Charging pile site selection method

Abstract

The invention provides a charging pile site selection method, which comprises the steps of determining an initial parameter of a preset algorithm based on community energy data and charging pile candidate position data; according to the initial parameters, the preset algorithm is calculated and solved, and charging pile locating and sizing data of each charging pile candidate position are obtained; and according to the charging pile locating and sizing data, determining a charging pile locating result based on a preset selection strategy. According to the charging pile site selection method provided by the invention, based on the community location condition and the energy load condition, the factors of multiple dimensions can be integrated to assist in optimizing the site selection management of the charging points, and the reasonable layout of the charging piles is realized.

Description

Technical Field

[0001] The present application relates to the technical field of charging piles, and in particular to a method for selecting a site for a charging pile. Background Art

[0002] With the rapid development and widespread use of electric vehicles, the construction of charging infrastructure has become a key issue in the popularization and promotion of electric vehicles. In the traditional charging mode, drivers choose charging piles based on their own needs and the availability of charging piles; and the driver's charging needs are affected by many factors, such as driving distance, usage time and charging time window.

[0003] During the research process of conceiving and formulating this application, the applicant discovered at least the following problems: within the community, the number of charging piles and the balance of energy distribution are not the same. Some charging piles or certain time periods may be frequently used, while others are idle for a long time, which causes difficulties in community vehicle charging management during the investment, construction, management and use of community charging piles. Summary of the invention

[0004] In order to alleviate the above problems, the present application provides a method for selecting a charging pile site, including: Determine the initial parameters of the preset algorithm based on community energy data and charging pile candidate location data; According to the initial parameters, the preset algorithm is calculated and solved to obtain the charging pile site selection and capacity determination data for each charging pile candidate location; According to the charging pile site selection and capacity determination data, the charging pile site selection result is determined based on a preset selection strategy.

[0005] Optionally, the step of determining initial parameters of the preset algorithm includes: A modeling dimension is determined based on the community energy data, and a mathematical model is established for the modeling dimension according to the community energy data and the charging pile candidate location data.

[0006] Optionally, the step of calculating and solving the preset algorithm according to the initial parameters to obtain a solution set for each charging pile candidate position includes: The particle swarm algorithm is called to perform iterative fitness calculation on the data model, and after each update of the particle swarm calculation result, an annealing process is performed on the particle swarm calculation result based on the annealing algorithm.

[0007] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The modeling dimension includes an investment cost dimension; the charging pile candidate location data includes the unit price of the charging pile, the fixed investment cost of each charging pile, the investment interest rate and the operating life; the equivalent investment coefficient of the charging pile facilities and equipment and the construction cost in the community and the conversion coefficient of the operating cost and the construction cost are set, and an investment cost model of the investment cost dimension is established based on the number of charging piles constructed.

[0008] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The modeling dimensions include the owner satisfaction dimension; the community energy data includes the coordinates of each parking space in the community, the number of charging vehicles in the community, and the service efficiency of charging piles; the maximum waiting time, queue sensitivity coefficient, distance satisfaction weight and waiting time satisfaction weight are set, and an owner satisfaction model of the owner satisfaction dimension is established based on the number of charging piles built.

[0009] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The modeling dimension includes the energy load scheduling dimension; the charging pile candidate location data includes the total community load, other energy equipment load and time-of-use electricity price strategy, determines the scheduling coefficient of the energy storage equipment, and establishes the energy load scheduling model of the owner satisfaction dimension based on the number of charging piles built.

[0010] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The candidate location data of the charging pile includes the community road coordinates and the candidate location coordinates of each charging pile, and the environment modeling is performed using the Euler connectivity graph in combination with the parking space coordinates; Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The demand weight of each modeling dimension is determined according to the community energy data and the charging pile candidate location data, and the objective function of community charging pile site selection is established based on the demand weight.

[0011] Optionally, the charging pile candidate location data includes the coordinates of the road connection points in the community and the coordinates of the candidate charging points; and the process of determining the initial parameters of the preset algorithm includes: Based on the coordinates of the road connection points and the coordinates of the candidate charging points, determining the population size and the number of outer loop iterations of the particle swarm algorithm, randomly initializing the positions and velocities of multiple particles, and initializing the individual optimal solution and the global optimal solution of each particle; The number of inner loop iterations and the temperature attenuation coefficient of the annealing algorithm are determined, and the termination temperature is calculated.

[0012] Optionally, the step of calling a particle swarm algorithm to iteratively calculate the fitness of the data model includes: When the number of outer loop iterations is not completed, calculating the fitness of each particle in the particle swarm based on the objective function; The cooperation and competition relationship between each proposed charging station is simulated, the individual optimal solution and the global optimal solution are obtained according to the fitness of each particle, the position and speed of each particle are updated, and the initial temperature of the annealing algorithm is updated, and the optimal solution is iteratively searched in the solution space.

[0013] Optionally, the step of simulating the cooperation and competition relationship between each proposed charging station, obtaining the individual optimal solution and the global optimal solution according to the fitness of each particle, and updating the position and speed of each particle includes: Based on the initial position and velocity of each particle in the particle population, a fitness function value is calculated according to the data model, and if the fitness function value is greater than the recorded individual best solution, it is marked as the individual best solution of the particle; The particles in the particle population cooperate to share information to obtain a global optimal solution, and perform iterative calculations to obtain a new position and velocity of the particle.

[0014] Optionally, after each update of the particle swarm computing result, the process of performing an annealing process on the particle swarm computing result based on an annealing algorithm includes: Based on the number of iterations of the inner loop, the output result of the particle swarm algorithm is used as the current optimal solution, and the acceptance probability is iteratively calculated according to the Metropolis criterion at the current initial temperature; Processing the current optimal solution according to the acceptance probability, and updating the initial temperature and the termination temperature; When the number of iterations of the inner loop is completed, the charging pile site selection and sizing data of the optimal value of the objective function is updated and recorded according to the current optimal solution, and the charging pile site selection and sizing data includes the charging pile investment cost evaluation information, owner satisfaction evaluation information, and energy load scheduling evaluation information corresponding to the site selection coordinates of each charging station.

[0015] Optionally, the process of processing the current optimal solution according to the acceptance probability and updating the initial temperature and the termination temperature includes: The result of the annealing algorithm is accepted with a preset probability at the current initial temperature, the inner loop iteration is executed and the acceptance probability is gradually reduced until the stop condition is met, so as to return to the optimal solution.

[0016] Optionally, the step of determining the charging pile site selection result based on the charging pile site selection and capacity determination data and based on a preset selection strategy includes: Determine the weight of each indicator in the charging pile site selection and capacity determination data through expert consultation, hierarchical analysis method and fuzzy comprehensive evaluation method, so as to perform weighted processing on the charging pile investment cost evaluation information, owner satisfaction evaluation information and energy load scheduling evaluation information; The charging pile investment cost evaluation information, the owner satisfaction evaluation information, and the energy load scheduling evaluation information are respectively multiplied by their corresponding weights, and then the weighted values ​​of all indicators are summed to obtain a comprehensive evaluation value for each charging pile candidate location; The candidate locations of the charging piles whose comprehensive evaluation values ​​are within the preset evaluation interval are output as the charging pile site selection results.

[0017] The charging pile site selection method provided in the present application determines the initial parameters of a preset algorithm based on community energy data and charging pile candidate location data; according to the initial parameters, the preset algorithm is calculated and solved to obtain the charging pile site selection and capacity data for each charging pile candidate location; according to the charging pile site selection and capacity data, the charging pile site selection result is determined based on a preset selection strategy; based on the community location conditions and energy load conditions, it can comprehensively consider factors in multiple dimensions to assist in optimizing the site selection management of charging points and achieve a reasonable layout of charging piles. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0019] Figure 1 This is a flow chart of a method for selecting a charging pile site according to an embodiment of the present application.

[0020] Figure 2 This is a diagram showing the charging time structure of an electric vehicle owner according to an embodiment of the present application.

[0021] Figure 3 This is a flow chart of an improved algorithm according to an embodiment of the present application.

[0022] Figure 4 This is a schematic diagram of the site selection process for community charging piles for this application.

[0023] Figure 5 This is a community road connectivity diagram according to an embodiment of the present application.

[0024] Figure 6 This is a graph of calculation results generated according to an embodiment of the present application.

[0025] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0027] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0028] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate that there are the described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or", "and / or", "including at least one of the following" etc. used in this application can be interpreted as inclusive, or mean any one or any combination. For example, “comprising at least one of the following: A, B, C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”, and for another example, “A, B or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”. An exception to this definition will only occur when a combination of elements, functions, steps or operations are inherently mutually exclusive in some manner.

[0029] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0030] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0031] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] First embodiment This application provides a method for selecting a charging pile site. Figure 1 This is a flow chart of a method for selecting a charging pile site according to an embodiment of the present application.

[0033] like Figure 1 As shown, in one embodiment, the site selection method of the charging pile includes: S10: Determine initial parameters of a preset algorithm based on community energy data and charging pile candidate location data.

[0034] For example, the supply of community energy, the demand for community energy, and the locations where charging piles can be built within the community are factors that have a significant impact on the distribution and management of charging piles, and are also the focus of the builders, managers, and users of charging piles. Through the preset algorithm, the data of concern to all parties can be integrated and optimized to solve the management and use problems of charging piles from the source data.

[0035] S20: According to the initial parameters, the preset algorithm is calculated and solved to obtain charging pile site selection and capacity determination data for each charging pile candidate location.

[0036] For example, in the process of fusing data for management optimization through a preset algorithm, the key is to use community energy data and charging pile candidate location data to calculate the fixed capacity data for each charging pile candidate location, so as to evaluate the option that better meets the needs of all parties among multiple charging pile candidate locations.

[0037] S30: Determine the charging pile site selection result based on the charging pile site selection and capacity determination data and a preset selection strategy.

[0038] For example, through appropriate selection strategies, the charging pile site selection and capacity determination data are scientifically evaluated and selected, and then the charging pile locations that meet user needs are screened out.

[0039] This embodiment determines the initial parameters of a preset algorithm based on community energy data and charging pile candidate location data; according to the initial parameters, the preset algorithm is calculated and solved to obtain the charging pile site selection and capacity data for each charging pile candidate location; according to the charging pile site selection and capacity data, the charging pile site selection result is determined based on a preset selection strategy; based on the community location and energy load conditions, it can comprehensively consider factors in multiple dimensions to assist in optimizing the site selection management of charging points and achieve a reasonable layout of charging piles.

[0040] Optionally, the step of determining initial parameters of the preset algorithm includes: A modeling dimension is determined based on the community energy data, and a mathematical model is established for the modeling dimension according to the community energy data and the charging pile candidate location data.

[0041] For example, mathematical modeling is to establish a mathematical model based on practical problems, solve the mathematical model, and then solve the practical problems based on the results.

[0042] When it is necessary to analyze and study a practical problem from a quantitative perspective, people need to use mathematical symbols and language to express and establish a mathematical model based on in-depth investigation and research, understanding object information, making simplified assumptions, and analyzing internal laws. Since community energy data involves multiple aspects of charging pile construction, operation, and use, mathematical modeling of user needs and community realities from different perspectives is conducive to scientifically and quantitatively evaluating the situation of each charging pile candidate location.

[0043] Optionally, the step of calculating and solving the preset algorithm according to the initial parameters to obtain a solution set for each charging pile candidate position includes: The particle swarm algorithm is called to perform iterative fitness calculation on the data model, and after each update of the particle swarm calculation result, an annealing process is performed on the particle swarm calculation result based on the annealing algorithm.

[0044] Exemplarily, the particle swarm algorithm is used as the main algorithm to enhance the global search capability and real-time optimization capability of the simulated charging vehicle group in the process of traversing the optional charging locations. Particle Swarm Optimization (PSO) is an optimization algorithm based on social behavior, inspired by collective behaviors such as bird flocks or fish schools. The algorithm iteratively searches for the optimal solution in the solution space by simulating the cooperation and competition between individuals. Particles adjust their speed and position based on their own experience and the global best solution to search in the target direction. The Simulated Annealing Algorithm (SA) is a global optimization algorithm that simulates the annealing principle in the process of determining the optimal charging point. The algorithm searches for the optimal solution to the problem in the solution space by accepting a worse solution with a certain probability and gradually reducing the acceptance probability. It can be used to solve problems such as combinatorial optimization and parameter solving.

[0045] Based on the particle swarm algorithm, the annealing algorithm is introduced to speed up the search process. After each particle position update, an annealing process is performed on each particle. In this way, the global search capability of the particle swarm algorithm and the local search capability of the annealing algorithm are combined to more effectively search for a better solution in the solution space.

[0046] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The modeling dimension includes an investment cost dimension; the charging pile candidate location data includes the unit price of the charging pile, the fixed investment cost of each charging pile, the investment interest rate and the operating life; the equivalent investment coefficient of the charging pile facilities and equipment and the construction cost in the community and the conversion coefficient of the operating cost and the construction cost are set, and an investment cost model of the investment cost dimension is established based on the number of charging piles constructed.

[0047] The investment cost is the sum of the monetary expenditure of materialized labor and living labor consumed by the fixed asset investment project. For example, the investment cost can be further divided into construction cost, facility equipment cost, fixed cost, land cost, capital cost, etc.

[0048] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The modeling dimensions include the owner satisfaction dimension; the community energy data includes the coordinates of each parking space in the community, the number of charging vehicles in the community, and the service efficiency of charging piles; the maximum waiting time, queue sensitivity coefficient, distance satisfaction weight and waiting time satisfaction weight are set, and an owner satisfaction model of the owner satisfaction dimension is established based on the number of charging piles built.

[0049] The psychological state of measuring and quantifying the user's direct feelings about the charging service with numbers is called satisfaction. Customer satisfaction is the basic condition for customer loyalty. For example, user satisfaction can be further divided into distance satisfaction and waiting time satisfaction.

[0050] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The modeling dimension includes the energy load scheduling dimension; the charging pile candidate location data includes the total community load, other energy equipment load and time-of-use electricity price strategy, determines the scheduling coefficient of the energy storage equipment, and establishes the energy load scheduling model of the owner satisfaction dimension based on the number of charging piles built.

[0051] For example, the use of charging piles requires electricity. Energy load dispatching refers to the fact that electricity production has the characteristics of power generation, power supply, and power consumption being completed instantly and simultaneously, and cannot be stored in large quantities, and various types of power loads have their own inherent power consumption time characteristics, thus forming peaks and valleys in power consumption in the power system, making the power generation and power supply equipment unable to be fully utilized or causing power shortages. With the diversification of community energy sources, the scope of energy load management has also expanded. In addition to traditional power load dispatching, it may involve dispatching and management of various new energy sources such as solar energy.

[0052] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The charging pile candidate location data includes community road coordinates and each charging pile candidate location coordinates, combined with the parking space coordinates, and environmental modeling is performed using an Euler connectivity graph.

[0053] An Euler graph refers to a path that passes through all edges in a graph (undirected or directed) and each edge passes only once. The corresponding loop is called an Euler loop. A graph with an Euler loop is called an Euler graph, and a graph with an Euler path but no Euler loop is called a semi-Euler graph. For example, the distribution of residential areas and road traffic conditions in the community can be obtained through community road coordinates, a community map can be constructed, and the road connection points of community roads can be determined. The candidate location coordinates of the charging pile can be matched and marked on the community map, so that environmental modeling can be performed through the Euler connectivity graph.

[0054] Optionally, the step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes: The demand weight of each modeling dimension is determined according to the community energy data and the charging pile candidate location data, and the objective function of community charging pile site selection is established based on the demand weight.

[0055] For example, when establishing the objective function from the three objective dimensions, in order to ensure the consistency of the optimization direction, the indicators are linearly weighted. Generally, if a certain indicator needs to be minimized, its weight is assigned a positive value; and if a certain indicator needs to be maximized, its weight is assigned a negative value. The purpose of this is to make the optimization direction of all indicators consistent, so as to facilitate the construction of a single objective function for optimization.

[0056] Optionally, the charging pile candidate location data includes the coordinates of the road connection points in the community and the coordinates of the candidate charging points; and the process of determining the initial parameters of the preset algorithm includes: Based on the coordinates of the road connection points and the coordinates of the candidate charging points, determining the population size and the number of outer loop iterations of the particle swarm algorithm, randomly initializing the positions and velocities of multiple particles, and initializing the individual optimal solution and the global optimal solution of each particle; The number of inner loop iterations and the temperature attenuation coefficient of the annealing algorithm are determined, and the termination temperature is calculated.

[0057] For example, in the process of using the particle swarm algorithm, it can be initialized, including setting the number of particle populations and the dimension of each particle; randomly initializing the position and velocity of each particle; initializing the individual best solution and the global best solution of each particle. In the process of the simulated annealing algorithm, initialization can be performed, the initial solution is used as the current optimal solution, and the initial temperature, termination temperature and number of outer loops are initialized.

[0058] Optionally, the step of calling a particle swarm algorithm to iteratively calculate the fitness of the data model includes: When the number of outer loop iterations is not completed, calculating the fitness of each particle in the particle swarm based on the objective function; The cooperation and competition relationship between each proposed charging station is simulated, the individual optimal solution and the global optimal solution are obtained according to the fitness of each particle, the position and speed of each particle are updated, and the initial temperature of the annealing algorithm is updated, and the optimal solution is iteratively searched in the solution space.

[0059] Exemplarily, on the basis of the particle swarm algorithm, the annealing algorithm is introduced to accelerate the search process. After each update of the particle position, an annealing process is performed on each particle. The annealing process accepts or rejects new solutions according to the Metropolis criterion and adjusts the acceptance probability according to the current temperature. As the iteration proceeds, the temperature gradually decreases, controlling the progress of the annealing process. In this way, the global search capability of the particle swarm algorithm and the local search capability of the annealing algorithm are combined to more effectively search for a better solution in the solution space.

[0060] Optionally, the step of simulating the cooperation and competition relationship between each proposed charging station, obtaining the individual optimal solution and the global optimal solution according to the fitness of each particle, and updating the position and speed of each particle includes: Based on the initial position and velocity of each particle in the particle population, a fitness function value is calculated according to the data model, and if the fitness function value is greater than the recorded individual best solution, it is marked as the individual best solution of the particle; The particles in the particle population cooperate to share information to obtain a global optimal solution, and perform iterative calculations to obtain a new position and velocity of the particle.

[0061] For example, in the particle swarm algorithm, the fitness function can be used to determine the attraction of the current position to the particle. The larger the fitness function value, the better the position is, the greater the attraction to the particle, and the more likely this fitness function value is the optimal solution. By simulating the cooperation and competition between individuals, the optimal solution is iteratively searched in the solution space. Particles will adjust their speed and position based on their own experience and the global optimal solution.

[0062] Optionally, after each update of the particle swarm computing result, the process of performing an annealing process on the particle swarm computing result based on an annealing algorithm includes: Based on the number of iterations of the inner loop, the output result of the particle swarm algorithm is used as the current optimal solution, and the acceptance probability is iteratively calculated according to the Metropolis criterion at the current initial temperature; Processing the current optimal solution according to the acceptance probability, and updating the initial temperature and the termination temperature; When the number of iterations of the inner loop is completed, the charging pile site selection and sizing data of the optimal value of the objective function is updated and recorded according to the current optimal solution, and the charging pile site selection and sizing data includes the charging pile investment cost evaluation information, owner satisfaction evaluation information, and energy load scheduling evaluation information corresponding to the site selection coordinates of each charging station.

[0063] For example, based on the particle swarm algorithm, the annealing algorithm is introduced to accelerate the search process of the computational objective function for the best candidate location of the charging pile. After each update of the particle position, an annealing process is performed on each particle. The annealing process accepts or rejects the new solution according to the Metropolis criterion and adjusts the acceptance probability according to the current temperature. As the iteration proceeds, the temperature gradually decreases, controlling the progress of the annealing process.

[0064] Optionally, the process of processing the current optimal solution according to the acceptance probability and updating the initial temperature and the termination temperature includes: The result of the annealing algorithm is accepted with a preset probability at the current initial temperature, the inner loop iteration is executed and the acceptance probability is gradually reduced until the stop condition is met, so as to return to the optimal solution.

[0065] For example, after the annealing algorithm is initialized, the initial solution can be used as the current optimal solution, and the initial temperature, termination temperature and number of outer loops are initialized. Set the main loop, accept the worse solution with a certain probability at the current temperature and gradually reduce the acceptance probability, execute the inner loop (iteration) until the stop condition is met, update the temperature and the new counter, and return the optimal solution. The stop conditions are: (a) Generate a new solution (neighborhood solution).

[0066] (b) Calculate the objective function difference between the current solution and the new solution .

[0067] (c) If Less than or equal to 0, accept the new solution as the current solution.

[0068] (d) Otherwise, according to a certain probability Accept new interpretations, including is the current temperature.

[0069] Optionally, the step of determining the charging pile site selection result based on the charging pile site selection and capacity determination data and based on a preset selection strategy includes: Determine the weight of each indicator in the charging pile site selection and capacity determination data through expert consultation, hierarchical analysis method and fuzzy comprehensive evaluation method, so as to perform weighted processing on the charging pile investment cost evaluation information, owner satisfaction evaluation information and energy load scheduling evaluation information; The charging pile investment cost evaluation information, the owner satisfaction evaluation information, and the energy load scheduling evaluation information are respectively multiplied by their corresponding weights, and then the weighted values ​​of all indicators are summed to obtain a comprehensive evaluation value for each charging pile candidate location; The candidate locations of the charging piles whose comprehensive evaluation values ​​are within the preset evaluation interval are output as the charging pile site selection results.

[0070] For example, a suitable comprehensive evaluation model can be selected according to the specific situation, including the analytic hierarchy process (AHP), fuzzy comprehensive evaluation method, TOPSIS method, etc. First, the indicators are weighted according to the determined indicator weights to reflect their importance in the comprehensive evaluation, and then the selected comprehensive evaluation model is used to perform a comprehensive evaluation calculation on each site selection plan or decision to obtain a comprehensive score. According to the comprehensive score, the comprehensive performance of each site selection plan or decision can be explained, and the contribution and weight of each indicator on the result can be analyzed. Finally, according to the results of the comprehensive evaluation, the final decision or site selection plan can be made, and the plan with the highest comprehensive score can be selected as the best decision.

[0071] For example, in the process of weighting indicators, each evaluation indicator can be quantified and converted into comparable values. For example, the evaluation information of charging pile investment cost can be converted into specific comparable values, the evaluation information of owner satisfaction can be converted into satisfaction scores, and the evaluation information of energy load scheduling can be converted into energy demand.

[0072] Exemplarily, before conducting a comprehensive evaluation, the standardization methods for standardizing the data of each indicator may include linear standardization, interval standardization, and the like. The standardized data is usually between 0 and 1. In the comprehensive weighted calculation stage, for each site selection plan or decision, the standardized indicator value is multiplied by its corresponding weight, and then the weighted values ​​of all indicators are summed. In this way, a comprehensive score can be obtained, which indicates the comprehensive performance of the plan or decision in the comprehensive evaluation. In the result interpretation stage, different site selection plans or decisions can be ranked and compared according to the comprehensive score. A higher comprehensive score indicates that the plan or decision is relatively good in the comprehensive evaluation, and can be used as the best choice, providing a quantitative basis for the final decision.

[0073] Second embodiment In order to achieve better vehicle charging management, in the site selection decision of charging piles, in addition to considering the load demand of operators and community power equipment, it is also necessary to consider the surrounding environmental factors of the charging station, such as traffic convenience, community population density, commercial activities, etc., to ensure that the charging station can serve a wider user group. In addition, in order to minimize the construction and operation costs of charging stations, it is possible to consider choosing locations connected to existing infrastructure, such as small shopping centers, parking lots, etc., so as to reduce the duplication of infrastructure construction and improve resource utilization efficiency. Regarding the power supply problem of charging stations, priority should be given to locations close to power supply facilities of the power grid to ensure power supply reliability and stability, while reducing the construction cost and energy loss of power supply lines.

[0074] When operators select charging station locations, in addition to focusing on controlling investment costs, they also need to consider the changing trends of future market demand. As the electric vehicle market continues to develop and become more popular, charging demand may gradually increase, so choosing a location with potential market demand will help improve the profitability of charging stations. In terms of investment costs, in addition to construction and equipment acquisition costs, operating and maintenance costs also need to be considered. Choosing a location with a suitable location can reduce operating costs. For example, choosing a location close to energy supply facilities and maintenance personnel bases can reduce energy loss and maintenance costs and improve the operating efficiency of charging stations. In addition, operators also need to consider the long-term profitability and payback period of charging stations. Choosing a location with lower investment costs but greater future profit potential can shorten the payback period and improve the return on investment, thereby increasing the operator's profit margin.

[0075] The owners' demand for charging stations is not only reflected in the convenience and experience of charging, but also involves a comprehensive consideration of charging services. In addition to hoping that the number of charging stations will increase, the charging distance will be shortened, and the waiting time in queues will be reduced, the owners are also concerned about whether the facilities and equipment of the charging stations are complete, whether the charging services are stable and reliable, and whether the charging fees are reasonable and fair. These factors will directly affect the owners' satisfaction and overall evaluation of the charging stations. Therefore, when evaluating the owner's satisfaction, it is necessary not only to consider the charging distance and the waiting time in queues, but also to comprehensively consider all aspects of the charging services to more comprehensively quantify the satisfaction of community users. In order to more accurately quantify the owner's satisfaction, a satisfaction function containing multiple factors can be introduced. In addition to considering the charging distance and the waiting time in queues, factors such as the convenience of charging facilities, the stability of services, and the comfort of the charging process can also be considered, so as to more comprehensively reflect the owner's charging experience. By dividing the charging behavior of community users into two parts, driving behavior and in-station behavior, and combining the actual needs and preferences of community users, a satisfaction model that is more in line with the actual situation can be constructed, providing a more scientific basis and guidance for the site selection and operation strategy of charging stations.

[0076] Figure 2 This is a diagram showing the charging time structure of an electric vehicle owner according to an embodiment of the present application.

[0077] In the process of charging station site selection, each demand point and charging station is considered as a point to represent the geographical location or potential construction location. Among them, the demand point refers to the place where electric vehicles need to be charged, and the charging station construction equipment selection refers to the possible location where the charging station can be built. In order to evaluate the distance between the demand point and the charging station, the Euclidean distance is generally used as a measurement standard. The Euclidean distance refers to the straight-line distance between two points, that is, the straight-line distance between the two points on a plane. By calculating the Euclidean distance between the demand point and the charging station, the physical distance between them can be quantified, which serves as an important basis for site selection decisions.

[0078] According to regulations, charging stations adopt the principle of first come first served, that is, the electric car owner who arrives at the charging station first will be the first to receive charging services. However, if the number of electric car owners who arrive at a charging station at the same time exceeds the service capacity of the charging station, that is, the limited number of charging piles or other factors make it impossible to meet all needs, then the owners who arrive later will need to queue up and wait until there are free charging piles available. This queuing method helps to reasonably allocate charging resources, ensure that every owner has the opportunity to receive charging services, and maintain the order and efficiency of the charging station.

[0079] The community area is divided into several small areas, each of which is called a demand point. Secondly, it is assumed that the charging demand in each demand point is equal to the total number of electric vehicles in the area, that is, all electric vehicles in each small area need to be charged. Finally, according to the assumption, all electric vehicles in each demand point can only choose the same charging station for charging, and cannot choose between different charging stations. Such settings and assumptions help to simplify the research model, make the distribution of charging demand clearer, and facilitate the analysis and optimization of charging station site selection and resource allocation.

[0080] When receiving charging services at a charging station, each charging pile can only provide charging services for one electric car at a time, and cannot provide services for multiple electric cars at the same time. This means that when a charging pile is charging an electric car, other electric cars need to wait for the charging pile to be free before they can charge. This rule ensures the independence and fairness of charging services. Each electric car can obtain charging services on a first-come, first-served basis, avoiding service conflicts and waste of resources.

[0081] The amount of electricity obtained from each charging behavior is the same and will not change due to different owners or other factors. This regulation can simplify the management and billing process of charging stations and also facilitate users to estimate and manage charging costs.

[0082] Whether it is a fast charging or slow charging pile, their electrical parameters are the same in the same charging station. This consistency helps improve the management efficiency of the charging station and reduce the complexity of charging equipment maintenance and management caused by inconsistent parameters.

[0083] For example, in the mathematical modeling stage, modeling can be performed according to different dimensions.

[0084] (1) Investment cost of charging piles In order to evaluate the construction cost of operators, charging piles are set up The total construction cost is , charging pile The main purchase cost is , charging pile Related facilities and equipment and construction costs are The total construction cost is:

[0085] Due to the main purchase cost of charging piles It is determined by the quantity and fast charging and slow charging. is the unit price of the fast charging pile, is the number of fast charging piles. is the unit price of the slow charging pile, is the number of slow charging piles, and the total purchase amount formula is as follows:

[0086] For the convenience of representation, it is assumed that the charging pile facilities and construction costs in the community are the product of the equivalent investment coefficient. and ,but:

[0087] The total construction cost can be expressed as:

[0088] set up For charging pile The operating cost of , 𝜂 is the conversion coefficient between the operating cost and the construction cost, then: 𝜂

[0089] Assume that the fixed cost of each charging pile (such as land cost, etc.) is , established within a community The fixed cost of a charging station is Assume that the interest rate at which the investment cost changes over time is , operating period is , then the mathematical modeling expression of the annual investment cost of the charging pile is:

[0090] (2) Owner satisfaction In order to evaluate the comprehensive satisfaction of community owners, it is divided into two parts: satisfaction with charging distance and satisfaction with waiting time. Let distance satisfaction be , For owners from point To the charging station The distance between and Indicates the threshold of distance satisfaction.

[0091]

[0092] set up For satisfaction with waiting time, For owners from point To the charging station The length of time between The maximum waiting time for the owner when the satisfaction level is 1. is the positive sensitivity coefficient of queuing theory, then the waiting time satisfaction is:

[0093] In this model, the number of electric vehicles arriving at the charging station is assumed to be Poisson distributed, and the queue at the charging station follows the first-come, first-served principle. If the charging station has reached its maximum service level when the owner arrives, the owner will wait in line. In this case, the waiting time of the electric vehicle owner can be calculated according to a specific calculation formula. For charging pile The service intensity, is the average number of electric vehicles arriving at charging stations per hour, is the average number of charging pile services per hour, Indicates the efficiency of fast charging service, Indicates the efficiency of slow charging service, is the probability that all charging piles are idle.

[0094]

[0095]

[0096]

[0097] set up is the weight of distance satisfaction, is the weight of satisfaction with waiting time, the total owner satisfaction can be mathematically modeled as follows:

[0098] (3) Energy load dispatch Assume the total load of the community is , by the charging pile load , other energy equipment loads are , the total load can be expressed as:

[0099] Assume the power of the charging pile is , the total power can be expressed as:

[0100] Assuming that the coordinated scheduling between charging piles and other equipment can be achieved by minimizing the total cost or maximizing the system benefit, an optimization model can be established, including the power allocation of charging piles. , the dispatch coefficient of energy storage equipment , time-of-use electricity price strategy ζ, the total electricity consumption time is , then the total function can be mathematically modeled as the expression:

[0101] (4) Objective function The objective function is established from the three objectives. In order to ensure the consistency of the optimization direction, the indicators are linearly weighted. Generally, if a certain indicator needs to be minimized, its weight is assigned a positive value; if a certain indicator needs to be maximized, its weight is assigned a negative value. The purpose of this is to make the optimization direction of all indicators consistent, so as to build a single objective function for optimization.

[0102]

[0103] in They are the investment cost weight of charging piles, owner satisfaction weight, and energy load scheduling weight, respectively. , .in:

[0104]

[0105]

[0106] (5) Constraints To meet the needs Electric car owners go to the candidate charging station The charging demand is based on the candidate charging station Charging piles have been built. is a 0-1 decision variable. If from arrive Receive charging service ,otherwise .set up If there is a charging station, =1, otherwise .

[0107]

[0108] A charging pile can only serve one owner, so the constraints are:

[0109] set up is the arrival rate of owner vehicles in the queuing system, is the average service efficiency of the charging pile, and the constraint on providing service is:

[0110] In the algorithm calculation and solution stage, this application iteratively solves the above objective function by improving the ion group algorithm to assist in finding a more suitable location for charging piles.

[0111] Exemplarily, the particle swarm algorithm is used as the main algorithm to enhance the global search capability and real-time optimization capability of the simulated charging vehicle group in the process of traversing the optional charging locations. Particle Swarm Optimization (PSO) is an optimization algorithm based on social behavior, inspired by collective behaviors such as bird flocks or fish schools. The algorithm iteratively searches for the optimal solution in the solution space by simulating the cooperation and competition between individuals. Particles adjust their speed and position based on their own experience and the global best solution in order to search in the target direction. In the process of using the particle swarm algorithm, it needs to be initialized, which includes setting the number of particles and the dimensions of each particle; randomly initialize the position and velocity of each particle; initialize the individual best solution for each particle and the global optimal solution .

[0112]

[0113]

[0114] Where C1 is the first learning factor, C2 is the second learning factor, is the weight; x is the position vector, and v is the velocity vector.

[0115] The Simulated Annealing Algorithm (SA) is a global optimization algorithm that simulates the annealing principle in the process of determining the optimal charging point. The algorithm searches for the optimal solution to the problem in the solution space by accepting a worse solution with a certain probability and gradually reducing the acceptance probability. It is usually used to solve problems such as combinatorial optimization and parameter solving. The algorithm needs to be initialized, and the initial solution is used as the current optimal solution. The initial temperature, termination temperature, and number of outer loops are initialized. Set the main loop, accept the worse solution with a certain probability at the current temperature and gradually reduce the acceptance probability, execute the inner loop (iteration) until the stop condition is met, update the temperature and the new counter, and return the optimal solution. The stop conditions are: (a) Generate a new solution (neighborhood solution).

[0116] (b) Calculate the objective function difference between the current solution and the new solution .

[0117] (c) If Less than or equal to 0, accept the new solution as the current solution.

[0118] (d) Otherwise, according to a certain probability Accept new interpretations, including is the current temperature.

[0119] Figure 3 This is a flow chart of an improved algorithm according to an embodiment of the present application.

[0120] Please refer to Figure 3 Based on the particle swarm algorithm, this application introduces the annealing algorithm to accelerate the search process. After each update of the particle position, an annealing process is performed on each particle. The annealing process accepts or rejects new solutions according to the Metropolis criterion and adjusts the acceptance probability according to the current temperature. As the iteration proceeds, the temperature gradually decreases, controlling the progress of the annealing process. In this way, the global search capability of the particle swarm algorithm and the local search capability of the annealing algorithm are combined to more effectively search for a better solution in the solution space.

[0121] Figure 4 This is a schematic diagram of the site selection process for community charging piles for this application.

[0122] Step 1: Input data such as community charging demand points and charging pile candidate points. Step 2: Set the algorithm parameters and initialize the parameters related to the location and capacity of charging piles, such as the maximum number of candidate points, the number of charging points to be built, and other parameters.

[0123] Step 3: Model input and model solution. Select multiple proposed charging stations from all candidate charging pile sites as the model input, use the improved particle swarm algorithm to solve the model, and update and record the charging pile site selection results when the objective function takes the optimal value: the charging station site selection coordinates and the charging pile investment cost evaluation information under the current coordinates, the owner satisfaction evaluation information, and the energy load scheduling evaluation information.

[0124] Step 4: Determine whether the iteration is terminated: traverse the combination of charging stations that meet the proposed charging piles, and determine whether the number of iterations (outer loop) has reached the maximum value. If so, output the optimal location and capacity determination result, otherwise jump to execute Step 3.

[0125] Third embodiment Figure 5 This is a community road connectivity diagram according to an embodiment of the present application.

[0126] like Figure 5 As shown, in this embodiment, taking a community as an example, a test case is designed with 15 residential buildings and 100 new energy vehicles in a two-dimensional plane area. Assume that the interest rate R of the year is 0.1, the number of candidate locations of charging stations is set to 7, and the total time T of each charging pile in the charging process is 5. There are 20 road connection points in the community, and 100 electric vehicles that need to be charged are randomly generated in 15 residential buildings.

[0127] For example, when initializing the algorithm, the PSO (ion swarm) algorithm learning factor is set and is 1.5, The inertia weight is 0.8, the population size is 50, the number of iterations is 200, and the internal iteration of the local annealing algorithm is 10; the initial temperature is 10000, and the temperature attenuation coefficient is 0.99. The weights of the three dimensions of charging pile investment cost, owner satisfaction, and energy load scheduling in the objective function (determined according to the demand intensity of the three dimensions) are 0.4, 0.3, and 0.3 respectively. Assume that the number of charging pile services per hour δE is 7, the satisfaction ωm1 (interval is -1-2, initially set to the middle value) is 0.5, and the satisfaction ωm2 is 0.5.

[0128] Please continue to refer to Figure 5 , the entire map is connected based on 20 road connection points. Here, the Euler connection graph is used to model the environment. After the modeling is completed, the site selection is solved.

[0129] Figure 6 This is a graph of calculation results generated according to an embodiment of the present application.

[0130] Please refer to Figure 6After the objective function is solved using the improved particle swarm model, the five-pointed star positions in the figure are candidate charging pile positions and are numbered 1-7 respectively, and the circle shape range is the radiation range that each candidate charging pile position can reach. Figure 6 It can be seen that the seven candidate locations for charging piles can almost cover the area of ​​the entire community, which fully demonstrates the feasibility of mathematical modeling and algorithms.

[0131] Please continue to refer to Figure 6 , based on the data collected from the 7 candidate locations of charging piles in the figure, the mathematical modeling expressions of investment cost, owner satisfaction, and power load scheduling of charging piles are mapped. Taking the candidate location of the charging pile at point 1 as an example, the improved ion swarm algorithm obtains the corresponding charging pile investment cost evaluation information, owner satisfaction evaluation information, and energy load scheduling evaluation information after iterative calculation, which are 1.290, 1.306, and 1.333 respectively. Among the three values ​​here, the investment cost evaluation information exceeds 1, which means that the investment cost may be a little higher, and the investment cost is lower than 1, which means that the investment cost will be lower than the basic cost; the owner satisfaction evaluation information is 1.306, which proves that the owner's satisfaction with the charging pile at position 1 exceeds 1, which is a positive evaluation; the evaluation information of power load scheduling is 1.333, which proves that the scheduling of this point may exceed its own carrying capacity (the evaluation information of power load scheduling is assumed to be normal scheduling if it is below 1, and it is above 1, which means that the local power equipment needs to be modified). Among the candidate locations of the charging pile corresponding to point 2, the three mapping relationships of the charging pile investment cost evaluation information, the owner satisfaction evaluation information, and the energy load scheduling evaluation information are converted to 0.913, 1.361, and 0.901. Based on the above analysis principle, it is proved that the candidate location of the charging pile at point 2 can reduce costs, have high satisfaction, and does not require additional scheduling in terms of power load scheduling.

[0132] The charging pile site selection method provided in the present application determines the initial parameters of a preset algorithm based on community energy data and charging pile candidate location data; according to the initial parameters, the preset algorithm is calculated and solved to obtain the charging pile site selection and capacity data for each charging pile candidate location; according to the charging pile site selection and capacity data, the charging pile site selection result is determined based on a preset selection strategy; based on the community location conditions and energy load conditions, it can comprehensively consider factors in multiple dimensions to assist in optimizing the site selection management of charging points and achieve a reasonable layout of charging piles.

[0133] It should be noted that in the present application, step codes such as S10, S20, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing the step, those skilled in the art may execute S20 first and then S10, etc., but these should all be within the scope of protection of the present application.

[0134] In the system embodiment provided in the present application, all technical features of any of the above-mentioned method embodiments may be included, and the expanded and explained contents of the specification are basically the same as those of the above-mentioned method embodiments, and will not be repeated here.

[0135] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.

[0136] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0137] It is understood that the above scenarios are only examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of the present application. The technical solutions of the present application can also be applied to other scenarios. For example, it is known to those skilled in the art that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0138] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0139] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0140] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0141] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0142] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0144] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for selecting a charging pile site, characterized in that: include: Determine the initial parameters of the preset algorithm based on community energy data and charging pile candidate location data; According to the initial parameters, the preset algorithm is calculated and solved to obtain the charging pile site selection and capacity determination data for each charging pile candidate location; According to the charging pile site selection and capacity determination data, the charging pile site selection result is determined based on a preset selection strategy.

2. A charging pile site selection method according to claim 1, characterized in that: The steps of determining the initial parameters of the preset algorithm include: A modeling dimension is determined based on the community energy data, and a mathematical model is established for the modeling dimension according to the community energy data and the charging pile candidate location data.

3. A method for selecting a charging pile site according to claim 2, characterized in that: The step of calculating and solving the preset algorithm according to the initial parameters to obtain a solution set for each charging pile candidate position includes: The particle swarm algorithm is called to perform iterative fitness calculation on the data model, and after each update of the particle swarm calculation result, an annealing process is performed on the particle swarm calculation result based on the annealing algorithm.

4. A method for selecting a charging pile site according to claim 3, characterized in that: The step of establishing a mathematical model for the modeling dimension according to the community energy data and the charging pile candidate location data includes at least one of the following: The modeling dimension includes an investment cost dimension; the candidate location data of the charging piles includes the unit price of the charging piles, the fixed investment cost of each charging pile, the investment interest rate and the operating life; the equivalent investment coefficient of the charging pile facilities and equipment and the construction cost in the community and the conversion coefficient of the operating cost and the construction cost are set, and the investment cost model of the investment cost dimension is established based on the number of charging piles built; The modeling dimension includes the owner satisfaction dimension; the community energy data includes the coordinates of each parking space in the community, the number of charging vehicles in the community, and the charging pile service efficiency; The maximum waiting time, queue sensitivity coefficient, distance satisfaction weight and waiting time satisfaction weight are set, and an owner satisfaction model of the owner satisfaction dimension is established based on the number of charging piles built; The modeling dimension includes the energy load scheduling dimension; the candidate location data of the charging pile includes the total community load, other energy equipment load and time-of-use electricity price strategy, determines the scheduling coefficient of the energy storage equipment, and establishes the energy load scheduling model of the owner satisfaction dimension based on the number of charging piles built; The candidate location data of the charging pile includes the community road coordinates and the candidate location coordinates of each charging pile, and the environment modeling is performed using the Euler connectivity graph in combination with the parking space coordinates; The demand weight of each modeling dimension is determined according to the community energy data and the charging pile candidate location data, and the objective function of community charging pile site selection is established based on the demand weight.

5. A method for selecting a charging pile site according to claim 4, characterized in that: The charging pile candidate location data includes the coordinates of the road connection points in the community and the coordinates of the candidate charging points; The process of determining the initial parameters of the preset algorithm includes: Based on the coordinates of the road connection points and the coordinates of the candidate charging points, determining the population size and the number of outer loop iterations of the particle swarm algorithm, randomly initializing the positions and velocities of multiple particles, and initializing the individual optimal solution and the global optimal solution of each particle; The number of inner loop iterations and the temperature attenuation coefficient of the annealing algorithm are determined, and the termination temperature is calculated.

6. A method for selecting a charging pile site according to claim 5, characterized in that: The step of calling the particle swarm algorithm to iteratively calculate the fitness of the data model includes: When the number of outer loop iterations is not completed, calculating the fitness of each particle in the particle swarm based on the objective function; The cooperation and competition relationship between each proposed charging station is simulated, the individual optimal solution and the global optimal solution are obtained according to the fitness of each particle, the position and speed of each particle are updated, and the initial temperature of the annealing algorithm is updated, and the optimal solution is iteratively searched in the solution space.

7. A method for selecting a charging pile site according to claim 6, characterized in that: The step of simulating the cooperation and competition relationship between each proposed charging station, obtaining the individual optimal solution and the global optimal solution according to the fitness of each particle, and updating the position and speed of each particle includes: Based on the initial position and velocity of each particle in the particle population, a fitness function value is calculated according to the data model, and if the fitness function value is greater than the recorded individual best solution, it is marked as the individual best solution of the particle; The particles in the particle population cooperate to share information to obtain a global optimal solution, and perform iterative calculations to obtain a new position and velocity of the particle.

8. A method for selecting a charging pile site according to claim 7, characterized in that: The process of performing an annealing process on the particle swarm operation result based on the annealing algorithm after each update of the particle swarm operation result includes: Based on the number of iterations of the inner loop, the output result of the particle swarm algorithm is used as the current optimal solution, and the acceptance probability is iteratively calculated according to the Metropolis criterion at the current initial temperature; Processing the current optimal solution according to the acceptance probability, and updating the initial temperature and the termination temperature; When the number of iterations of the inner loop is completed, the charging pile site selection and sizing data of the optimal value of the objective function is updated and recorded according to the current optimal solution, and the charging pile site selection and sizing data includes the charging pile investment cost evaluation information, owner satisfaction evaluation information, and energy load scheduling evaluation information corresponding to the site selection coordinates of each charging station.

9. A method for selecting a charging pile site according to claim 8, characterized in that: The process of processing the current optimal solution according to the acceptance probability and updating the initial temperature and the termination temperature includes: The result of the annealing algorithm is accepted with a preset probability at the current initial temperature, the inner loop iteration is executed and the acceptance probability is gradually reduced until the stop condition is met, so as to return to the optimal solution.

10. A method for selecting a charging pile site according to any one of claims 1 to 9, characterized in that: The step of determining the charging pile site selection result based on the charging pile site selection and capacity determination data and based on a preset selection strategy comprises: Determine the weight of each indicator in the charging pile site selection and capacity determination data through expert consultation, hierarchical analysis method and fuzzy comprehensive evaluation method, so as to perform weighted processing on the charging pile investment cost evaluation information, owner satisfaction evaluation information and energy load scheduling evaluation information; The charging pile investment cost evaluation information, the owner satisfaction evaluation information, and the energy load scheduling evaluation information are respectively multiplied by their corresponding weights, and then the weighted values ​​of all indicators are summed to obtain a comprehensive evaluation value for each charging pile candidate location; The candidate locations of the charging piles whose comprehensive evaluation values ​​are within the preset evaluation interval are output as the charging pile site selection results.

Images