the saturation load density of the target power supply area, the regional electricity use nature, and the geographical coordinates, electricity load, and operation data of the power supply unit, the embodiments of the present application can more accurately evaluate the importance and potential of each power supply unit. This helps to more reasonably allocate power resources during grid division, avoid waste and idleness of resources, and improve the overall utilization efficiency of power resources.

[0042] Finally, in the process of power grid planning and management, the scientificity and accuracy of decision-making are crucial. Through introducing concepts such as saturated load density and regional electricity consumption nature, and conducting in-depth analysis in combination with actual data, the embodiments of this application provide more comprehensive and accurate information support for decision-makers. This helps decision-makers formulate power grid planning and management strategies more scientifically and improve the scientificity and accuracy of decision-making.

[0043] In a possible implementation manner, after obtaining the geographical coordinates, electricity consumption loads, and operation data of each power supply unit in the target power supply area, the method may further include:

[0044] Perform preprocessing of cleaning, denoising, and normalization on the geographical coordinates, electricity consumption loads, and operation data of each power supply unit in the target power supply area, and use data dimensionality reduction technology to remove redundant data from the preprocessed geographical coordinates, electricity consumption loads, and operation data.

[0045] Optionally, there may be situations such as data errors, data redundancy, or data missing in the initially obtained geographical coordinates, electricity consumption loads, and operation data of each power supply unit. Therefore, in this embodiment, after obtaining the geographical coordinates, electricity consumption loads, and operation data of each power supply unit, preprocessing operations such as cleaning, denoising, and normalization are required for the above data to eliminate defects such as data errors or data missing, and then data dimensionality reduction technology is used to remove redundant data from the preprocessed data to ensure the accuracy of the obtained data, thereby improving the accuracy of subsequent power supply grid division.

[0046] In step 102, a power supply grid division model is constructed using the operation data of each power equipment, and based on the genetic algorithm, the power supply grid division model is solved to obtain an initial grid division scheme; the power supply grid division model takes the minimum sum of variances of the operation data as the optimization goal, and the initial grid division scheme includes each power supply grid initially divided in the target power supply area and all power supply units existing in each power supply grid.

[0047] In the embodiments of this application, a power supply grid division model is constructed using the operation data of each power equipment obtained in step 101, where the power supply grid division model takes the minimization of the sum of variances of the operation data as the optimization goal. Then, the genetic algorithm is used to solve the power supply grid division model to obtain an initial grid division scheme, where the initial grid division scheme includes each power supply grid initially divided in the target power supply area and all power supply units existing in each power supply grid.

[0048] The objective function of the power supply grid division model is:

[0049]

[0050] Where D PD is the variance of the annual failure times of N power devices in each power supply grid. T D is the variance of the operation years of N power devices in each power supply grid. L C is the variance of the power supply line lengths of N power devices in each power supply grid. Y P is the variance of the annual failure operation and maintenance costs of N power devices in each power supply grid. Zn is the annual failure times of the power devices in the nth power supply grid. is the average value of the annual failure times of the power devices in the power supply grids in the target power supply area. is the average value of the operation years of the power devices in the nth power supply grid. L is the average value of the operation years of the power devices in the power supply grids in the target power supply area. Zn is the power supply line length of the nth power supply grid. C is the average value of the power supply line lengths of the power supply grids in the target power supply area. Zn is the annual failure operation and maintenance cost of the nth power supply grid. is the average value of the annual failure operation and maintenance costs of the power devices in the power supply grids in the target power supply area. N is the number of power supply grids in the target power supply area, n is the serial number of the power supply grid, and α1, α2, α3, and α4 are all weight coefficients.

[0051] The constraint conditions of the power supply grid division model can include the power supply user number constraint, the substation capacity constraint, the power supply radius constraint, and the island capacity constraint.

[0052] Among them, the power supply user number constraint is:

[0053]

[0054] Among them, H Zn is the total number of power supply users in the nth power supply grid, and H n is the total number of power supply users in the target power supply area.

[0055] The substation capacity constraint is:

[0056]

[0057] Among them, P j is the active power of the load node j, and C i，p is the confidence capacity of the distributed photovoltaic power source without energy storage within the power supply range of the substation i, and C i，pe is the confidence capacity of the distributed photovoltaic power source with energy storage within the power supply range of the substation i, S i is the capacity of the substation i, and e i is the maximum load rate of the substation i. is the power factor of substation i, j is the load node number, and J is the total number of load nodes.

[0058] The power supply radius constraint is:

[0059] l ij ≤R i

[0060] where l ij is the transmission distance between substation i and load node j, and R i is the maximum power supply radius of substation i.

[0061] The island capacity constraint is:

[0062]

[0063] where P DG，m is the active power of the m-th distributed power source in the island, P LOAD，j is the active power of load node j, M is the total number of distributed power sources in the island, J is the total number of load nodes, m is the number of the distributed power source in the island, and j is the number of the load node.

[0064] The embodiment of the present application constructs a power supply grid division model with the minimization of the sum of variances of operation data as the optimization goal, which narrows the selection range of the power supply grid, improves the accuracy of the preliminary division, and provides a choice for subsequent fine division.

[0065] In a possible implementation manner, based on the genetic algorithm, solving the power supply grid division model to obtain an initial grid division scheme may include:

[0066] Taking each power supply unit in the target power supply area as the initial population, initializing the initial population, and using the initialized initial population as the current population;

[0067] Calculating the fitness of the current population;

[0068] Judging whether the current iteration number is greater than the preset iteration number;

[0069] If the current iteration number is greater than the preset iteration number, then taking the power supply grid composed of each power supply unit in the current population corresponding to the fitness at the current iteration number as the initial grid division scheme;

[0070] If the current iteration number is not greater than the preset iteration number, then performing selection, crossover, and mutation on the current population respectively to generate the next population, updating the current population with the next population, and returning to the step of calculating the fitness of the current population to continue execution.

[0071] Among them, the genetic algorithm randomly selects multiple sample points from the global as the initial points, which can well solve the problem of local optimum. And the evaluation criterion of the genetic algorithm is not limited to the form of the objective function of the traditional derivative. Therefore, the embodiment of the present application uses the genetic algorithm to solve the power supply grid division model, which can solve the complex non-linear programming problem that the traditional algorithm cannot solve.

[0072] Optionally, each power supply unit in the target power supply area is used as the initial population, and the initial population is initialized. The initialized initial population is used as the current population, and then the fitness of the current population is calculated. It is judged whether the current iteration number is greater than the preset iteration number. If the current iteration number is greater than the preset iteration number, each power supply unit under the current population corresponding to the fitness calculated by the current iteration number is used as the initial grid division scheme; if the current iteration number is not greater than the preset iteration number, first perform selection, crossover and mutation on the current population to generate the next population, and then update the current population with the next population, and repeat the iteration operation.

[0073] The embodiment of the present application solves the power supply grid division model based on the genetic algorithm, and can initially automatically find the optimal or near-optimal grid division scheme. This intelligent division method enables the power grid to quickly adapt and make corresponding adjustments in the face of changes such as load growth and equipment update, so as to maintain the stable operation and efficient power supply of the power grid. At the same time, this method also provides strong support for the future expansion and upgrade of the power grid.

[0074] In step 103, based on the geographical coordinates of each power supply unit, the geographical coordinate similarity of each power supply unit in each preliminarily divided power supply grid is calculated respectively.

[0075] In the embodiment of the present application, using the similarity calculation formula and the geographical coordinates of each power supply unit obtained in step 101, the geographical coordinate similarity of each power supply unit in each preliminarily divided power supply grid is calculated respectively.

[0076] Correspondingly, the similarity calculation formula is:

[0077]

[0078] Among them, F1 is the geographical coordinate similarity between the i-th power supply unit and the j-th power supply unit, (x i , y i ) is the geographical coordinate of the i-th power supply unit, (x j , y j ) is the geographical coordinate of the j-th power supply unit, l ij is the adjacent coefficient between the i-th power supply unit and the j-th power supply unit, and l max is the maximum value of the distances between adjacent power supply units.

[0079] In the embodiments of the present application, by calculating the similarity of each power supply unit in each power supply grid, the purpose is to provide a judgment basis for the subsequent fine division of the power supply grid, thereby improving the accuracy of the power supply grid division.

[0080] In step 104, based on the power consumption load of each power supply unit, calculate the regional functions of each power supply unit in each preliminarily divided power supply grid respectively.

[0081] In the embodiments of the present application, use the power consumption load of each power supply unit and the land area of the corresponding power supply unit to determine the regional functions of each power supply unit in each preliminarily divided power supply grid. According to the regional functions, the power supply units in the corresponding power supply grid can be better classified.

[0082] In a possible implementation manner, calculating the regional functions of each power supply unit in each preliminarily divided power supply grid based on the power consumption load of each power supply unit may include:

[0083] Obtain the land area of each power supply unit in the target power supply area;

[0084] Based on the power consumption load and the corresponding land area of each power supply unit in each preliminarily divided power supply grid, calculate the load density of the corresponding power supply unit;

[0085] Determine the regional function of the power supply unit according to the load density of each power supply unit.

[0086] Optionally, obtain the power consumption area of each power supply unit in the target power supply area and the power consumption load of each power supply unit, calculate the load density of each power supply unit in each preliminarily divided power supply grid, and then use the load density of each power supply unit to determine the regional function of the corresponding power supply unit.

[0087] Exemplarily, a certain power supply grid includes 17 power supply units, which are numbered 1 to 17 respectively. According to the land area and power consumption load of each power supply unit, calculate the load density of each power supply unit, so as to determine the regional function of each power supply unit. The specific information is shown in the following table:

[0088]

[0089]

[0090] The embodiments of the present application use the load density to determine the regional function of the power supply unit, providing a basis for the subsequent more refined grid division.

[0091] In step 105, based on all power supply units in each power supply grid, as well as the geographical coordinate similarity and regional function of the corresponding power supply units, an optimal grid division plan for the target power supply area is determined.

[0092] In the embodiment of the present application, each power supply unit in each power supply grid obtained through step 101, the geographical coordinate similarity of each power supply unit obtained through step 103, and the regional function of each power supply unit obtained through step 104 jointly act to determine an optimal grid division plan for the target power supply area. The optimal grid division plan includes the power supply grid division of the target power supply area and all power supply units included in each power supply grid.

[0093] In a possible implementation manner, based on all power supply units in each power supply grid, as well as the geographical coordinate similarity and regional function of the corresponding power supply units, determining an optimal grid division plan for the target power supply area may include:

[0094] For each power supply grid, perform the following steps:

[0095] Judge whether the geographical coordinate similarity of each power supply unit is less than the preset similarity, and whether the regional function of each power supply unit is the same;

[0096] If the geographical coordinate similarity of each power supply unit is greater than the preset similarity, and the regional function of each power supply unit is the same, then determine that this power supply grid is the optimal grid division plan;

[0097] If there are power supply units with geographical coordinate similarity not greater than the preset similarity, and / or power supply units with different regional functions, then remove the power supply units with geographical coordinate similarity not greater than the preset similarity and the power supply units with different regional functions from this power supply grid, and determine the remaining power supply units as the optimal grid division plan.

[0098] Optionally, after the initial grid division plan obtained through the power supply grid division model, the embodiment of the present application also optimizes the initial grid division plan by using the geographical coordinate similarity and regional function of each power supply unit. Specifically, for each power supply grid, perform the following steps:

[0099] Determine whether the geographical coordinate similarity of each power supply unit in the power supply grid is greater than a preset similarity, and whether the regional functions of each power supply unit are the same. If the geographical coordinate similarity of each power supply unit is greater than the preset similarity and the regional functions are the same, then determine the initial grid division plan as the optimal grid division plan for the power supply grid; if there are power supply units with a geographical coordinate similarity not greater than the preset similarity, and / or there is at least one power supply unit with different regional functions, then remove the power supply units with a geographical coordinate similarity not greater than the preset similarity and the power supply units with different regional functions from the power supply grid, and form a new power supply grid with the remaining power supply units as the optimal grid division plan for the power supply grid.

[0100] First of all, based on the initial grid division plan, the embodiments of the present application can more accurately identify power supply units with similar electricity consumption characteristics and regional characteristics by introducing two dimensions of geographical coordinate similarity and regional function, so as to divide them into the same grid. This precise division helps to improve the efficiency of subsequent power management, planning, and maintenance.

[0101] Furthermore, under the optimal grid division plan, power companies can more accurately grasp the electricity consumption demands and characteristics of each grid, so as to allocate and dispatch power resources in a targeted manner. This helps to reduce resource waste and improve the reliability and economy of power supply.

[0102] Then, since the power supply units within each optimal grid have a high degree of similarity in geographical coordinates and regional functions, power companies can provide personalized power supply services for different grids according to these characteristics. For example, provide high-reliability power supply guarantees for industrial zone grids, and pay more attention to the comfort and energy conservation of power supply for residential area grids.

[0103] Secondly, by dividing power supply units with similar geographical coordinates and the same regional functions into the same grid, the embodiments of the present application can reduce the unstable factors in the operation of the power grid caused by excessive differences in power supply units. This helps to reduce the failure rate of the power grid and improve the overall operation efficiency and stability of the power grid.

[0104] Moreover, the embodiments of the present application provide a clear framework and basis for power grid planning and management. Power companies can carry out more refined power grid planning, equipment layout, and operation and maintenance management based on these grids, thereby reducing management costs and improving management efficiency.

[0105] Finally, based on the optimal grid division, power companies can more flexibly adjust and optimize power supply strategies to adapt to the development needs of different regions. This helps to promote the coordinated development of various industries within the region and improve the overall economic and social benefits.

[0106] The present application provides a method for optimizing the division of a distribution network grid. The method includes obtaining the geographical coordinates, power consumption loads, and operation data of each power supply unit in the target power supply area; constructing a power supply grid division model using the operation data of each power equipment, and solving the power supply grid division model based on a genetic algorithm to obtain an initial grid division plan. The power supply grid division model aims to minimize the sum of variances of the operation data. The initial grid division plan includes each initially divided power supply grid in the target power supply area and all power supply units existing in each power supply grid. Based on the geographical coordinates of each power supply unit, the geographical coordinate similarity of each power supply unit in each initially divided power supply grid is calculated respectively. Based on the power consumption load of each power supply unit, the regional function of each power supply unit in each initially divided power supply grid is calculated respectively. Based on all power supply units in each power supply grid and the geographical coordinate similarity and regional function of the corresponding power supply units, the optimal grid division plan for the target power supply area is determined. Through the power supply grid division model, geographical coordinate similarity, and regional function, the present application realizes the refined division of the distribution network grid. Moreover, by using the power supply grid division model and the genetic algorithm, the intelligence and automation of the distribution network grid division can be improved, providing strong support for constructing a safer, more efficient, and greener intelligent distribution network, thereby enhancing the flexibility and scalability of the entire power grid system.

[0107] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0108] The following is the device embodiment of the present application. For the details not described in detail, reference can be made to the corresponding method embodiment above.

[0109] Figure 2 The structure diagram of the distribution network grid optimization division device provided by the embodiment of the present application is shown. For the convenience of description, only the parts related to the embodiment of the present application are shown and are described in detail as follows:

[0110] As Figure 2 shown, the distribution network grid optimization division device 2 includes:

[0111] A data acquisition module 21, configured to acquire the geographical coordinates, power consumption loads, and operation data of each power supply unit in the target power supply area;

[0112] The preliminary division module 22 is used to construct a power supply grid division model by using the operation data of each power equipment, and solve the power supply grid division model based on the genetic algorithm to obtain an initial grid division scheme; the power supply grid division model takes the minimum sum of variances of the operation data as the optimization objective, and the initial grid division scheme includes each power supply grid preliminarily divided in the target power supply area and all power supply units existing in each power supply grid;

[0113] The similarity calculation module 23 is used to calculate the geographical coordinate similarity of each power supply unit in each power supply grid preliminarily divided based on the geographical coordinates of each power supply unit;

[0114] The regional function calculation module 24 is used to calculate the regional function of each power supply unit in each power supply grid preliminarily divided based on the power consumption load of each power supply unit;

[0115] The optimal division module 25 of the scheme is used to determine the optimal grid division scheme of the target power supply area based on all power supply units in each power supply grid and the geographical coordinate similarity and regional function of the corresponding power supply units.

[0116] The present application provides a device for optimizing the grid division of a distribution network. By obtaining the geographical coordinates, power consumption load and operation data of each power supply unit in the target power supply area; constructing a power supply grid division model by using the operation data of each power equipment, and solving the power supply grid division model based on the genetic algorithm to obtain an initial grid division scheme; the power supply grid division model takes the minimum sum of variances of the operation data as the optimization objective, and the initial grid division scheme includes each power supply grid preliminarily divided in the target power supply area and all power supply units existing in each power supply grid; calculating the geographical coordinate similarity of each power supply unit in each power supply grid preliminarily divided based on the geographical coordinates of each power supply unit; calculating the regional function of each power supply unit in each power supply grid preliminarily divided based on the power consumption load of each power supply unit; determining the optimal grid division scheme of the target power supply area based on all power supply units in each power supply grid and the geographical coordinate similarity and regional function of the corresponding power supply units. The present application realizes the refined division of the distribution network grid through the power supply grid division model and the geographical coordinate similarity and regional function; and by using the power supply grid division model and the genetic algorithm, it can improve the intelligence and automation of the distribution network grid division, provide strong support for constructing a safer, more efficient and greener intelligent distribution network, thereby enhancing the flexibility and scalability of the entire power grid system.

[0117] In a possible implementation manner, the operation data may include the annual failure times, operation years, power supply line length and annual failure operation and maintenance costs of each power equipment, and the objective function of the power supply grid division model is:

[0118]

[0119] Among them, D P is the variance of the annual failure times of N power devices in each power supply grid, D T is the variance of the operation years of N power devices in each power supply grid, D L is the variance of the power supply line lengths of N power devices in each power supply grid, C Y is the variance of the annual failure operation and maintenance costs of N power devices in each power supply grid, P Zn is the annual failure times of the power devices in the nth power supply grid, is the average value of the annual failure times of the power devices in the power supply grids within the target power supply area, is the average value of the operation years of the power devices in the nth power supply grid, is the average value of the operation years of the power devices in the power supply grids within the target power supply area, L Zn is the power supply line length of the nth power supply grid, is the average value of the power supply line lengths of the power supply grids within the target power supply area, C Zn is the annual failure operation and maintenance cost of the nth power supply grid, is the average value of the annual failure operation and maintenance costs of the power devices in the power supply grids within the target power supply area, N is the number of power supply grids within the target power supply area, n is the serial number of the power supply grid, and α1, α2, α3, and α4 are all weight coefficients.

[0120] In a possible implementation, the constraint conditions of the power supply grid division model may include the power supply user number constraint, the substation capacity constraint, the power supply radius constraint, and the island capacity constraint;

[0121] The power supply user number constraint is:

[0122]

[0123] Among them, H Zn is the total number of power supply users in the nth power supply grid, H n is the total number of power supply users in the target power supply area;

[0124] The substation capacity constraint is:

[0125]

[0126] Among them, P j is the active power of load node j, C i，p is the confidence capacity of the distributed photovoltaic power source without energy storage within the power supply range of substation i, C i，pe is the confidence capacity of the distributed photovoltaic power source with energy storage within the power supply range of substation i, S iThe capacity of substation i, e i The maximum load rate of substation i, The power factor of substation i, j is the load node number, and J is the total number of load nodes;

[0127] The power supply radius constraint is:

[0128] l ij ≤R i

[0129] Among them, l ij is the transmission distance between substation i and load node j, and R i is the maximum power supply radius of substation i;

[0130] The island capacity constraint is:

[0131]

[0132] Among them, P DG，m is the active power of the m-th distributed power source in the island, and P LOAD，j is the active power of load node j. M is the total number of distributed power sources in the island, J is the total number of load nodes, m is the number of the distributed power source in the island, and j is the number of the load node.

[0133] In a possible implementation manner, the preliminary division module can be used for:

[0134] Using each power supply unit in the target power supply area as the initial population, initializing the initial population, and using the initialized initial population as the current population;

[0135] Calculating the fitness of the current population;

[0136] Judging whether the current iteration number is greater than the preset iteration number;

[0137] If the current iteration number is greater than the preset iteration number, then use the power supply grid composed of each power supply unit in the current population corresponding to the fitness at the current iteration number as the initial grid division scheme;

[0138] If the current iteration number is not greater than the preset iteration number, then perform selection, crossover, and mutation on the current population respectively to generate the next population, and use the next population to update the current population, and return to the step of calculating the fitness of the current population to continue execution.

[0139] In a possible implementation manner, the similarity calculation module can be used for:

[0140] According to the geographical coordinates of each power supply unit in each power supply grid preliminarily divided, calculating the similarity of each power supply unit in the corresponding power supply grid. The similarity calculation formula is:

[0141]

[0142] Among them, F1 is the geographical coordinate similarity between the i-th power supply unit and the j-th power supply unit, (x i , y i ) is the geographical coordinate of the i-th power supply unit, (x j , y j ) is the geographical coordinate of the j-th power supply unit, l ij is the adjacent coefficient between the i-th power supply unit and the j-th power supply unit, and l max is the maximum value of the distance between adjacent power supply units.

[0143] In a possible implementation, the regional function calculation module can be used to:

[0144] Obtain the land area of each power supply unit in the target power supply area;

[0145] Based on the power consumption load and the corresponding land area of each power supply unit in each power supply grid preliminarily divided, calculate the load density of the corresponding power supply unit;

[0146] Determine the regional function of the power supply unit according to the load density of each power supply unit.

[0147] In a possible implementation, the optimal scheme division module can be used to:

[0148] For each power supply grid, perform the following steps:

[0149] Judge whether the geographical coordinate similarity of each power supply unit is greater than the preset similarity, and whether the regional functions of each power supply unit are the same;

[0150] If the geographical coordinate similarity of each power supply unit is greater than the preset similarity, and the regional functions of each power supply unit are the same, then determine that the power supply grid is the optimal grid division scheme;

[0151] If there are power supply units whose geographical coordinate similarity is not greater than the preset similarity, and / or there are power supply units with different regional functions, then remove the power supply units whose geographical coordinate similarity is not greater than the preset similarity and the power supply units with different regional functions from the power supply grid, and determine the remaining power supply units as the optimal grid division scheme.

[0152] In a possible implementation, the device may further include a regional power consumption property judgment module, and the regional power consumption property judgment model can be used to:

[0153] Obtain the power consumption load of each power supply unit in the target power supply area and the total area of the target power supply area;

[0154] Calculate the saturation load density of the target power supply area by using the electricity consumption loads of each power supply unit in the target power supply area and the total area of the target power supply area;

[0155] Determine the regional electricity consumption nature of the target power supply area by using the saturation load density of the target power supply area.

[0156] In a possible implementation manner, the device may further include a preprocessing module, and the preprocessing module may be used for:

[0157] Perform preprocessing such as cleaning, denoising, and normalization on the geographical coordinates, electricity consumption loads, and operation data of each power supply unit in the target power supply area, and use data dimensionality reduction technology to remove redundant data from the preprocessed geographical coordinates, electricity consumption loads, and operation data.

[0158] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0159] Those of ordinary skill in the art can realize that the templates, units, and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0160] If the module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes of the above method embodiments of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments for optimizing the division of the distribution network grid can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0161] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for optimizing the division of a distribution network grid, characterized in that, Including: Obtain the geographical coordinates, power consumption loads, and operation data of each power supply unit within the target power supply area; Construct a power supply grid division model using the operation data of each power equipment, and solve the power supply grid division model based on the genetic algorithm to obtain an initial grid division plan; The power supply grid division model takes the minimum sum of variances of operation data as the optimization objective, and the initial grid division plan includes each initially divided power supply grid within the target power supply area and all power supply units existing in each power supply grid; Based on the geographical coordinates of each power supply unit, calculate the geographical coordinate similarity of each power supply unit in each initially divided power supply grid respectively; Based on the power consumption load of each power supply unit, calculate the regional function of each power supply unit in each initially divided power supply grid respectively; based on all power supply units in each power supply grid and the corresponding geographical coordinate similarity and regional function of the power supply units, determine the optimal grid division plan for the target power supply area.

2. The method for optimizing the division of the distribution network grid according to claim 1, characterized in that The operation data includes the annual failure times, operation years, power supply line length, and annual failure operation and maintenance costs of each power equipment, and the objective function of the power supply grid division model is: Among them, D P is the variance of the annual failure times of N power equipment in each power supply grid. D T is the variance of the operation years of N power equipment in each power supply grid. D L is the variance of the power supply line lengths of N power equipment in each power supply grid. C Y is the variance of the annual failure operation and maintenance costs of N power equipment in each power supply grid. P Zn is the annual failure times of the power equipment in the nth power supply grid. is the average value of the annual failure times of the power equipment in the power supply grids in the target power supply area. is the average value of the operation years of the power equipment in the nth power supply grid. is the average value of the operation years of the power equipment in the power supply grids in the target power supply area. L Zn is the power supply line length of the nth power supply grid. is the average value of the power supply line lengths of the power supply grids in the target power supply area. C Zn is the annual failure operation and maintenance cost of the nth power supply grid. is the average value of the annual failure operation and maintenance costs of the power equipment in the power supply grids in the target power supply area. N is the number of power supply grids in the target power supply area, n is the serial number of the power supply grid, and α1, α2, α3, and α4 are all weight coefficients.

3. The power distribution network grid optimization and division method according to claim 2, wherein The constraint conditions of the power supply grid division model include power supply user number constraint, substation capacity constraint, power supply radius constraint, and island capacity constraint; The power supply user number constraint is: Among them, H Zn is the total number of power supply users in the nth power supply grid, and H n is the total number of power supply users in the target power supply area; The substation capacity constraint is: Among them, P j is the active power of load node j, C i,p is the confidence capacity of the distributed photovoltaic power source without energy storage within the power supply range of substation i, C i,pe is the confidence capacity of the distributed photovoltaic power source with energy storage within the power supply range of substation i, S i is the capacity of substation i, e i is the maximum load rate of substation i, is the power factor of substation i, j is the load node number, and J is the total number of load nodes; The power supply radius constraint is: l ij ≤R i where l ij is the transmission distance between substation i and load node j, and R i is the maximum power supply radius of substation i; The island capacity constraint is: Among them, P DG,m is the active power of the m-th distributed power source in the island, and P LOAD,j is the active power of load node j. M is the total number of distributed power sources in the island, j is the total number of load nodes, m is the number of the distributed power source in the island, and j is the number of the load node.

4. The method for optimizing the division of the distribution network grid according to claim 1, wherein The step of solving the power supply grid division model based on the genetic algorithm to obtain an initial grid division plan includes: Take each power supply unit in the target power supply area as the initial population, initialize the initial population, and use the initialized initial population as the current population; Calculate the fitness of the current population; Judge whether the current iteration number is greater than the preset iteration number; If the current iteration number is greater than the preset iteration number, then take the power supply grid composed of each power supply unit in the current population corresponding to the fitness at the current iteration number as the initial grid division plan; If the current iteration number is not greater than the preset iteration number, then perform selection, crossover, and mutation on the current population respectively to generate the next population, and update the current population with the next population, and return to the step of calculating the fitness of the current population to continue execution.

5. The method for optimizing the division of a distribution network grid according to claim 1, characterized in that The step of calculating the geographical coordinate similarity of each power supply unit in each initially divided power supply grid respectively based on the geographical coordinates of each power supply unit includes: According to the geographical coordinates of each power supply unit in each initially divided power supply grid, calculate the similarity of each power supply unit in the corresponding power supply grid, and the similarity calculation formula is: Among them, F1 is the geographical coordinate similarity between the i-th power supply unit and the j-th power supply unit, )x i , y i ) is the geographical coordinate of the i-th power supply unit, )x j , y j ) is the geographical coordinate of the j-th power supply unit, l ij is the adjacency coefficient between the i-th power supply unit and the j-th power supply unit, l max is the maximum distance of adjacent power supply units.

6. The method for optimizing the division of a distribution network grid according to claim 1, characterized in that The step of calculating the regional function of each power supply unit in each initially divided power supply grid respectively based on the power consumption load of each power supply unit includes: Obtain the land area of each power supply unit within the target power supply area; Based on the power consumption load and the corresponding land area of each power supply unit in each initially divided power supply grid, calculate the load density of the corresponding power supply unit; Determine the regional function of the power supply unit according to the load density of each power supply unit.

7. The method for optimizing the division of the distribution network grid according to claim 1, characterized in that Determining the optimal grid division plan for the target power supply area based on all power supply units in each power supply grid, as well as the geographical coordinate similarity and regional function of the corresponding power supply units, includes the following: For each power supply grid, perform the following steps: Judge whether the geographical coordinate similarity of each power supply unit is greater than the preset similarity, and whether the regional function of each power supply unit is the same; If the geographical coordinate similarity of each power supply unit is greater than the preset similarity, and the regional function of each power supply unit is the same, then determine that this power supply grid is the optimal grid division plan; If there are power supply units whose geographical coordinate similarity is not greater than the preset similarity, and / or there are power supply units with different regional functions, then remove the power supply units whose geographical coordinate similarity is not greater than the preset similarity and the power supply units with different regional functions from this power supply grid, and determine the remaining power supply units as the optimal grid division plan.

8. The method for optimizing the division of the distribution network grid according to claim 1, characterized in that Before obtaining the geographical coordinates, power consumption loads and operation data of each power supply unit in the target power supply area, the method further includes: Obtain the power consumption loads of each power supply unit in the target power supply area and the total area of the target power supply area; Use the power consumption loads of each power supply unit in the target power supply area and the total area of the target power supply area to calculate the saturated load density of the target power supply area; Use the saturated load density of the target power supply area to determine the regional power consumption nature of the target power supply area.

9. The method for optimizing the division of the distribution network grid according to claim 1, characterized in that After obtaining the geographical coordinates, power consumption loads and operation data of each power supply unit in the target power supply area, the method further includes: Perform preprocessing such as cleaning, denoising, and normalization on the geographical coordinates, power consumption loads and operation data of each power supply unit in the target power supply area, and use data dimensionality reduction technology to remove redundant data from the preprocessed geographical coordinates, power consumption loads and operation data.

10. A device for optimizing the division of a distribution network grid, characterized in that, Including: A data acquisition module, configured to acquire the geographical coordinates, power consumption loads and operation data of each power supply unit in the target power supply area; A preliminary division module, configured to construct a power supply grid division model using the operation data of each power equipment, and solve the power supply grid division model based on a genetic algorithm to obtain an initial grid division plan; The power supply grid division model takes the minimum sum of variances of operation data as the optimization target, and the initial grid division plan includes each power supply grid preliminarily divided in the target power supply area and all power supply units existing in each power supply grid; A similarity calculation module, configured to calculate the geographical coordinate similarity of each power supply unit in each power supply grid divided preliminarily based on the geographical coordinates of each power supply unit; A regional function calculation module, configured to calculate the regional function of each power supply unit in each power supply grid divided preliminarily based on the power consumption load of each power supply unit; A plan optimal division module, configured to determine the optimal grid division plan for the target power supply area based on all power supply units in each power supply grid, as well as the geographical coordinate similarity and regional function of the corresponding power supply units.

Images