A method, device, equipment, medium and product for charging pile layout

Abstract

The present application discloses a method, device, equipment, medium and product for charging pile layout, which relates to the field of charging facility construction. The method includes obtaining charging pile data of a target area; the charging pile data includes: the geographical location of the charging pile site and the tram data around the charging pile site; the tram data includes: the number and distribution of electric vehicles; according to the charging pile data of the target area and the objective function, a multi-population hybrid cross particle swarm optimization algorithm is used for multiple iterations to determine the optimal charging pile layout plan for the target area; the objective function is constructed based on the investment cost, operation cost and maintenance cost; the optimal charging pile layout plan is the layout quantity of the charging piles and the layout positions of the charging piles when the set standard is met; the set standard is that the fitness value calculated according to the objective function is the smallest or the number of iterations is the largest. The present application can accurately and efficiently realize the layout of the charging piles, thereby improving the charging efficiency.

Description

Technical Field

[0001] The present application relates to the field of charging facility construction, and particularly to a method, device, equipment, medium and product for charging pile layout. Background Art

[0002] Problems such as the energy crisis caused by the shortage of fossil energy and the air pollution caused by excessive emissions of greenhouse gases are becoming increasingly serious. New energy vehicles, especially electric vehicles (EVs), have begun to become the main development direction of the automotive industry. In order to promote the development of the electric vehicle industry, promoting the construction of electric vehicle charging infrastructure has become one of the important links in the electric vehicle industrial system project.

[0003] Currently, the construction of electric vehicle charging infrastructure still mainly focuses on market demonstrations, which lags far behind the development of electric vehicles. Relevant theoretical research has not yet received extensive attention from the academic community. How to reasonably layout electric vehicle charging stations, making it convenient for electric vehicle chargers to charge while saving construction costs has become one of the key concerns of urban planning departments, transportation departments, and power supply enterprises. Summary of the Invention

[0004] The purpose of the present application is to provide a method, device, equipment, medium and product for charging pile layout, which can accurately and efficiently realize the layout of charging piles, thereby improving the charging efficiency.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In the first aspect, the present application provides a method for charging pile layout, including:

[0007] Obtain the charging pile data of the target area; the charging pile data includes: the geographical location of the charging pile site and the tram data around the charging pile site; the tram data includes: the number and distribution of electric vehicles.

[0008] According to the charging pile data of the target area and the objective function, use the multi-population hybrid cross particle swarm optimization algorithm for multiple iterations to determine the optimal charging pile layout plan for the target area; the objective function is constructed based on investment cost, operating cost, and maintenance cost; the optimal charging pile layout plan is the layout quantity of charging piles and the layout position of charging piles when reaching the set standard; the set standard is that the fitness value calculated according to the objective function is the smallest or the number of iterations is the largest.

[0009] In the second aspect, the present application provides a device for charging pile layout, including:

[0010] A data acquisition module, configured to acquire charging pile data of a target area; the charging pile data includes: the geographical location of a charging pile site and electric vehicle data around the charging pile site; the electric vehicle data includes: the number and distribution of electric vehicles.

[0011] A charging pile layout module, configured to perform multiple iterations using a multi-swarm hybrid crossover particle swarm optimization algorithm according to the charging pile data of the target area and an objective function, to determine an optimal charging pile layout plan for the target area; the objective function is constructed based on investment cost, operation cost, and maintenance cost; the optimal charging pile layout plan is the layout quantity of charging piles and the layout positions of charging piles when a set standard is met; the set standard is that the fitness value calculated according to the objective function is the smallest or the number of iterations is the largest.

[0012] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the above-mentioned charging pile layout method.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned charging pile layout method is implemented.

[0014] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above-mentioned charging pile layout method is implemented.

[0015] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0016] The present application provides a charging pile layout method, device, equipment, medium, and product. According to the charging pile data of the target area and the objective function, by using a multi-swarm hybrid crossover particle swarm optimization algorithm (Multi-swarm Crossoverhybrid Strategy Particle Swarm Optimization, MCSPSO) to perform multiple iterations, an optimal charging pile layout plan for the target area is determined. The multi-swarm hybrid crossover particle swarm optimization algorithm can effectively prevent the particle swarm optimization algorithm from falling into a local optimum in complex problems, can effectively improve the particle swarm search speed, accelerate finding the optimal charging pile layout position, and realize a more reasonable layout of charging piles. Therefore, the present application can accurately and efficiently implement the layout of charging piles, thereby improving the charging efficiency. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of a charging pile layout method provided by an embodiment of the present application;

[0019] Figure 2 It is an overall implementation process diagram of the charging pile layout method provided by another embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of charging pile data provided by an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of a specific iteration process provided by an embodiment of the present application;

[0022] Figure 5 It is a coordinate diagram of the optimized charging pile layout provided by an embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of functional modules of a charging pile layout device provided by another embodiment of the present application;

[0024] Figure 7 It is a schematic diagram of the structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0026] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the drawings and specific implementation manners.

[0027] Currently, regarding the spatial location planning scheme of charging infrastructure, most of them start from perspectives such as cost and existing power grids and use the traditional Particle Swarm Optimization (PSO) algorithm to implement. In reality, due to a large amount of data, the traditional particle swarm optimization algorithm has a high complexity and a large model solving difficulty.

[0028] Specifically, the unique feature of the Particle Swarm Optimization (PSO) algorithm lies in that it retains both the global optimal value of the particles and the known optimal position information during the search process. Both of these play important roles in the convergence speed of the algorithm, helping to avoid getting trapped in local optimal values and accelerating the finding of the global optimal solution. This characteristic enables the PSO algorithm to perform excellently in dealing with complex problems and become a favored optimization method in academic research and practical applications. However, similar to other nature-inspired metaheuristic algorithms, the PSO algorithm has two main limitations: premature convergence and getting trapped in local minima when solving complex multimodal problems. There are many factors affecting the convergence and performance of the PSO algorithm, such as swarm size, velocity clamping, position clamping, neighborhood topology, synchronous or asynchronous updates, especially the choice of control parameters. In fact, a major problem in PSO performance control is the exploration / exploitation balance, because excessive exploration wastes computing resources, while excessive exploitation leads to premature local convergence. In practice, there is a trade-off between the exploration ability and the exploitation ability, and these two abilities should be well balanced to obtain good problem optimization performance. However, in a dynamic environment, it is difficult for the PSO algorithm to maintain a balance between exploration (global search) and exploitation (local search).

[0029] How to improve the convergence speed of the PSO algorithm and avoid premature convergence has become the most important research issue in the PSO algorithm. Regarding this issue, a large amount of research work has been done, and many variants of PSO have been proposed. These algorithms balance the local search ability and the global search ability by adjusting parameters, modifying update rules, and designing new strategies during the evolution process, and have achieved certain improvements in the convergence of solutions. However, with the increasing complexity of optimization problems, the current algorithms still cannot guarantee good solution diversity and efficiency in reality.

[0030] Improving the PSO algorithm should be considered from how to maintain population diversity while balancing the global search ability and the local development ability to prevent the PSO from getting trapped in local optima. However, a single improvement strategy cannot effectively deal with optimization problems of different natures. And there is literature showing that the multi-strategy PSO algorithm can well balance the exploration and exploitation abilities of particles, can effectively prevent the PSO algorithm from getting trapped in local optima in complex problems, thereby increasing the probability of the algorithm finding the optimal solution, and ultimately can be applied to a specific charging pile model.

[0031] As Figure 1 shown, this embodiment provides a charging pile layout method, which specifically includes:

[0032] Step 101, obtaining the charging pile data of the target area; the charging pile data includes: the geographical location of the charging pile sites and the tram data around the charging pile sites; the tram data includes: the number and distribution of electric vehicles.

[0033] Step 102: According to the charging pile data of the target area and the objective function, use the multi-population hybrid cross particle swarm optimization algorithm to perform multiple iterations to determine the optimal charging pile layout plan for the target area.

[0034] Among them, the objective function is constructed based on the investment cost, operation cost, and maintenance cost; the optimal charging pile layout plan is the layout quantity of the charging piles and the layout positions of the charging piles when meeting the set standard; the set standard is that the fitness value calculated according to the objective function is the smallest or the number of iterations is the largest.

[0035] In another exemplary embodiment of the present application, Step 102 specifically includes:

[0036] (1) Randomly initialize the particle population; the particle population includes multiple particles; one particle represents a charging pile layout plan.

[0037] (2) According to the charging pile data of the target area and the objective function, calculate the fitness value of each particle in the particle population.

[0038] (3) Sort the fitness values of all particles in ascending order to form a fitness value sequence.

[0039] (4) Use the particles corresponding to the first m 1 *N fitness values in the fitness value sequence to form the elite group S good , use the particles corresponding to the m 1 *Nth fitness value to the m 2 *Nth fitness value in the fitness value sequence to form the ordinary group S normal , and use the particles corresponding to the fitness values after the m 2 *Nth fitness value in the fitness value sequence to form the inferior group S weak ; N represents the number of particles in the particle population; m 1 and m 2 are both constants, m 1 ∈ [0, 1], m 2 ∈ [0, 1], m 1 < m 2 . For example, N can take the value of 100, m 1 can take the value of 0.3, and m 2 can take the value of 0.7.

[0040] (5) Use different update strategies for the elite group, the ordinary group, and the inferior group to perform multiple iterative updates of the particle velocity and position to determine the optimal charging pile layout plan for the target area; among them, different velocities and positions correspond to different charging pile layout plans, and calculate the fitness value once for each update of the velocity and position of the group.

[0041] In another exemplary embodiment of the present application, for the current iteration number, the first update strategy, the second update strategy, and the third update strategy are respectively adopted for the elite group to update the particle velocity and position, obtaining three updated velocities and positions, and taking the one with the minimum fitness value as the updated velocity and position of the elite group at the current iteration number.

[0042] The calculation formula of the first update strategy is:

[0043]

[0044] where X id (iter + 1) represents the updated position of the current particle i in dimension d in the elite group; X id (iter) represents the position of the current particle i in dimension d in the elite group before update; rand represents a random value between [0, 1]; fitness i represents the fitness value of the current particle i in the elite group; Gbest represents the fitness value of the global optimal particle; ε is an infinitesimal value to prevent it from being equal to 0. Among them, the first update strategy only updates the position and keeps the velocity unchanged. The number of dimensions of the particle is determined according to the objective function.

[0045] The calculation formula of the second update strategy is:

[0046]

[0047] X id (iter + 1) = X id (iter) + V id (iter + 1);

[0048] where V id (iter + 1) represents the updated velocity of the current particle i in dimension d in the elite group; V id (iter) represents the velocity of the current particle i in dimension d in the elite group before update; ω, c 1 and c 2 both represent the acceleration coefficients of the particle; Pbest id represents the historical optimal coordinate of the current particle i in dimension d.

[0049] The calculation formula of the third update strategy is:

[0050] V id (iter + 1) = ω·V id (iter) + ω·0.1·(ub - lb)·(randn(-1, 1));

[0051] X id (iter + 1) = X id (iter) + V id (iter + 1);

[0052] Among them, ub represents the upper bound of the objective function; lb represents the lower bound of the objective function; randn(-1, 1) represents a random value located in [-1, 1].

[0053] In another exemplary embodiment of the present application, for the current iteration number, the fourth update strategy is adopted for updating the particle velocity and position of the ordinary population, and the velocity and position of the ordinary population after the update of the current iteration number are obtained.

[0054] The calculation formula of the fourth update strategy is as follows:

[0055] MBest(iter) = mean{Pbest 1 , Pbest 2 ,..., Pbest K};

[0056] fit(CPbest(iter)) < fit(X k );

[0057]

[0058] Among them, V kd (iter + 1) represents the velocity of the current particle k in the ordinary population after updating in dimension d; V kd (iter) represents the velocity of the current particle k in the ordinary population before updating in dimension d; ω, c 1 and c 2 both represent the acceleration coefficients of the particles; rand represents a random value between [0, 1]; Mbest d represents the geometric center of all particles in the ordinary population; CPbest d represents the particle position in the ordinary population whose fitness value is better than that of the current particle k; X kd represents the position of the current particle k in the ordinary population in dimension d; X k (iter + 1) represents the position of the current particle k in the ordinary population after updating in all dimensions; X k (iter) represents the position of the current particle k in the ordinary population before updating in all dimensions; V k (iter + 1) represents the velocity of the current particle k in the ordinary population after updating in all dimensions; V k (iter) represents the velocity of the current particle k in the ordinary population before updating in all dimensions; p kRepresents an intermediate variable; fitness k Represents the fitness value of the current particle k in the ordinary population; K represents the number of particles in the ordinary population.

[0059] In another exemplary embodiment of the present application, for the current iteration number, a fifth update strategy is adopted for the inferior population to update the particle velocity and position, and the velocity and position of the inferior population after the current iteration number is updated are obtained.

[0060] The calculation formula of the fifth update strategy is:

[0061] RPbest∈S good ;

[0062]

[0063] X nd (iter + 1) = X nd (iter) + V nd (iter + 1);

[0064] Among them, V nd (iter + 1) represents the updated velocity of the current particle n in the inferior population in dimension d; V nd (iter) represents the velocity of the current particle n in the inferior population in dimension d before update; ω, c 1 and c 2 both represent the acceleration coefficients of the particles; r 1 and r 2 both represent random values between [0, 1]; RPbest d (iter) represents the historical optimum of a random particle whose fitness value is better than that of the current particle n; Gbest d (iter) represents the global optimum of all particles in the inferior population; X nd (iter + 1) represents the updated position of the current particle n in the inferior population in dimension d; X nd (iter) represents the position of the current particle n in the inferior population in dimension d before update; S good Represents the elite population.

[0065] In another exemplary embodiment of the present application, the expression of the objective function is:

[0066]

[0067] Among them, f represents the value of the objective function; N EVCS represents the total number of charging pile sites; T represents the number of charging piles arranged at the charging pile sites; represents the investment cost; Represents the operating cost of the a-th charging pile site; Represents the maintenance cost of the a-th charging pile site; t represents the number of the charging pile; ε is an infinitesimal value to prevent it from being equal to 0.

[0068] See Figure 2 , the overall implementation process of the charging pile layout method in the above embodiment can be described as follows:

[0069] Step 1: Obtain the geographical locations of the charging pile sites and the surrounding electric vehicle data in a certain urban area through social research, and finally determine the charging pile layout model, that is, the objective function, and the specific expression is not elaborated here.

[0070] Step 2: Implement optimization based on the multi-population hybrid crossover particle swarm algorithm.

[0071] Sub-step 1: Randomly initialize the population position and velocity, and obtain the particle fitness value according to the objective function. The fitness value of each particle corresponds to the cost of a charging pile layout, that is, the value of the objective function.

[0072] Sub-step 2: Sort and classify according to the particle fitness value in Sub-step 1.

[0073] The specific process of classification and sorting is: Select m 1 , m 2 between [0, 1] as the index for processing population separation, and then sort the population in ascending order according to the fitness value. The particles with an index less than m 1 *N belong to the "elite group" and are divided into the elite group; the particles with an index between m 1 *N and m 2 *N are divided into the ordinary group; the particles with an index greater than m 2 *N are divided into the inferior group.

[0074] Sub-step 3: Based on the elite group in Sub-step 2, use the first, second, and third update strategies to update the speed and position, thereby updating the value of the objective function to obtain the first result.

[0075] Based on the greedy strategy, select the coordinate with the better final fitness value from the above three update strategies as the position of the particle in the next iteration. By cross-selecting the above strategies, the current state of the elite particles can be better retained, but there is a probability of jumping out of the local optimum through a certain degree of perturbation.

[0076] Based on the ordinary group in Sub-step 2, use the fourth update strategy to update the speed and position to obtain the second result.

[0077] In order to balance global search and local exploration, an adaptive position update mechanism is used in the second update strategy. The adaptive update strategy is reflected in:

[0078]

[0079] Based on the disadvantaged group in sub-step 2, the fifth updating strategy is adopted to update the speed and position, and the third result is obtained.

[0080] Finally, update the gbest of the particle and continue the above steps until the iteration ends. At this point, the algorithm is completed.

[0081] Step 3: Input the objective function of the charging pile layout model in step 1 into the algorithm system constructed in step 2. Finally, the location of each charging pile layout and the final number of charging pile layouts can be obtained from the optimal value of the objective function of the charging pile model.

[0082] The specific process is:

[0083] Sub-step 1: According to the specific demand coordinates, demand load, cost coefficient, region, and centralized charging station coordinates, the objective function of the charging pile is imported into the multi-population hybrid crossover particle swarm algorithm for continuous iteration.

[0084] Sub-step 2: Finally, when the update result reaches the maximum number of iterations or the iteration reaches the global optimum, the iteration is terminated to obtain the optimal result. When the particle swarm ends the iteration, the reasonable layout of the electric vehicle charging station is achieved.

[0085] The effectiveness of the multi-swarm mixed crossover particle swarm algorithm of this embodiment is verified below.

[0086] The charging pile layout method based on multi-swarm hybrid crossover particle swarm algorithm includes:

[0087] 1. Taking the minimum sum of the total cost (including investment, operation and maintenance costs) and network loss costs of charging stations during the planning period as the goal, the mathematical model for the optimal planning of electric vehicle charging stations was constructed by considering the relevant constraints.

[0088] The reasonable driving range of an electric vehicle is defined as the distance that the electric vehicle can travel when the power battery pack is discharged from the optimal discharge depth to the maximum discharge depth. The reasonable driving range of an electric vehicle under uniform speed is

[0089] Charging station service radius The actual distance D between two adjacent charging stations EVCS Should meet:

[0090]

[0091] According to the actual distance between two adjacent charging stations and the service radius of each charging station, the given preliminary selected site addresses are screened to determine a reasonable charging station site planning scheme. At the same time, according to the Voronoi diagram widely used in geographic information systems, the charging service areas of charging stations are divided to guide vehicle owners to select appropriate charging stations for charging according to the battery status.

[0092] 2. Determine the objective function of the charging station planning model.

[0093] 3. Figure 3 The specific service points of the charging stations are given, and the demand coordinates, demand loads, cost coefficients, regions, and the coordinates of the centralized charging stations are determined. The number of selected sites is 7, and the specific demand points are 34.

[0094] 4. When using the traditional particle swarm optimization algorithm to handle the layout of charging piles, it is easy to fall into local optimum. To solve this problem, a multi-swarm hybrid cross particle swarm optimization algorithm is proposed.

[0095] In this specific embodiment, the number of particle swarm populations is set to 20, and the number of iterations is set to 500 times. The acceleration coefficient range of c 1 , c 2 is (0.5, 2.5), and ω is set to 0.5 - 0.2. The specific iteration process is as Figure 4 shown. Finally, the coordinate map of the optimized charging pile layout can be obtained, as Figure 5 shown.

[0096] Based on the same inventive concept, the embodiment of the present application also provides a charging pile layout device for implementing the charging pile layout method involved above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions recorded in the above method. Therefore, the specific limitations in one or more embodiments of the charging pile layout device provided below can refer to the limitations on the charging pile layout method in the above text, and will not be repeated here.

[0097] In an exemplary embodiment, as Figure 6 shown, a charging pile layout device is provided, including:

[0098] A data acquisition module 601, configured to acquire charging pile data of a target area; the charging pile data includes: the geographical location of the charging pile site and the tram data around the charging pile site; the tram data includes: the number and distribution of electric vehicles.

[0099] The charging pile layout module 602 is configured to perform multiple iterations using a multi-population hybrid crossover particle swarm optimization algorithm according to the charging pile data and the objective function of the target area, so as to determine the optimal charging pile layout plan for the target area; the objective function is constructed based on the investment cost, operating cost, and maintenance cost; the optimal charging pile layout plan is the layout quantity of the charging piles and the positions of the charging pile layouts when meeting the set standard; the set standard is that the fitness value calculated according to the objective function is the smallest or the number of iterations is the largest.

[0100] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the charging pile data of the target area. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a charging pile layout method.

[0101] Those skilled in the art can understand that Figure 7 the structure shown in

[0102] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above method embodiments.

[0103] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, it implements the steps in the above method embodiments.

[0104] In an exemplary embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the steps in the above method embodiments.

[0105] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memories can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0106] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, etc., without limitation.

[0107] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0108] In this article, specific examples are used to elaborate on the principles and implementation manners of this application. The descriptions of the above embodiments are only used to help understand the method of this application and its core idea. At the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. To sum up, the content of this specification should not be construed as a limitation to this application.

Claims

1. A charging pile layout method, characterized in that: The charging pile layout method comprises: Acquire charging pile data of the target area; the charging pile data includes: the geographical location of the charging pile site and the tram data around the charging pile site; the tram data includes: the number and distribution of electric vehicles; According to the charging pile data and objective function of the target area, a multi-swarm hybrid crossover particle swarm algorithm is used for multiple iterations to determine the optimal charging pile layout plan for the target area; the objective function is constructed based on investment cost, operation cost and maintenance cost; the optimal charging pile layout plan is the layout quantity and location of the charging piles when the set standard is met; the set standard is the minimum fitness value calculated according to the objective function or the maximum number of iterations; According to the charging pile data and objective function of the target area, a multi-swarm hybrid crossover particle swarm algorithm is used for multiple iterations to determine the optimal charging pile layout plan for the target area, including: Randomly initialize a particle population; the particle population includes a plurality of particles; one particle represents a charging pile layout scheme; Calculating the fitness value of each particle in the particle population according to the charging pile data of the target area and the objective function; Sort the fitness values ​​of all particles in ascending order to form a fitness value sequence; The group consisting of particles corresponding to the first m1*N fitness values ​​in the fitness value sequence is regarded as the elite group, the group consisting of particles corresponding to the fitness values ​​from the m1*Nth to the m2*Nth fitness values ​​in the fitness value sequence is regarded as the ordinary group, and the group consisting of particles corresponding to the fitness values ​​after the m2*Nth fitness value in the fitness value sequence is regarded as the inferior group; N represents the number of particles in the particle population; m1∈[0,1], m2∈[0,1], m1<m2; Different updating strategies are used for the elite group, the ordinary group and the disadvantaged group to perform multiple iterative updates on the particle speed and position, and determine the optimal charging pile layout scheme for the target area; wherein different speeds and positions correspond to different charging pile layout schemes, and the fitness value is calculated once each time the speed and position of the group are updated; For the current number of iterations, the first update strategy, the second update strategy and the third update strategy are respectively used to update the particle speed and position of the elite group to obtain the updated speed and position, and the one with the smallest fitness value is used as the speed and position of the elite group after the current number of iterations.

2. The charging pile layout method according to claim 1, characterized in that: The calculation formula of the first update strategy is: Among them, X id (iter+1) represents the position of the current particle i in the elite group after the dimension d is updated; X id (iter) represents the position of the current particle i in the elite group before the dimension d is updated; rand represents a random value between [0, 1]; fitness i represents the fitness value of the current particle i in the elite group; Gbest represents the fitness value of the global optimal particle; ε is an infinitely small value; The calculation formula of the second update strategy is: Among them, V id (iter+1) represents the speed of the current particle i in the elite group after the update in dimension d; V id (iter) represents the velocity of the current particle i in the elite group before the dimension d is updated; ω, c1 and c2 all represent the acceleration coefficients of the particle; Pbest id Represents the historical optimal coordinates of the current particle i in dimension d; The calculation formula of the third update strategy is: 5 id (iter+1)=ω·V id (path)+ω·0.1·(ub-lb)·(randn(-1,1)); X id (iter+1)=X id (iter)+V id (iter+1); Among them, ub represents the upper boundary of the objective function; lb represents the lower boundary of the objective function; randn(-1,1) represents a random value in [-1,1]; For the current number of iterations, the fourth update strategy is used to update the particle speed and position of the common group to obtain the updated speed and position of the common group for the current number of iterations; The calculation formula of the fourth update strategy is: Among them, V kd (iter+1) represents the velocity of the current particle k in the general population after the dimension d is updated; V kd (iter) represents the velocity of the current particle k in the common population before the dimension d is updated; ω, c1 and c2 all represent the acceleration coefficients of the particle; rand represents a random value between [0, 1]; Mbest d Represents the geometric center of all particles in the general population; CPbest d Indicates the position of the particle in the general population whose fitness value is better than the current particle k; X kd represents the position of the current particle k in dimension d in the general population; X k (iter+1) represents the position of the current particle k in the general population after all dimensions are updated; X k (iter) represents the position of the current particle k in the general population before all dimensions are updated; V k (iter+1) represents the velocity of the current particle k in the general population after all dimensions are updated; V k (iter) represents the velocity of the current particle k in the general population before all dimensions are updated; p k Represents an intermediate variable; fitness k represents the fitness value of the current particle k in the common population; K represents the number of particles in the common population.

3. The charging pile layout method according to claim 1, characterized in that: For the current number of iterations, the fifth updating strategy is used to update the particle speed and position of the disadvantaged group to obtain the updated speed and position of the disadvantaged group after the current number of iterations; The calculation formula of the fifth update strategy is: Among them, V nd (iter+1) represents the speed of the current particle n in the disadvantaged group after the dimension d is updated; V nd (iter) represents the velocity of the current particle n in the disadvantaged group before the dimension d is updated; ω, c1 and c2 represent the acceleration coefficients of the particles; r1 and r2 represent random values ​​between [0, 1]; RPbest d (iter) represents the historical best of random particles with a fitness value better than the current particle n; Gbest d (iter) represents the global optimum of all particles in the disadvantaged group; X nd (iter+1) represents the position of the current particle n in the disadvantaged group after the dimension d is updated; X nd (iter) represents the position of the current particle n in the disadvantaged group before the dimension d is updated.

4. The charging pile layout method according to claim 1, characterized in that: The expression of the objective function is: Where f represents the value of the objective function; N EVCS represents the total number of charging pile sites; T represents the number of charging piles arranged at the charging pile site; represents the investment cost; represents the operating cost of the ath charging station; represents the maintenance cost of the a-th charging pile station; t represents the number of the charging pile; ε is an infinitely small value.

5. A charging pile layout device, characterized in that: The charging pile layout device is applied to the charging pile layout method according to any one of claims 1 to 4, and the charging pile layout device comprises: A data acquisition module is used to acquire charging pile data in a target area; the charging pile data includes: the geographical location of the charging pile site and the tram data around the charging pile site; the tram data includes: the number and distribution of electric vehicles; The charging pile layout module is used to determine the optimal charging pile layout plan for the target area based on the charging pile data and the objective function of the target area, using a multi-swarm mixed crossover particle swarm algorithm for multiple iterations; the objective function is constructed based on investment cost, operation cost and maintenance cost; the optimal charging pile layout plan is the layout quantity and location of the charging piles when the set standard is met; the set standard is the minimum fitness value calculated according to the objective function or the maximum number of iterations.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the charging pile layout method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the charging pile layout method described in any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the charging pile layout method described in any one of claims 1 to 4 is implemented.

Images