Method, device and equipment for orderly charging of electric vehicles and storage medium

Abstract

The application provides an orderly charging method, device and equipment of an electric vehicle and a storage medium. It relates to the technical field of big data. The method comprises the following steps: taking multiple charging powers of the electric vehicle at different time points as particles of an initial population of an NSGA2 algorithm, and substituting the particles into a target optimization function of the lowest charging cost and a target optimization function of user charging satisfaction; obtaining an external non-dominated solution set by calculation; evaluating the evolution state of the NSGA2 algorithm according to the probability value of the external non-dominated solution set, including a convergence state and a diversity state; improving the diversity by population conversion if the algorithm is in the diversity state; obtaining a particle with the minimum potential energy value and calculating a global optimal value; selecting a compromise solution as a target charging power in the global optimal value; and performing orderly charging of the electric vehicle according to the target charging power. The method reduces the charging cost of the user and improves the charging satisfaction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, and particularly relates to an orderly charging method and device for an electric vehicle, an electric vehicle charging equipment and a storage medium. BACKGROUND

[0002] At present, electric vehicles become the development trend of future automobile market. Due to the endurance problem of batteries, the convenience and cost of charging electric vehicles have become a common concern of people.

[0003] In the prior art, the charging process of electric vehicles lacks scientific and effective management. For example, due to the influence of user travel habits, obvious charging peaks appear at certain time periods.

[0004] The inventor finds that the charging process of electric vehicles in the prior art mainly has the following problems: charging at a charging peak will exacerbate the power supply pressure of the power grid, and charging at a high electricity price period will also increase the charging cost of users and reduce the charging satisfaction of users. SUMMARY

[0005] The present application provides an orderly charging method and device for an electric vehicle, an electric vehicle charging equipment and a storage medium, to solve the problem of high charging cost caused by the lack of scientific and effective management in the charging process of electric vehicles in the prior art.

[0006] In a first aspect, the present application provides an orderly charging method for an electric vehicle, comprising:

[0007] The multiple charging powers of the electric vehicle at different time points are taken as particles of an initial population of an NSGA2 algorithm to substitute into an objective optimization function of the lowest charging cost and an objective optimization function of user charging satisfaction, to calculate the function values corresponding to each particle in the initial population, wherein the NSGA2 algorithm includes a preset number of particles in the initial population and an iteration number;

[0008] The domination relationship of the particles in the initial population is calculated according to the function values, to obtain an external non-dominated solution set, the entropy value of the external non-dominated solution set is calculated, the probability value is obtained according to the entropy value, and the evolution state of the NSGA2 algorithm is evaluated according to the probability value entropy value;

[0009] If the evolution state of the NSGA2 algorithm is in a convergence state, the particle with the minimum potential energy value is selected as a global optimal solution; if the evolution state of the NSGA2 algorithm is in a diversity state, the particle with the minimum density value is selected as a global optimal solution, and a population conversion operation is performed, the particles obtained by the population conversion are arranged in ascending order of potential energy value, and the first N particles are selected and returned, wherein N is a positive integer;

[0010] updating the velocity and position of the particle with the minimum potential energy value, the particle with the minimum density value and the first N particles, and updating the global optimal value found by the particle with the minimum potential energy value, the particle with the minimum density value and the first N particles in this iteration according to the velocity and position;

[0011] determining whether the NSGA2 algorithm reaches a preset iteration number, if not, returning to the step of calculating the dominance relation of the particles in the initial population according to the function value, and if yes, outputting the global optimal value and selecting a compromise solution as a target charging power using a TOPSIS method in the global optimal value, and performing orderly charging of the electric vehicle according to the target charging power.

[0012] In a possible design, before the electric vehicle charging power is substituted into the target optimization function of the lowest charging cost and the target optimization function of the user charging satisfaction as the particles of the initial population of the NSGA2 algorithm, the method further includes: establishing a charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times, and establishing the target optimization function of the lowest charging cost and the target optimization function of the user charging satisfaction according to the charging and discharging model.

[0013] After the charging is completed, the charging cost is calculated according to the current electricity price information, and charging completion reminding information is pushed to the user, so that the user realizes no-sense payment through a quick payment function.

[0014] In a possible design, the method of establishing the charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times, and establishing the target optimization function of the lowest charging cost and the target optimization function of the user charging satisfaction according to the charging and discharging model includes: a formula for establishing the charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times is as follows:

[0015]

[0016] wherein E a (t+1) represents the battery storage capacity at t+1 time; E a (t) represents the battery storage capacity at t time; represents the charging power or discharging power of the electric vehicle at t time, the charging power of the electric vehicle is set to be positive, that is, the discharging power is negative, that is, η ch and η dis respectively represent the battery charging efficiency and discharging efficiency; Δt represents the experimental simulation step length.

[0017] The calculation formula of the target optimization function of the lowest charging cost according to the charging and discharging model is as follows:

[0018]

[0019] F1 represents an optimized economic index, used to measure the change of the optimized electricity cost; represents the charging power or discharging power of the electric vehicle at time t; represents the constant charging power; γ(t) represents the electricity price information at time t; Δt represents the experimental simulation step; s represents the charging start time, and e represents the charging end time;

[0020] The calculation formula of the target optimization function of the user charging satisfaction degree according to the charging and discharging model is as follows:

[0021] min F2 = (E a (t) - E set ) 2 ;

[0022] F2 represents an optimized satisfaction index, used to measure the optimized electricity satisfaction degree; E a (t) represents the battery storage capacity at time t, that is, the actual storage capacity when charging is completed, and the unit is KWh; and E set represents the ideal storage capacity set by the user, and the unit is KWh.

[0023] In a possible design, the function value is used to calculate the dominance relationship of the particles in the initial population, to obtain an external non-dominated solution set, to calculate the entropy value of the external non-dominated solution set, to obtain a probability value according to the entropy value, and to evaluate the evolution state of the NSGA2 algorithm according to the probability value, including: the function value is used to calculate the dominance relationship of the particles in the initial population, and the calculated non-dominated solution is stored in the external non-dominated solution set; the entropy value of the external non-dominated solution set is calculated, and the probability value is obtained according to the entropy value; it is judged whether a random value is greater than or equal to the probability value, if yes, the NSGA2 algorithm is in a convergence state, and if not, the NSGA2 algorithm is in a diversity state.

[0024] In a possible design, the entropy value of the external non-dominated solution set is calculated, and the probability value is obtained according to the entropy value, including: the calculation formula of the entropy value of the external non-dominated solution set is as follows:

[0025]

[0026] H g represents the entropy value of the gth iteration; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population; is the number of non-dominated solutions in the mth column of the kth row in the gth iteration;

[0027] The calculation formula of the probability value according to the entropy value is:

[0028]

[0029] ΔH g = H g - H g-1 ;

[0030] In the formula, Pr g represents a probability value; ΔH g represents the change of the entropy value; H g represents the population entropy value of the gth iteration; H g -1 represents the population entropy value of the (g-1)th iteration; δ represents the threshold of the change of the entropy value; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population.

[0031] In a possible design, before the calculation of the entropy value of the external non-dominated solution set, the calculation of the probability value according to the entropy value, and the evaluation of the evolution state of the NSGA2 algorithm according to the probability value, the method further includes: calculating the coordinate value corresponding to a particle in the external non-dominated solution set, and calculating the potential energy value and the density value of the particle according to the coordinate value.

[0032] In a possible design, the calculation of the coordinate value corresponding to a particle in the external non-dominated solution set and the calculation of the potential energy value and the density value of the particle according to the coordinate value include: the calculation formula of the coordinate value corresponding to a particle in the external non-dominated solution set is:

[0033]

[0034] In the formula, represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet; represents the rounding operation; represents the function value of the kth non-dominated solution in the external non-dominated solution set on the mth objective optimization function; K represents the total number of particles in the external non-dominated solution set; and the calculation formula of the potential energy value of the particle according to the coordinate value is:

[0035]

[0036] In the formula, φ(x k ) represents the potential energy value; m represents the mth objective optimization function, and M represents the total number of particles in the initial population; represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet; and the calculation formula of the density value of the particle according to the coordinate value is:

[0037]

[0038]

[0039] wherein, p(x k ) represents a density value; d PC (x k , x l ) represents the distance sum of the individual k and other particles in the external non-dominated solution set; l and k respectively represent two arbitrary particles in the external non-dominated solution set; m represents the mth objective optimization function; and M represents the total number of particles in the initial population; represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet.

[0040] In a possible design, the population conversion operation is performed, the particles converted from the population are arranged in ascending order of potential energy values, and the first N particles are selected and returned, including: obtaining all non-dominated solutions in the external non-dominated solution set, performing binary crossover and polynomial mutation of the MOPSO algorithm on the all non-dominated solutions to generate a sub-population; merging the initial population of the MOPSO algorithm and the sub-population to obtain a parent-child population; calculating the coordinate values corresponding to the particles in the parent-child population, calculating the potential energy values of the particles in the parent-child population according to the coordinate values; and arranging the particles in the parent-child population in ascending order of potential energy values, selecting and returning the first N particles, wherein N is a positive integer.

[0041] In a possible design, the velocity and position of the particle with the minimum potential energy value and the first N particles are updated, and the calculation formula of the global optimal value found by the population particle in the current iteration according to the velocity and position is as follows:

[0042]

[0043] wherein, ω represents an inertia weight parameter, r1 and r2 are random numbers with values between 0 and 1, c1 and c2 are acceleration constants, i and g are respectively particle and iteration number indexes, and respectively represent the position and flight velocity searched by the ith particle in the gth iteration, and respectively represent the individual optimal position currently found by the particle i and the global optimal value found by the population in the gth iteration.

[0044] In a second aspect, the present application provides an orderly charging device for an electric vehicle, comprising:

[0045] The computing module is configured to: take multiple charging powers of the electric vehicle at different time points as particles of an initial population of an NSGA2 algorithm, and substitute the particles into objective optimization functions of charging cost minimization and user charging satisfaction, to obtain function values corresponding to each particle in the initial population, wherein the NSGA2 algorithm includes a preset number of particles in the initial population and a preset number of iterations;

[0046] The evaluation module is configured to: calculate a dominance relationship of the particles in the initial population according to the function values, to obtain an external non-dominated solution set, calculate an entropy value of the external non-dominated solution set, obtain a probability value according to the entropy value, and evaluate an evolution state of the NSGA2 algorithm according to the probability value;

[0047] The population conversion module is configured to: if the evolution state of the NSGA2 algorithm is in a convergence state, select a particle with a minimum potential energy value as a global optimal solution; if the evolution state of the NSGA2 algorithm is in a diversity state, select a particle with a minimum density value as the global optimal solution, and perform a population conversion operation to obtain particles by population conversion, arrange the particles in ascending order of the potential energy value, and select and return the first N particles, where N is a positive integer.

[0048] The updating module is configured to: update velocities and positions of the particle with the minimum potential energy value, the particle with the minimum density value, and the first N particles, and update a global optimal value found by the particle with the minimum potential energy value, the particle with the minimum density value, and the first N particles in the current iteration according to the velocities and the positions.

[0049] The output module is configured to: determine whether the NSGA2 algorithm reaches the preset number of iterations, if not, return to the step of calculating the dominance relationship of the particles in the initial population according to the function values, and if yes, output the global optimal value, and select a compromise solution as a target charging power by using a TOPSIS method in the global optimal value, and perform ordered charging of the electric vehicle according to the target charging power.

[0050] The payment module is configured to: calculate a charging cost according to current price information after charging is completed, and push charging completion reminding information to the user, so that the user realizes non-sensing payment through a quick payment function.

[0051] In a third aspect, an electronic device is provided, including: a processor, and a memory in communication connection with the processor;

[0052] The memory stores computer execution instructions, and the processor executes the computer execution instructions stored in the memory to implement the ordered charging method of the electric vehicle as described in the first aspect and various possible designs of the first aspect.

[0053] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and when a processor executes the computer execution instructions, the ordered charging method of the electric vehicle is implemented.

[0054] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, and when the computer program is executed by a processor, the ordered charging method of the electric vehicle is implemented.

[0055] The ordered charging method of the electric vehicle, the device, the equipment and the storage medium provided by the present application can solve the problem of high charging cost caused by the lack of scientific and effective management in the charging process of the electric vehicle, reduce the charging cost of the user, and improve the charging satisfaction. BRIEF DESCRIPTION OF DRAWINGS

[0056] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application.

[0057] Figure 1 The flow of the ordered charging method of the electric vehicle provided by the embodiment of the present application Figure 1 ;

[0058] Figure 2 The flow of the ordered charging method of the electric vehicle provided by the embodiment of the present application Figure 2 ;

[0059] Figure 3 The structural schematic diagram of the ordered charging device of the electric vehicle provided by the embodiment of the present application

[0060] Figure 4 The structural schematic diagram of the electronic device provided by the embodiment of the present application

[0061] Figure 5 The Pareto front solution distribution diagram of the five algorithms provided by the embodiment of the present application

[0062] The present application has been shown and described with reference to the preferred embodiments. Equivalent mechanisms and methods incorporating only functionally similar to those described herein are within the scope of the application. Therefore, the application is not limited except as indicated in the appended claims. DETAILED DESCRIPTION

[0063] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The description herein is intended for illustrating the conceptual aspects of the application by way of example and by reference to particular embodiments. It is therefore contemplated that other embodiments, modifications, and variations can be made in the application, as will be apparent to those skilled in the art from consideration of the disclosure. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0064] Terminology:

[0065] Heuristic Algorithm: A heuristic algorithm is an algorithm based on intuition or experience, which gives all feasible solutions of an optimization problem space under the convergence criteria of the algorithm. The heuristic algorithm is mainly designed by simulating the relevant behavior experience in the fields of biology, physics and society, such as particle swarm algorithm, ant colony algorithm, simulated annealing algorithm, etc.

[0066] Electric vehicle orderly charging: According to the electric vehicle charging cost model and satisfaction model, and combined with the current electricity price situation, the charging power of electric vehicle in each period is regulated through heuristic algorithm, and the charging demand in high electricity price period is transferred to low electricity price period, which reduces the user charging cost while ensuring the completion of battery charging target.

[0067] At present, electric vehicles have become the trend of future automobile market development. Due to the problem of battery endurance, the convenience and cost of electric vehicle charging have become a common concern. The existing technology lacks scientific and effective management in the process of electric vehicle charging. For example, due to the influence of user travel habits, obvious charging peak value appears in some periods, or the charging and discharging characteristics of battery vehicles are not considered, which cannot guarantee to reduce the user's charging cost under the premise of reaching the specified power when the electric vehicle leaves. The existing technology of electric vehicle charging process mainly has the following problems: charging in the charging peak will aggravate the power supply pressure of the power grid, and charging in the high electricity price period will also increase the charging cost of users and reduce the charging satisfaction of users.

[0068] To solve the above technical problems, the application proposes the following technical concept: multiple charging powers of the electric vehicle at different times are taken as particles of an initial population of an NSGA2 algorithm to be substituted into an objective optimization function of minimum charging cost and an objective optimization function of user charging satisfaction, an external non-dominated solution set is obtained by calculation, the evolution state of the NSGA2 algorithm is evaluated according to the probability value of the external non-dominated solution set, including the convergence state and the diversity state, if the diversity state is reached, the diversity is improved by population conversion, the particle with the minimum potential energy value is obtained and the global optimal value is calculated, a compromise solution is selected as the target charging power from the global optimal value, and the electric vehicle is charged in order according to the target charging power, so that the problem of high charging cost caused by the lack of scientific and effective management in the charging process of the electric vehicle in the prior art can be solved.

[0069] The technical solutions of the application and how the technical solutions solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the application will be described below with reference to the drawings.

[0070] The embodiment of the application provides an orderly charging method of an electric vehicle. Figure 1 The flow of the orderly charging method of the electric vehicle provided by the embodiment of the application Figure 1 The execution subject of the method of the embodiment can be a server, which is not particularly limited in the embodiment. As shown in the figure, the orderly charging method of the electric vehicle includes: Figure 1

[0071] S101, multiple charging powers of the electric vehicle at different times are taken as particles of an initial population of an NSGA2 algorithm to be substituted into an objective optimization function of minimum charging cost and an objective optimization function of user charging satisfaction, and the function value corresponding to each particle in the initial population is calculated, wherein the NSGA2 algorithm includes the number of particles in the initial population and the number of iterations.

[0072] In the embodiment, the NSGA2 (Non-dominated Sorting Genetic Algorithms) 2 algorithm is a multi-objective optimization algorithm based on Pareto optimal solution, the core of which is to coordinate the relationship between each objective function and find the optimal solution set that makes each objective function reach a relatively large or small function value. Among many genetic algorithms for objective optimization, the NSGA2 algorithm is a multi-objective genetic algorithm with the widest application range and the greatest influence, and has the characteristics of simplicity and effectiveness.

[0073] ​In this embodiment, before the charging power of the electric vehicle is substituted into the objective optimization function of the lowest charging cost and the objective optimization function of the user charging satisfaction as the initial population of the NSGA2 algorithm, the following is further included: establishing a charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times, and establishing the objective optimization function of the lowest charging cost and the objective optimization function of the user charging satisfaction according to the charging and discharging model.

[0074] Specifically, the formula for establishing the charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times is as follows:

[0075]

[0076] In the formula, E a (t+1) represents the battery storage capacity at time t+1; E a (t) represents the battery storage capacity at time t; represents the charging power or discharging power of the electric vehicle at time t, and the charging power of the electric vehicle is set to be positive, i.e. the discharging power is negative, i.e. η ch and η dis represent the charging efficiency and discharging efficiency of the battery, respectively; and Δt represents the experimental simulation step length.

[0077] The current state of charge Soc a (t) can be obtained by the ratio of the battery storage capacity E a (t) at time t to the total capacity C a of the battery. In order to avoid damage to the battery life due to too low or too high battery capacity, the state of charge of the battery is constrained by formula (3), and represent the minimum and maximum states of charge, respectively. During the experimental simulation process, the charging and discharging power of the battery also affects the battery life, and the charging and discharging processes are constrained by formulas (4) and (5).

[0078]

[0079] The maximum energy storage capacity and the minimum energy storage capacity of the battery of the electric vehicle are used to regulate the inappropriate charging and discharging power. Formula (4) adjusts the charging power in the overcharged state, and formula (5) adjusts the discharging power in the overdischarged state.

[0080] The calculation formula of the objective optimization function of the lowest charging cost established according to the charging and discharging model is as follows:

[0081]

[0082] F1 represents an optimized economic index, used to measure the change of the optimized electricity cost; represents the charging power or discharging power of the electric vehicle at t time; represents the constant charging power; γ(t) represents the electricity price information at t time; Δt represents the experimental simulation step; s represents the charging start time, and e represents the charging end time.

[0083] If F1<1, it indicates that the optimized electricity cost is lower than the electricity cost before optimization, and the smaller the value is, the better the economic degree after optimization is, and vice versa.

[0084] In order to ensure that the electric vehicle participating in the dispatch reaches the specified power value when the user leaves, the optimization scheme of charging is evaluated through the penalty function constraint, and the more the battery power is at the charging end time, the smaller the punishment degree is, and vice versa. According to the charging and discharging model, the calculation formula of the target optimization function of the user charging satisfaction is as follows:

[0085] min F2 = (E a (t) - E set ) 2 (7)

[0086] F2 represents an optimized satisfaction index, used to measure the optimized electricity satisfaction; E a (t) represents the battery power at t time, that is, the actual power at the end of charging, and the unit is KWh; E set represents the ideal power set by the user, and the unit is KWh.

[0087] Specifically, the number of particles in the preset initial population is determined according to the actual situation, for example, 150, 200 or 250, and the embodiment of the application does not make specific limitation on this.

[0088] The preset number of iterations is determined according to the actual situation, for example, 400 times, 500 times or 600 times, and the embodiment of the application does not make specific limitation on this.

[0089] S102, the dominance relationship of the particles in the initial population is calculated according to the function value, the external non-dominated solution set is obtained, the entropy value of the external non-dominated solution set is calculated, the probability value is obtained according to the entropy value, and the evolution state of the NSGA2 algorithm is evaluated according to the probability value.

[0090] In the embodiment, the dominance relation of the particles in the initial population is calculated according to the function values, the non-dominated solutions calculated are stored in an external non-dominated solution set, the entropy value of the external non-dominated solution set is calculated, and the probability value is obtained according to the entropy value; whether a random value is greater than or equal to the probability value is judged, if yes, the NSGA2 algorithm is in a convergence state, and if no, the NSGA2 algorithm is in a diversity state.

[0091] The dominance relation of the particles in the initial population is calculated according to the function values, and the dominance relation here refers to a Pareto dominance relation. The Pareto dominance relation is a concept commonly used in multi-objective optimization and is used to describe the superior-inferior relation between two solutions. If one solution is superior to another solution in all objective functions, the former dominates the latter. Specifically, assuming that two solutions are x1 and x2, and the objective function values are fl(x1), f2(x1), f1(x2) and f2(x2), x1 dominates x2 when and only when: fl(x1)≤f1(x2) and f2(x1)≤f2(x2) and at least one objective function value satisfies a strict inequality. In other words, if one solution is at least equivalent to another solution in all objective functions and superior to it in a certain objective function, the former dominates the latter. Otherwise, if the two solutions are the same in all objective functions or x2 dominates x1, they do not constitute a Pareto dominance relation.

[0092] The NSGA2 algorithm stores the non-dominated solutions found in each iteration into the external non-dominated solution set, that is, the external non-dominated solution set is the set of non-dominated solutions in each iteration.

[0093] Specifically, the calculation formula of the entropy value of the external non-dominated solution set is:

[0094]

[0095] In the formula, H g represents the entropy value of the gth iteration; K represents the total number of particles in the external non-dominated solution set; M represents the total number of particles in the initial population; is the number of non-dominated solutions in the kth row and mth column in the gth iteration;

[0096] The calculation formula of the probability value obtained according to the entropy value is:

[0097]

[0098] ΔH g = H g - H g-1 (11)

[0099] In the formula, Pr g represents a probability value; ΔH g represents the change in the entropy value; Hg Hg represents the population entropy value at the gth iteration; Hg-1 represents the population entropy value at the (g-1)th iteration; δ represents a threshold value of the entropy value change; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population. g-1 Hg represents the population entropy value at the gth iteration; Hg-1 represents the population entropy value at the (g-1)th iteration; δ represents a threshold value of the entropy value change; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population.

[0100] In this embodiment, the convergence and diversity are two basic problems in the multi-objective evolutionary algorithm, the convergence state refers to the state of continuously refining the existing solution, and the diversity state refers to the state of searching for a new feasible solution. Selecting the particle with the minimum density value as the global optimal solution can improve the diversity of the solution, and selecting the particle with the minimum potential energy value as the global optimal solution can improve the convergence.

[0101] In this embodiment, after the domination relationship of the particles in the initial population is calculated according to the function values, the external non-dominated solution set is obtained, the entropy value of the external non-dominated solution set is calculated, the probability value is obtained according to the entropy value, and before the evolutionary state of the NSGA2 algorithm is evaluated according to the probability value, the following steps are further included: calculating the coordinate values corresponding to the particles in the external non-dominated solution set, and calculating the potential energy value and the density value of the particles according to the coordinate values.

[0102] Specifically, the calculation formula for calculating the coordinate values corresponding to the particles in the external non-dominated solution set is:

[0103]

[0104] In the formula, φ(x represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet; represents the rounding operation; represents the function value of the kth non-dominated solution in the external non-dominated solution set on the mth objective optimization function; and K represents the total number of particles in the external non-dominated solution set.

[0105] The calculation formula for calculating the potential energy value of the particles according to the coordinate values is:

[0106]

[0107] In the formula, φ(x k ) represents the potential energy value; m represents the mth objective optimization function, and M represents the total number of particles in the initial population; represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet.

[0108] The calculation formula for calculating the density value of the particles according to the coordinate values is:

[0109]

[0110] In the formula, ρ(x k ) represents the density value; dPC (x k ,x l ) represents the distance between individual k and other particles in the external non-dominated solution set; l and k represent any two particles in the external non-dominated solution set; m represents the mth objective optimization function; M represents the total number of particles in the initial population; represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet.

[0111] S103, determine whether a random value is greater than or equal to a probability value, if yes, execute step S104, if no, execute step S105;

[0112] In this embodiment, a random value between [0-1] is randomly generated, if the random value is greater than the probability value Pr g , the particle with the minimum potential energy value in the external non-dominated solution set will be selected as the global optimal solution. Otherwise, the probability of selecting the particle with the minimum density value as the global optimal solution is 1-Pr g .

[0113] S104, determine that the evolution state of the NSGA2 algorithm is in the convergence state, and select the particle with the minimum potential energy value as the global optimal solution.

[0114] In this embodiment, when the random value is greater than or equal to the probability value Pr g , the evolution state of the NSGA2 algorithm is in the convergence state, and the particle with the minimum potential energy value in the external non-dominated solution set is selected as the global optimal solution.

[0115] S105, determine that the evolution state of the NSGA2 algorithm is in the diversity state, select the particle with the minimum density value as the global optimal solution, and perform a population conversion operation, arrange the particles obtained by the population conversion in ascending order of potential energy value, select and return the first N particles, where N is a positive integer.

[0116] In this embodiment, when the random value is less than the probability value Pr g , the evolution state of the NSGA2 algorithm is in the diversity state, which means that the diversity of the population needs to be improved, and genetic operation needs to be performed on the population particles to improve the diversity of the population, so the particle with the minimum density value is selected as the global optimal solution while the population conversion operation is performed.

[0117] S106, update the speed and position of the particle with the minimum potential energy value, the particle with the minimum density value, and the first N particles, and update the global optimal value found by the particle with the minimum potential energy value, the particle with the minimum density value, and the first N particles in this iteration according to the speed and position.

[0118] In this embodiment, the particle with the minimum potential energy value, the particle with the minimum density value and the velocity and position of the first N particles are updated, and the calculation formula of the global optimal value found by the particle with the minimum potential energy value, the particle with the minimum density value and the first N particles in this iteration according to the velocity and position is:

[0119]

[0120] In the formula, ω represents an inertia weight parameter, r1 and r2 are random numbers with values between [0, 1], c1 and c2 are acceleration constants, i and g are particle and iteration number indexes respectively, and respectively represent the position and flight velocity searched by the i-th particle in the g-th iteration, and respectively represent the individual optimal position currently found by the particle i and the global optimal value found by the population in the g-th iteration.

[0121] The functions of c1 and c2 are to adjust the step length of the particle flying in the two guiding directions of the individual optimal position and the global optimal position.

[0122] S107, it is judged whether the NSGA2 algorithm reaches a preset iteration number, if not, step 102 is executed, and if yes, step S108 is executed.

[0123] In this embodiment, the preset iteration number has been set in step S101 and is determined according to actual conditions, for example, 400 times, 500 times or 600 times, and the embodiment of the present application does not make specific limitation on this.

[0124] S108, the global optimal value is output, a compromise solution is selected as the target charging power in the global optimal value by using a TOPSIS method, and the orderly charging of the electric vehicle is performed according to the target charging power.

[0125] In this embodiment, the global optimal value found by the population in the g-th iteration has been obtained in step S106 the global optimal value is output a compromise solution is selected as the target charging power in the global optimal value by using a TOPSIS method, wherein the TOPSIS method includes the following steps: normalizing a decision matrix, calculating a weighted normalized decision matrix, determining a positive ideal solution NIS, calculating the Euclidean distance of each individual from the PIS and NIS, calculating the relative closeness coefficient of each Pareto front solution from the PIS, performing descending order sorting on the Pareto front according to the relative closeness coefficient, selecting the first individual as the compromise solution, and taking the compromise solution as the target charging power.

[0126] S109. After charging is completed, the charging fee is calculated based on the current electricity price information, and a charging completion reminder message is pushed to the user so that the user can make a seamless payment through the quick payment function.

[0127] In this embodiment, users typically leave their vehicles during the charging process. Therefore, when the car finishes charging, the lack of a notification will cause the electric vehicle to occupy the charging equipment resources for an extended period, increasing the user's charging costs. Thus, in this embodiment, after calculating the charging fee upon completion, a charging completion notification will be sent to the user so that they can complete the payment.

[0128] To verify the performance of the ordered charging method (i.e., hybrid algorithm) for electric vehicles according to embodiments of the present invention, the method was compared with the results of NSGA-II, SPEA2, PESA2, and MOPSO algorithms on four multi-objective test functions, namely ZDT1, ZDT2, ZDT3, and ZDT4. The population size of all algorithms was set to 200, and the number of iterations was set to 500. Figure 5 The distribution of Pareto front solutions for each algorithm under different test functions is presented.

[0129] Figure 5 Pareto front solution distribution diagrams for the five algorithms provided in the embodiments of this application, from Figure 5 As can be seen from the above, the solution set obtained by the ordered charging method for electric vehicles (i.e., the hybrid algorithm) in this embodiment of the invention is closer to the real Pareto front than that of other algorithms, and is significantly better than other algorithms.

[0130] In summary, the orderly charging method for electric vehicles in this embodiment uses multiple charging powers of the electric vehicle at different times as particles in the initial population of the NSGA2 algorithm. These particles are then substituted into the objective optimization functions for minimizing charging costs and user charging satisfaction. An external non-dominated solution set is calculated, and the evolutionary state of the NSGA2 algorithm is evaluated based on the probability values ​​of this set. If the algorithm is in a convergent state, the particle with the lowest potential energy is selected as the global optimal solution. If it is in a diverse state, the particle with the lowest density is selected as the global optimal solution, and diversity is increased through population transformation. A compromise solution is chosen from the global optimal values ​​as the target charging power. Orderly charging of the electric vehicle is then performed based on this target charging power. Therefore, this method can solve the problem of high charging costs caused by a lack of scientific and effective management in the electric vehicle charging process, reducing user charging costs and improving charging satisfaction.

[0131] Figure 2 The flowchart of the orderly charging method for electric vehicles provided in the embodiments of this application Figure 2 .like Figure 2 As shown, the orderly charging method for this electric vehicle includes the following steps:

[0132] S201, obtain all non-dominated solutions in the external non-dominated solution set, perform binary crossover and polynomial mutation of the MOPSO algorithm on all non-dominated solutions to generate a sub-population.

[0133] In this embodiment, the MOPSO (multi-objective particle swarm optimization) algorithm is a particle swarm optimization (PSO) algorithm originally used for single-objective optimization applied to multi-objective optimization. The MOPSO algorithm is a commonly used algorithm in multi-objective optimization algorithms. The MOPSO uses an external repository and a grid-based particle distribution method to maintain the diversity of the population. All non-dominated solutions in the non-dominated solution set obtained by the NSGA2 algorithm are used as the initial population of the MOPSO algorithm, and then the conventional binary crossover and polynomial mutation operations of the MOPSO algorithm are performed on the initial population to generate a sub-population.

[0134] When the dimension of the objective function and the problem size are large, the MOPSO algorithm is prone to premature convergence, making it difficult to find the true optimal solution. Inspired by the genetic algorithm's ability to maintain population diversity, the population individuals are selected for crossover and mutation operations by evaluating the state of population evolution in different iterations of the multi-objective particle swarm optimization algorithm, thereby maintaining the diversity of particles in the population.

[0135] S202, merge the initial population of the MOPSO algorithm and the sub-population to obtain a parent and child population.

[0136] In this embodiment, the initial population of the MOPSO algorithm obtained by step S201 is all non-dominated solutions in the non-dominated solution set obtained by the NSGA2 algorithm. The initial population is merged with the sub-population generated in step S201 to obtain a parent and child population.

[0137] S203, calculate the coordinate values corresponding to the particles in the parent and child population, and calculate the potential energy values of the particles in the parent and child population according to the coordinate values.

[0138] In this embodiment, the method of calculating the coordinate values corresponding to the particles in the parent and child population is the same as the calculation formula of calculating the coordinate values corresponding to the particles in the external non-dominated solution set in step S102. The method of calculating the potential energy values of the particles in the parent and child population according to the coordinate values is the same as the calculation formula of calculating the potential energy values of the particles in step S102. Therefore, it will not be described here.

[0139] S204, arrange the particles in the parent and child population in ascending order of potential energy value, and select and return the first N particles, where N is a positive integer.

[0140] In this embodiment, the particles in the parent and child population are sorted according to the potential energy values calculated in step S203, and the first N particles with the smallest potential energy values are selected.

[0141] In conclusion, the orderly charging method of the electric vehicle in the embodiment, by performing the crossover and mutation operation on the initial population of the MOPSO algorithm, obtains the parent and child populations, and calculates the potential energy values of the particles in the parent and child populations, obtains the first N particles with the minimum potential energy values, solves the problem that the MOPSO algorithm is prone to premature convergence when the dimension of the objective function and the problem size are large, and thus the algorithm is difficult to find the real optimal solution, thereby maintaining the diversity of the particles in the population and helping to find the real optimal solution, i.e., the target charging power.

[0142] Figure 3 The structure schematic diagram of the orderly charging device of the electric vehicle provided by the embodiment of the application is shown in FIG. 1. Figure 3 As shown in the figure, the orderly charging device of the electric vehicle comprises a calculation module 301, an evaluation module 302, a population conversion module 303, an updating module 304 and an output module 305.

[0143] The calculation module 301 is configured to substitute the multiple charging powers of the electric vehicle at different time points into the objective optimization function of the lowest charging cost and the objective optimization function of the user charging satisfaction as the particles of the initial population of the NSGA2 algorithm, and calculate the function values corresponding to each particle in the initial population, wherein the NSGA2 algorithm comprises the number of particles in the initial population and the iteration number.

[0144] The evaluation module 302 is configured to calculate the dominance relationship of the particles in the initial population according to the function values, obtain an external non-dominated solution set, calculate the entropy value of the external non-dominated solution set, obtain a probability value according to the entropy value, and evaluate the evolution state of the NSGA2 algorithm according to the probability value.

[0145] The population conversion module 303 is configured to select the particle with the minimum potential energy value as the global optimal solution if the evolution state of the NSGA2 algorithm is in the convergence state, select the particle with the minimum density value as the global optimal solution if the evolution state of the NSGA2 algorithm is in the diversity state, perform the population conversion operation, arrange the particles obtained by the population conversion in ascending order of the potential energy values, and select and return the first N particles, wherein N is a positive integer.

[0146] The updating module 304 is configured to update the speed and position of the particle with the minimum potential energy value, the particle with the minimum density value and the first N particles, and update the global optimal value found by the particle with the minimum potential energy value, the particle with the minimum density value and the first N particles in the iteration according to the speed and position.

[0147] The output module 305 is configured to determine whether the NSGA2 algorithm reaches a preset iteration number, and if not, return to the step of calculating the dominance relation of the particles in the initial population according to the function value; if yes, output the global optimal value, and select a compromise solution as the target charging power by using the TOPSIS method in the global optimal value, and perform orderly charging of the electric vehicle according to the target charging power.

[0148] The payment module is configured to calculate the charging fee according to the current electricity price information after the charging is completed, and push the charging completion reminding information to the user, so that the user realizes no-sense payment through the quick payment function.

[0149] In some embodiments, the apparatus further includes an establishment module 306 configured to establish a charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times, and establish a target optimization function of the lowest charging fee and a target optimization function of the user charging satisfaction according to the charging and discharging model.

[0150] In some embodiments, the establishment module 306 is specifically configured to establish the formula of the charging and discharging model of the electric vehicle according to the charging power or discharging power of the electric vehicle at different times as follows:

[0151]

[0152] In the formula, E a (t+1) represents the battery storage capacity at t+1 time; E a (t) represents the battery storage capacity at t time; represents the charging power or discharging power of the electric vehicle at t time, and the charging power of the electric vehicle is set to be positive, that is, the discharging power is negative, that is, η ch and η dis respectively represent the battery charging efficiency and discharging efficiency; and Δt represents the experimental simulation step.

[0153] The calculation formula of the target optimization function of the lowest charging fee established according to the charging and discharging model is as follows:

[0154]

[0155] In the formula, F1 represents the economic index after optimization, which is used to measure the change of the optimized electricity cost; represents the charging power or discharging power of the electric vehicle at t time; represents the constant charging power; γ(t) represents the electricity price information at t time; Δt represents the experimental simulation step; and s represents the charging start time, and e represents the charging end time.

[0156] The calculation formula of the target optimization function of the user charging satisfaction degree according to the charging and discharging model is as follows:

[0157] minF2=(E a (t)-E set ) 2 ;

[0158] In the formula, F2 represents the optimized satisfaction index, used to measure the optimized power consumption satisfaction degree; E a (t) represents the battery storage capacity at t moment, that is, the actual storage capacity when charging is completed, in the unit of KWh, and E set represents the ideal storage capacity set by the user, in the unit of KWh.

[0159] In some embodiments, the evaluation module 302 is specifically configured to calculate the dominance relation of the particles in the initial population according to the function value, store the calculated non-dominated solution into an external non-dominated solution set, calculate the entropy value of the external non-dominated solution set, and obtain a probability value according to the entropy value; and determine whether a random value is greater than or equal to the probability value, if yes, the NSGA2 algorithm is in a convergence state, and if no, the NSGA2 algorithm is in a diversity state.

[0160] In some embodiments, the evaluation module 302 is specifically configured to calculate the entropy value of the external non-dominated solution set, and obtain a probability value according to the entropy value, including: the calculation formula of the entropy value of the external non-dominated solution set is as follows:

[0161]

[0162] In the formula, H g represents the entropy value of the gth iteration; K represents the total number of particles in the external non-dominated solution set; M represents the total number of particles in the initial population; is the number of non-dominated solutions of the kth row and the mth column in the gth iteration; and the calculation formula of the probability value according to the entropy value is as follows:

[0163]

[0164] ΔH g =H g -H g-1 ;

[0165] In the formula, Pr g represents a probability value; ΔH g represents the change of the entropy value; H g represents the population entropy value at the gth iteration; H g-1 represents the population entropy value at the g-1th iteration; δ represents the threshold value of the change of the entropy value; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population.

[0166] In some embodiments, the apparatus further comprises a second calculation module 307 configured to calculate coordinate values corresponding to particles in the external non-dominated solution set, and calculate potential energy values and density values of the particles according to the coordinate values.

[0167] In some embodiments, the second calculation module 307 is specifically configured to calculate the coordinate values corresponding to the particles in the external non-dominated solution set according to the following formula:

[0168]

[0169] In the formula, x represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet; represents the rounding operation; represents the function value of the kth non-dominated solution in the external non-dominated solution set on the mth objective optimization function; and K represents the total number of particles in the external non-dominated solution set.

[0170] The calculation formula for calculating the potential energy values of the particles according to the coordinate values is as follows:

[0171]

[0172] In the formula, φ(x k ) represents the potential energy value; m represents the mth objective optimization function, and M represents the total number of particles in the initial population. represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet.

[0173] The calculation formula for calculating the density values of the particles according to the coordinate values is as follows:

[0174]

[0175] In the formula, ρ(x k ) represents the density value; d PC (x k ,x l ) represents the sum of distances between the kth particle and other particles in the external non-dominated solution set; l and k represent any two particles in the external non-dominated solution set; m represents the mth objective optimization function; and M represents the total number of particles in the initial population. represents the coordinate value of the kth non-dominated solution in the external non-dominated solution set on the mth alphabet.

[0176] In some embodiments, the population conversion module 303 is specifically configured to: obtain all particles in the external non-dominated solution set, perform binary crossover and polynomial mutation of the MOPSO algorithm on all particles to generate a sub-population; merge the initial population of the MOPSO algorithm and the sub-population to obtain a parent-child population; calculate coordinate values corresponding to the particles in the parent-child population, calculate potential energy values of the particles in the parent-child population according to the coordinate values; arrange the particles in the parent-child population in ascending order of the potential energy values, and select and return the first N particles, where N is a positive integer.

[0177] In some embodiments, the updating module 304 is specifically configured to update the velocity and position of the particle with the minimum potential energy value and the first N particles, and update the calculation formula of the global optimal value found by the population particles in the current iteration according to the velocity and position.

[0178]

[0179] In the formula, ω represents an inertia weight parameter, r1 and r2 are random numbers with values between 0 and 1, c1 and c2 are acceleration constants, i and g are particle and iteration number indexes respectively, and respectively represent the position and flight speed searched by the i-th particle in the g-th iteration, and respectively represent the individual optimal position currently found by the particle i and the global optimal value found by the population in the g-th iteration.

[0180] The ordered charging device of the electric vehicle provided by the embodiments of the present application can be used to execute the technical scheme of the ordered charging method of the electric vehicle in the above embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0181] It should be noted that the division of each module of the above apparatus is only a logical function division, and all or part of them can be integrated into a physical entity or physically separated when actually implemented. These modules can all be implemented in the form of software invoked by a processing element; all can be implemented in the form of hardware; or some modules are implemented in the form of software invoked by a processing element and some modules are implemented in the form of hardware. For example, the allocation module 1103 can be a separately set processing element, or can be integrated into a chip of the above apparatus, in addition, it can also be stored in the form of program code in the memory of the above apparatus, and the function of the above allocation module 1103 is invoked and executed by a processing element of the above apparatus. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or independently implemented. The processing element here can be an integrated circuit with signal processing capability. In the implementation process, each step of the above method or each module can be completed by integrated logic circuit of hardware in the processing element or instruction in the form of software.

[0182] Figure 4 The structure schematic diagram of the electronic device provided by the embodiment of the application is shown in the figure. Figure 4 As shown in the figure, the electronic device can include a transceiver 401, a processor 402, and a memory 403.

[0183] The processor 402 executes the computer execution instructions stored in the memory, so that the processor 402 executes the scheme in the above embodiment. The processor 402 can be a general-purpose processor, including a central processing unit CPU, a network processor NP, etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0184] The memory 403 is connected with the processor 402 through a system bus and completes mutual communication, and the memory 403 is used for storing computer program instructions.

[0185] The transceiver 401 can be used to obtain a to-be-run task and configuration information of the to-be-run task.

[0186] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries and read-only libraries). The memory can include random access memory (RAM) and can also include non-volatile memory.

[0187] The electronic device provided by the embodiment of the application can be the terminal device of the above embodiment.

[0188] The embodiment of the application further provides a chip for running instructions, which is used to execute the technical solution of the ordered charging method of the electric vehicle in the above embodiment.

[0189] The embodiment of the application further provides a computer readable storage medium, which stores computer instructions, and when the computer instructions are run on a computer, the computer executes the technical solution of the ordered charging method of the electric vehicle in the above embodiment.

[0190] The embodiment of the application further provides a computer program product, which includes a computer program stored in a computer readable storage medium, at least one processor can read the computer program from the computer readable storage medium, and when the at least one processor executes the computer program, the technical solution of the ordered charging method of the electric vehicle in the above embodiment can be realized.

[0191] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0192] The modules illustrated as separate components may or may not be physically separate, and the components illustrated as modules may or may not be physical units, i.e., may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected to implement the embodiments of the present application according to actual needs.

[0193] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more modules can be integrated in one unit. The above-mentioned modules can be realized in the form of hardware, or in the form of hardware plus software functional modules.

[0194] The integrated modules realized in the form of software functional modules can be stored in a computer readable storage medium. The software functional modules stored in a storage medium include a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method of each embodiment of the present application.

[0195] It should be understood that the above-mentioned processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0196] The memory can include a high-speed RAM memory, and can also include a non-volatile storage NVM, for example at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0197] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0198] The storage medium described above can be realized by any type of volatile or nonvolatile storage devices or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or an optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0199] An exemplary storage medium is coupled to the processor so that the processor can read information from, and write information to, the storage medium. Of course, the storage medium can be part of the processor. The processor and the storage medium can be located in an application specific integrated circuits (ASIC). Of course, the processor and the storage medium can exist as discrete components in an electronic control unit or a host device.

[0200] Those of ordinary skill in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by relevant hardware instructed by programs. The foregoing programs can be stored in a computer readable storage medium. When the programs are executed, the steps of the above-mentioned method embodiments are executed; and the foregoing storage medium includes various storage media that can store program codes, such as ROM, RAM, magnetic disks or optical disks.

[0201] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An orderly charging method for electric vehicles, characterized in that, include: The charging power of electric vehicles at different times is used as particles in the initial population of the NSGA2 algorithm. These particles are substituted into the objective optimization function of minimizing charging costs and the objective optimization function of user charging satisfaction. The function value corresponding to each particle in the initial population is calculated. The NSGA2 algorithm includes a preset number of particles and a preset number of iterations in the initial population. The dominance relationships of particles in the initial population are calculated based on the function value to obtain the external non-dominated solution set. The entropy value of the external non-dominated solution set is calculated, and the probability value is obtained based on the entropy value. The evolutionary state of the NSGA2 algorithm is evaluated based on the probability value. If the evolutionary state of the NSGA2 algorithm is in the convergence state, the particle with the smallest potential energy value is selected as the global optimal solution; if the evolutionary state of the NSGA2 algorithm is in the diversity state, the particle with the smallest density value is selected as the global optimal solution, and a population transformation operation is performed. The particles obtained by the population transformation are arranged in ascending order of potential energy value, and the first N particles are selected and returned, where N is a positive integer. Update the velocity and position of the particle with the lowest potential energy value, the particle with the lowest density value, and the top N particles. Based on the velocity and position, update the global optimal value found in this iteration for the particle with the lowest potential energy value, the particle with the lowest density value, and the top N particles. Determine whether the NSGA2 algorithm has reached the preset number of iterations. If not, return to the step of calculating the dominance relationship of particles in the initial population based on the function value. If yes, output the global optimum value, and use the TOPSIS method to select a compromise solution from the global optimum value as the target charging power. Then, perform orderly charging of the electric vehicle based on the target charging power. Once charging is complete, the charging cost is calculated based on the current electricity price, and a charging completion reminder is sent to the user, enabling them to make a seamless payment through the quick payment function.

2. The method according to claim 1, characterized in that, Before substituting the electric vehicle's charging power as the initial population particles of the NSGA2 algorithm into the objective optimization function for minimizing charging costs and the objective optimization function for user charging satisfaction, the following steps are also included: A charging and discharging model for electric vehicles is established based on the charging or discharging power of electric vehicles at different times. Based on the charging and discharging model, an objective optimization function for minimizing charging costs and an objective optimization function for user charging satisfaction are established.

3. The method according to claim 2, characterized in that, The process involves establishing a charging / discharging model for the electric vehicle based on its charging or discharging power at different times, and establishing objective optimization functions for minimizing charging costs and user charging satisfaction based on the charging / discharging model. This includes: The formula for establishing a charging and discharging model for an electric vehicle based on its charging or discharging power at different times is as follows: In the formula, E a (t+1) represents the battery's stored capacity at time t+1; E a (t) represents the battery charge at time t; This represents the charging or discharging power of the electric vehicle at time t. The charging power of the electric vehicle is assumed to be positive, i.e. The discharge power is negative, that is... η ch and η dis These represent the battery charging efficiency and discharging efficiency, respectively; Δt represents the experimental simulation step size. The formula for calculating the objective function that minimizes charging costs, based on the charge-discharge model, is as follows: In the formula, F1 represents the optimized economic index, which is used to measure the change in electricity costs after optimization; This represents the charging or discharging power of the electric vehicle at time t. γ(t) represents constant charging power; γ(t) represents the electricity price information at time t; Δt represents the experimental simulation step size; s represents the charging start time; and e represents the charging end time. The formula for calculating the objective optimization function of user charging satisfaction based on the charging and discharging model is as follows: minF2=(E a (t)-E set ) 2 ; In the formula, F2 represents the optimized satisfaction index, used to measure the optimized electricity user satisfaction; E a (t) represents the battery's stored capacity at time t, i.e., the actual stored capacity when charging is complete, in kWh, E. set This indicates the user-defined ideal energy storage capacity, expressed in kWh.

4. The method according to claim 1, characterized in that, The process of calculating the dominance relationships of particles in the initial population based on the function value to obtain the external non-dominated solution set, calculating the entropy value of the external non-dominated solution set, obtaining a probability value based on the entropy value, and evaluating the evolutionary state of the NSGA2 algorithm based on the probability value includes: The dominance relationships of particles in the initial population are calculated based on the function value, and the calculated non-dominated solutions are stored in the external non-dominated solution set. Calculate the entropy value of the external non-dominated solution set, and obtain the probability value based on the entropy value; Determine whether a random value is greater than or equal to the probability value. If yes, the NSGA2 algorithm is in a convergent state; otherwise, the NSGA2 algorithm is in a diversity state.

5. The method according to claim 4, characterized in that, The calculation of the entropy value of the external non-dominated solution set, and the determination of the probability value based on the entropy value, includes: The formula for calculating the entropy value of the external non-dominated solution set is as follows: In the formula, H g Let represent the entropy value of the g-th iteration; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population. This represents the number of non-dominated solutions in the k-th row and m-th column during the g-th iteration. The formula for calculating the probability value based on the entropy value is as follows: ΔH g =H g -H g-1 ; In the formula, Pr g ΔH represents a probability value. g H represents the change in entropy; g H represents the population entropy value at the g-th iteration; g-1 δ represents the population entropy value at the (g-1)th iteration; K represents the total number of particles in the external non-dominated solution set; and M represents the total number of particles in the initial population.

6. The method according to claim 1, characterized in that, Before calculating the entropy value of the external non-dominated solution set, obtaining a probability value based on the entropy value, and evaluating the evolutionary state of the NSGA2 algorithm based on the probability value, the method further includes: Calculate the coordinate values ​​of the particles in the external non-dominated solution set, and calculate the potential energy and density values ​​of the particles based on the coordinate values.

7. The method according to claim 6, characterized in that, The step of calculating the coordinate values ​​corresponding to the particles in the external non-dominated solution set, and calculating the potential energy and density values ​​of the particles based on the coordinate values, includes: The formula for calculating the coordinate values ​​of the particles in the external non-dominated solution set is as follows: In the formula, This represents the coordinate value of the k-th non-dominated solution in the m-th alphabet of the external non-dominated solution set; Indicates the rounding operation; The function value of the k-th non-dominated solution in the external non-dominated solution set is given by the m-th objective function; K represents the total number of particles in the external non-dominated solution set. The formula for calculating the potential energy of the particle based on the coordinate values ​​is as follows: In the formula, φ(x) k ) represents the potential energy value; m represents the m-th objective function; and M represents the total number of particles in the initial population. This represents the coordinate value of the k-th non-dominated solution in the m-th alphabet of the external non-dominated solution set; The formula for calculating the density value of the particle based on the coordinate values ​​is as follows: In the formula, ρ(x) k ) represents the density value; d PC (x k ,x l ) represents the sum of distances between individual k and other particles in the external non-dominated solution set; l and k represent two arbitrary particles in the external non-dominated solution set; m represents the m-th objective function; M represents the total number of particles in the initial population; This represents the coordinate value of the k-th non-dominated solution in the m-th alphabet of the external non-dominated solution set.

8. The method according to claim 1, characterized in that, The process of performing a population conversion operation, arranging the particles obtained from the population conversion in ascending order of potential energy value, and selecting and returning the top N particles includes: Obtain all non-dominated solutions from the external non-dominated solution set, and perform binary crossover and polynomial mutation of the MOPSO algorithm on all non-dominated solutions to generate a subpopulation; The initial population and child population of the MOPSO algorithm are merged to obtain the parent-child population; Calculate the coordinate values ​​corresponding to the particles in the parent-child population, and calculate the potential energy value of the particles in the parent-child population based on the coordinate values; Sort the particles in the parent-child population in ascending order of potential energy value, select and return the top N particles, where N is a positive integer.

9. The method according to any one of claims 1 to 8, characterized in that, The formula for updating the velocity and position of the particle with the smallest potential energy and the top N particles, and updating the global optimum value of the population particles in this iteration based on the velocity and position, is as follows: In the formula, ω represents the inertia weight parameter, r1 and r2 are random numbers between [0,1], c1 and c2 are acceleration constants, and i and g are the particle and iteration number indices, respectively. and Let their positions and velocity be the positions and velocity of the i-th particle in the g-th iteration, respectively. and Let represent the individual optimal position found by particle i and the global optimal value found by the population in the g-th iteration, respectively.

10. An orderly charging device for electric vehicles, characterized in that, include: The calculation module is used to substitute multiple charging powers of electric vehicles at different times as particles of the initial population of the NSGA2 algorithm into the objective optimization function of the lowest charging cost and the objective optimization function of user charging satisfaction, and calculate the function value corresponding to each particle in the initial population. The NSGA2 algorithm includes a preset number of particles and number of iterations in the initial population. The evaluation module is used to calculate the dominance relationship of particles in the initial population based on the function value, obtain the external non-dominated solution set, calculate the entropy value of the external non-dominated solution set, obtain the probability value based on the entropy value, and evaluate the evolutionary state of the NSGA2 algorithm based on the probability value. The population conversion module is used to select the particle with the smallest potential energy value as the global optimal solution if the evolutionary state of the NSGA2 algorithm is in the convergence state; and to select the particle with the smallest density value as the global optimal solution if the evolutionary state of the NSGA2 algorithm is in the diversity state. At the same time, a population conversion operation is performed, the particles obtained by the population conversion are arranged in ascending order of potential energy value, and the top N particles are selected and returned, where N is a positive integer. The update module is used to update the velocity and position of the particle with the smallest potential energy value, the particle with the smallest density value, and the top N particles, and update the global optimal value found in this iteration of the particle with the smallest potential energy value, the particle with the smallest density value, and the top N particles based on the velocity and position. The output module is used to determine whether the NSGA2 algorithm has reached the preset number of iterations. If not, it returns to the step of calculating the dominance relationship of particles in the initial population based on the function value. If yes, it outputs the global optimum value and uses the TOPSIS method to select a compromise solution from the global optimum value as the target charging power, and performs orderly charging of electric vehicles based on the target charging power. The payment module calculates the charging cost based on the current electricity price after charging is complete and sends a charging completion reminder to the user, enabling the user to make a seamless payment through the quick payment function.

11. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the orderly charging method for an electric vehicle as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the orderly charging method for an electric vehicle as described in any one of claims 1-9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the orderly charging method for an electric vehicle according to any one of claims 1-9.

Images