Electric vehicle charging optimization method, system and device and readable storage medium

Abstract

The invention discloses an electric vehicle charging optimization method, system and device and a readable storage medium. The method comprises the steps that the starting charging time and the ending charging time of the day are determined; when the initial charging time is reached, monitoring whether an electric vehicle is accessed to be charged, and if so, continuing the subsequent steps; judging whether the accessed electric vehicle urgently uses electricity, if so, adopting high-power quick charging, and otherwise, adopting low-power slow charging; solving the minimum value of the charging target function by adopting an adaptive genetic algorithm in an iterative optimization manner, and obtaining an optimized charging strategy; and controlling the connected electric vehicle to be charged orderly, continuously monitoring the charging condition of the electric vehicle and whether a new vehicle is connected or not, and when the new vehicle is connected, carrying out demand judgment again and updating the optimal charging strategy. According to the method, the charging economy of the electric vehicle user and the operation safety of the power distribution network are considered, the charging target function is solved by using the adaptive genetic algorithm to obtain the optimized charging strategy, and the operation stability of the power grid is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of power supply optimization, and in particular to an electric vehicle charging optimization method, system, device and readable storage medium. Background Art

[0002] The overlap rate between unscheduled electric vehicle charging load and residential load is as high as 85%, which will lead to a "peak on peak" phenomenon in the distribution network load, thereby further widening the peak-to-valley difference in the distribution network load, increasing the peak-shaving pressure on the power grid and affecting the safe and stable operation of the power grid. Summary of the invention

[0003] In response to the problems that the charging load of electric vehicles causes the peak-to-valley difference of the distribution network load to further widen, increasing the peak-shaving pressure of the power grid, and the like, the present application provides an electric vehicle charging optimization method, system, device and readable storage medium. The present application takes into account the economy of electric vehicle users when charging and the safe and stable operation of the distribution network, and uses an adaptive genetic algorithm to solve the charging objective function to obtain an optimized charging strategy, thereby ensuring the stability of the power grid operation and reducing the charging cost of users.

[0004] This application is implemented through the following technical solutions:

[0005] An electric vehicle charging optimization method, the optimization method comprising:

[0006] Obtain the electricity price and real-time load distribution of the day from the power grid, determine the load curve of the community box transformer, and determine the starting and ending charging times of the day according to the low-consumption section of the load curve;

[0007] When the starting charging time is reached, monitoring whether an electric vehicle is connected for charging, and if yes, continuing with the subsequent steps;

[0008] Determine whether the connected electric vehicle is in urgent need of electricity based on the user's charging needs. If so, use high-power fast charging; otherwise, use low-power slow charging;

[0009] An adaptive genetic algorithm is used to calculate the charging objective function and perform iterative optimization to solve the minimum value of the charging objective function to obtain an optimized charging strategy;

[0010] Control the orderly charging of connected electric vehicles according to the optimized charging strategy, and continuously monitor the charging status of electric vehicles and whether new vehicles are connected. When new vehicles are connected, re-determine the demand and update the optimized charging strategy;

[0011] Charging ends when the charging demands of all connected electric vehicles are met or the charging termination time is reached.

[0012] In some embodiments, the charging objective function is:

[0013] F=α1F1+α2F2+α3F3

[0014] Wherein, F1 represents the load peak-valley difference, F2 represents the load variance, F3 represents the user charging fee, α1, α2, α3 represent the weighted coefficients of the load peak-valley difference, load variance, and user charging fee, respectively, and α1+α2+α3=1.

[0015] In some embodiments, the constraints of the charging objective function include:

[0016] Community box-type transformer capacity constraint: At any time, the total load of the distribution network is less than the maximum load limit of the community box-type transformer;

[0017] User charging demand constraints: The battery capacity of each electric vehicle at the end of charging must reach the user's minimum expectation;

[0018] High-power charging ratio constraint: A preset ratio of electric vehicles adopts high-power fast charging mode.

[0019] In some implementations, the weight of the load peak-valley difference is 0.2, the weight of the load variance is 0.4, and the weight of the user charging fee is 0.4.

[0020] In some embodiments, the adaptive genetic algorithm is used to calculate the current charging objective function and perform iterative optimization to solve the minimum value of the charging objective function. The specific process is as follows:

[0021] The original charging sequence is randomly generated according to user demand and the number of electric vehicles as the initial population;

[0022] Calculating the objective function value of the initialized population, and calculating the adaptive genetic crossover and mutation probability based on the objective function value;

[0023] According to the adaptive genetic crossover and mutation probability, performing crossover genetics and mutation on the initialized population;

[0024] The elite of the population is retained, and then the adaptive genetic crossover and mutation probability are calculated for the remaining population, and the previous step is returned to execute until the maximum number of iterations is reached;

[0025] Output the optimal charging strategy.

[0026] In some embodiments, the adaptive genetic crossover probability calculation formula is:

[0027]

[0028] In the formula, k max represents the maximum value of the fitness function, kavg represents the average value of the fitness function, k′ represents the value with the largest fitness of the two parents in the genetic crossover operation, and p jmax represents the maximum genetic crossover probability, p jmin represents the minimum genetic crossover probability, p j is the genetic crossover probability of the current iteration;

[0029] The formula for calculating the probability of adaptive genetic mutation is:

[0030]

[0031] In the formula, k" represents the value with the largest fitness of the two parents in the genetic mutation operation, p bmax represents the maximum genetic variation probability, p bmin represents the minimum genetic variation probability, p b is the genetic mutation probability of the current iteration.

[0032] In a second aspect, the present application proposes an electric vehicle charging optimization system, the optimization system comprising:

[0033] A load analysis module, which obtains the electricity price and real-time load distribution of the day from the power grid, determines the load curve of the community transformer, and determines the starting and ending charging times of the day according to the low-power consumption section in the load curve;

[0034] A monitoring module is used to monitor whether there are electric vehicles connected to charge within the charging start and end time range, and if so, drive the demand analysis module; at the same time, it also continuously monitors the charging status and whether there are new cars connected, and if there are new cars connected, drives the demand analysis module and the optimization module to update the charging strategy, and ends the charging if the charging requirements of the connected electric vehicles are met or the termination time is reached;

[0035] A demand analysis module, which determines whether the connected electric vehicle is in urgent need of electricity according to the user's charging demand, and if so, adopts high-power fast charging, otherwise adopts low-power slow charging;

[0036] An optimization module, wherein the optimization module uses an adaptive genetic algorithm to calculate a charging objective function and performs iterative optimization to solve a minimum value of the charging objective function to obtain an optimized charging strategy;

[0037] And, a control module, wherein the control module controls the orderly charging of the electric vehicle according to the optimized charging strategy.

[0038] In some embodiments, the optimization module further includes:

[0039] A model building unit, wherein the model building unit builds the charging objective function based on the user charging fee, the peak-to-valley difference of the power grid load and the load variance and sets the constraint conditions of the charging objective function;

[0040] And, a model solving unit, wherein the model solving unit uses an adaptive genetic algorithm to calculate the charging objective function and performs iterative optimization and solves and outputs an optimal charging strategy.

[0041] In a third aspect, the present application proposes an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0042] In a fourth aspect, the present application proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0043] The present application proposes an electric vehicle charging optimization method, system, device and readable storage medium, which take into account both the stable operation of the distribution network and the economy on the user side, improve the peak-shaving capacity of the power grid, and correspondingly reduce the charging cost on the electricity user side; the present application adopts a genetic algorithm with adaptive genetic crossover mutation probability, which can dynamically adjust the crossover mutation probability according to the value of the objective function, improve the efficiency of the algorithm, and provide technical support for the safe operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the embodiments of the present application, constitute a part of the present application, and do not constitute a limitation on the embodiments of the present application. In the drawings:

[0045] Figure 1 This is a flow chart of the optimization method of an embodiment of the present application;

[0046] Figure 2 This is a principle block diagram of the optimization system of an embodiment of the present application;

[0047] Figure 3 This is the original load distribution diagram of a certain community box transformer;

[0048] Figure 4 This is a comparison chart of load distribution between optimized charging and non-optimized charging;

[0049] Figure 5 This is a comparison chart of the effects of genetic algorithm and adaptive genetic algorithm. DETAILED DESCRIPTION

[0050] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with examples and drawings. The illustrative implementation scheme of the present application and its description are only used to explain the present application and are not intended to limit the present application.

[0051] Example:

[0052] The charging load of electric vehicles increases the peak load regulation pressure of the power grid, affecting the operational stability of the power grid. This embodiment provides an electric vehicle charging optimization method, which takes into account the economic efficiency of electric vehicle users when charging and the safe and stable operation of the distribution network, constructs the optimization target based on the user-side cost (cost), the grid-side load variance, and the peak-to-valley difference, and uses an adaptive genetic algorithm to solve the optimized charging strategy. This strategy will continuously update the charging plan of electric vehicles over time, and has a faster convergence speed and better optimization effect, providing technical support for the safe and stable operation of the power grid.

[0053] like Figure 1 As shown, the method proposed in this embodiment includes the following steps:

[0054] Step 100, obtain the electricity price and real-time load distribution of the day from the grid side, determine the load curve of the community box transformer, and determine the charging start and end time of the day according to the low power consumption section in the load curve.

[0055] This step obtains the electricity price of the day and the real-time load distribution from the power grid to determine the load curve of the community transformer. The charging start and end times of the day are determined by the low-consumption segment in the load curve, that is, the starting charging time and the ending charging time. Users can only charge within the charging start and end time periods, so that users can charge during the low-consumption period. This can avoid increasing the peak-shaving capacity of the power grid, save costs, and ensure the safe and stable operation of the power grid.

[0056] Step 200, when the starting charging time is reached, monitor whether there is an electric vehicle connected for charging, and if so, continue with the subsequent steps.

[0057] Step 300, judging whether the connected electric vehicle is in urgent need of electricity according to the user's charging demand, if so, adopting high-power fast charging, otherwise adopting low-power slow charging.

[0058] Step 400, using an adaptive genetic algorithm to calculate the charging objective function and perform iterative optimization to solve the minimum value of the charging objective function, thereby obtaining an optimized charging strategy.

[0059] In step 400, a charging objective function is constructed based on the user-side charging fee (cost), the peak-to-valley difference of the grid-side load, and the load variance. The constructed charging objective function F is:

[0060] F=α1F1+α2F2+α3F3

[0061] Where F1 represents the load peak-valley difference, F2 represents the load variance, F3 represents the user charging fee, and α1, α2, and α3 represent the weighted coefficients of the load peak-valley difference, load variance, and user charging fee, respectively.

[0062] Among them, the load peak-to-valley difference F1 is expressed as:

[0063] F1=max(p(t))-min(p(t))

[0064] Where p(t) represents the load at time t.

[0065] The load variance F2 is expressed as:

[0066]

[0067] In the formula, pa v represents the average load at j moments.

[0068] The user charging fee F3 is expressed as:

[0069]

[0070] In the formula, C j represents the charging cost per kilowatt-hour at the jth moment; Δt represents each control time; t in Indicates the starting time of charging; t end Indicates the time to terminate charging; X i，j represents the charging status of the i-th electric vehicle at the j-th moment; n represents the number of connected electric vehicles; P EV Indicates the charging load power of each electric vehicle.

[0071] In the above charging objective function, α1+α2+α3=1. In order to fully ensure the stable operation of the power grid, the weight of the load peak-to-valley difference in this embodiment is preferably 0.2, that is, α1=0.2, and the weight of the load variance is preferably 0.4, that is, α2=0.4. Taking into account the charging economy on the user side, the weight of the user charging cost is preferably 0.4, that is, α3=0.4.

[0072] The constraints of the above charging objective function include:

[0073] (1) Community transformer capacity constraint: At any time, the total load of the distribution network is less than the maximum load limit of the community transformer:

[0074]

[0075] In the formula, p max Indicates the maximum load limit of the community box-type transformer; p load，j (t) represents the original load when there is no electric vehicle connected to the community for charging at the jth moment.

[0076] (2) User charging demand constraint: The power of each car at the end of charging must reach the user's minimum expectation:

[0077]

[0078] In the formula, Indicates the minimum expected battery capacity at the end of charging. Indicates the rated capacity of the electric vehicle battery; Indicates the remaining battery capacity when charging starts.

[0079] (3) High-power charging ratio constraint: Since high-power charging has a significant impact on grid load fluctuations, this embodiment also sets a high-power charging ratio constraint. For example, it is set that only 40% of electric vehicles can use high-power charging. Of course, this ratio is only an exemplary description and can be adjusted according to actual application scenarios.

[0080] This embodiment uses an adaptive genetic algorithm to calculate the charging objective function at this time and performs iterative optimization and solution. The specific process is as follows:

[0081] (1) Randomly generate the original charging sequence according to user demand and the number of trams as the initial population.

[0082] (2) Calculate the objective function value of the initialized population, and calculate the adaptive genetic crossover and mutation probability based on the objective function value. Specifically, the inverse of the objective function is set as the fitness function, as shown in the following formula, which is used to calculate the genetic crossover and mutation probability:

[0083]

[0084] After the original population is randomly generated, a higher genetic crossover and mutation probability is required to make the value of the objective function drop rapidly. In the later stage of evolution, in order to make the objective function converge as quickly as possible, a lower genetic crossover and mutation probability is required. Therefore, this embodiment adopts a strategy of adaptively adjusting the genetic crossover and mutation probability along with the objective function to achieve a balance between search and randomness. The adaptive genetic crossover probability is calculated as follows:

[0085]

[0086] In the formula, k max represents the maximum value of the fitness function, k avg represents the average value of the fitness function, k′ represents the value with the largest fitness of the two parents in the genetic crossover operation, and p jmax represents the maximum genetic crossover probability, p jmin represents the minimum genetic crossover probability, p j is the genetic crossover probability of the current iteration.

[0087] The probability of adaptive genetic mutation is calculated as follows:

[0088]

[0089] In the formula, k″ represents the value with the largest fitness of the two parents in the genetic mutation operation, and p bmax represents the maximum genetic variation probability, p bmin represents the minimum genetic variation probability, p b is the genetic mutation probability of the current iteration.

[0090] (3) The first generation population undergoes cross-inheritance and mutation.

[0091] (4) The elite of the population is retained, and then the adaptive genetic crossover and mutation probabilities are calculated for the remaining population.

[0092] (5) Repeat (3)-(4) until the maximum number of iterations is reached.

[0093] (6) Output the optimal charging strategy.

[0094] Step 500, controlling the orderly charging of electric vehicles according to the optimized charging strategy, and continuously monitoring the charging status of electric vehicles and whether new vehicles are connected, and repeating steps 300 to 400 when new vehicles are connected.

[0095] Step 600: When the charging requirements of all connected electric vehicles are met or the charging termination time is reached, the charging is terminated.

[0096] The optimization method proposed in this embodiment takes into account both the stable operation of the distribution network and the economic efficiency of the user side, improves the peak-shaving capacity of the power grid, and correspondingly reduces the charging cost on the power user side. The adaptive genetic algorithm can dynamically adjust the crossover mutation probability according to the value of the objective function to improve the efficiency of the algorithm. The obtained electric vehicle charging optimization strategy can update the charging plan of the electric vehicle over time.

[0097] Based on the same technical concept as above, this embodiment also proposes an electric vehicle charging optimization system, such as Figure 2 As shown, the optimization system proposed in this embodiment includes:

[0098] The load analysis module obtains the electricity price of the day and the real-time load distribution from the grid side, determines the load curve of the community transformer, and determines the charging start and end time of the day according to the low power consumption section in the load curve.

[0099] The monitoring module is used to monitor whether there are electric vehicles connected to charge within the charging start and end time range. If so, it drives the demand analysis module. At the same time, it also continuously monitors the charging status and whether there are new cars connected. If a new car is connected, it drives the demand analysis module and the optimization module to update the charging strategy. If the charging needs of the connected electric vehicles are met or the charging termination time is reached, the charging is terminated.

[0100] The demand analysis module determines whether the connected electric vehicle is in urgent need of electricity based on the user's charging needs. If so, high-power fast charging is adopted; otherwise, low-power slow charging is adopted.

[0101] The optimization module uses an adaptive genetic algorithm to calculate the charging objective function and performs iterative optimization to solve the minimum value of the charging objective function to obtain an optimized charging strategy.

[0102] And, a control module, which controls the orderly charging of the electric vehicle according to the optimized charging strategy.

[0103] Furthermore, the optimization module also includes:

[0104] The model building unit constructs a charging objective function based on the user charging cost, the peak-to-valley difference of the power grid load and the load variance and sets the constraints of the charging objective function. The specific charging objective function and its constraints are as described in step 400 above, and will not be described in detail here.

[0105] And, a model solving unit, which uses an adaptive genetic algorithm to calculate the charging objective function and perform iterative optimization to solve and output an optimal charging strategy.

[0106] This embodiment uses a charging pile in a parking lot of a residential area as an example to verify the above optimization method.

[0107] The time-of-use electricity price adopted by the grid is obtained from Table 1, and the original load distribution of the community box transformer is determined as follows: Figure 3 shown.

[0108] Table 1 Time-of-use electricity price strategy

[0109]

[0110] The above optimization method is used to perform iterative optimization to solve the minimum value of the weighted function (objective function), output the optimization strategy to each unit charging pile, control the orderly charging of electric vehicles, and continuously monitor the charging status of electric vehicles and whether there are new cars connected to the charging pile. When a new car is connected, the objective function is updated and optimized.

[0111] 100 electric vehicles are charged in an optimized and disorderly manner. The load distribution of optimized charging and non-charging is as follows: Figure 4 As shown in the figure, the peak-to-valley difference of the non-required charging is 2 to 3 times that of the optimized charging, and the variance is 8 to 10 times that of the optimized charging. The optimized charging can also reduce the charging cost on the user side.

[0112] The situations when 50, 100 and 150 cars enter the station for charging are simulated respectively. The results of no need to charge and optimized charging of electric vehicles in the three situations are shown in Table 2. The peak-to-valley difference and variance of the optimized charging load of 50 and 100 electric vehicles are significantly reduced, and the peak-to-valley difference and variance of 150 cars can also be effectively controlled. This shows that the optimization method proposed in the above embodiment can be applied to a variety of occasions.

[0113] Table 2 Charging effect of different number of electric vehicles

[0114]

[0115] It is simulated that 100 electric vehicle users participate in optimized charging at 0%, 40%, 80% and 100% respectively. The load characteristics of the community transformer are shown in Table 3. It can be seen that when the proportion of optimized charging users increases from 0% to 100%, the peak-to-valley difference decreases by 476kW and the variance decreases by 40412kW 2 , the user fee is reduced by 372 yuan. When 40% of users participate in optimized charging, the load peak-valley difference and variance are reduced to half of that of disordered charging; when 80% of users participate in optimized charging, the peak-valley difference is reduced to 1 / 3 of that of disordered charging, and the variance is reduced to 1 / 10. It shows that the above optimization method proposed in this embodiment has good adaptability to different participation ratios and can effectively maintain the stability of the distribution network.

[0116] Table 3 Load characteristics of different proportions of users participating in dispatching

[0117]

[0118]

[0119] In order to verify the convergence effect and convergence accuracy of the adaptive genetic algorithm in solving the objective function, it is compared with the traditional genetic algorithm. 100 vehicles are simulated in the above simulation environment to optimize the charging effect. The convergence curve is as follows: Figure 5 shown.

[0120] Depend on Figure 5It can be seen that the adaptive genetic algorithm proposed in this embodiment has a faster convergence speed and better optimization effect, and has good stability. The load distribution and user charging costs obtained by solving the adaptive genetic algorithm and the traditional genetic algorithm are shown in Table 4. It can be seen from Table 4 that the optimization strategy solved by the adaptive genetic algorithm has a smaller load peak-to-valley difference, variance, and user charging costs, which effectively avoids the problem that the traditional genetic algorithm converges slowly and is prone to falling into the local optimum.

[0121] Table 4 Data analysis of different algorithms

[0122]

[0123] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0124] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0127] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only the specific implementation method of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for optimizing charging of an electric vehicle, characterized in that: The optimization method comprises: Obtain the electricity price and real-time load distribution of the day from the power grid, determine the load curve of the community box transformer, and determine the starting and ending charging times of the day according to the low-consumption section of the load curve; When the starting charging time is reached, monitoring whether an electric vehicle is connected for charging, and if yes, continuing with the subsequent steps; Determine whether the connected electric vehicle is in urgent need of electricity based on the user's charging needs. If so, use high-power fast charging; otherwise, use low-power slow charging; An adaptive genetic algorithm is used to calculate the charging objective function and perform iterative optimization to solve the minimum value of the charging objective function to obtain an optimized charging strategy; Control the orderly charging of connected electric vehicles according to the optimized charging strategy, and continuously monitor the charging status of electric vehicles and whether new vehicles are connected. When new vehicles are connected, re-determine the demand and update the optimized charging strategy; Charging ends when the charging demands of all connected electric vehicles are met or the charging termination time is reached.

2. The electric vehicle charging optimization method according to claim 1, characterized in that: The charging objective function is: F=α1F1+α2F2+α3F3 Wherein, F1 represents the load peak-valley difference, F2 represents the load variance, F3 represents the user charging fee, α1, α2, α3 represent the weighted coefficients of the load peak-valley difference, load variance, and user charging fee, respectively, and α1+α2+α3=1.

3. The electric vehicle charging optimization method according to claim 2, characterized in that: The constraints of the charging objective function include: Community box-type transformer capacity constraint: At any time, the total load of the distribution network is less than the maximum load limit of the community box-type transformer; User charging demand constraints: The battery capacity of each electric vehicle at the end of charging must reach the user's minimum expectation; High-power charging ratio constraint: A preset ratio of electric vehicles adopts high-power fast charging mode.

4. The electric vehicle charging optimization method according to claim 2, characterized in that: The weight of the load peak-to-valley difference is 0.2, the weight of the load variance is 0.4, and the weight of the user charging fee is 0.

4.

5. An electric vehicle charging optimization method according to any one of claims 1 to 4, characterized in that: The adaptive genetic algorithm is used to calculate the current charging objective function and perform iterative optimization to solve the minimum value of the charging objective function. The specific process is as follows: The original charging sequence is randomly generated according to user demand and the number of electric vehicles as the initial population; Calculating the objective function value of the initialized population, and calculating the adaptive genetic crossover and mutation probability based on the objective function value; According to the adaptive genetic crossover and mutation probability, performing crossover genetics and mutation on the initialized population; The elite of the population is retained, and then the adaptive genetic crossover and mutation probability are calculated for the remaining population, and the previous step is returned to execute until the maximum number of iterations is reached; Output the optimal charging strategy.

6. The electric vehicle charging optimization method according to claim 5, characterized in that: The adaptive genetic crossover probability calculation formula is: In the formula, k max represents the maximum value of the fitness function, k avg represents the average value of fitness function, k ′ Indicates the value of the larger fitness of the two parents in the genetic crossover operation, p jmax represents the maximum genetic crossover probability, p jmin represents the minimum genetic crossover probability, p j is the genetic crossover probability of the current iteration; The formula for calculating the probability of adaptive genetic mutation is: In the formula, k″ represents the value with the largest fitness of the two parents in the genetic mutation operation, and p bmax represents the maximum genetic variation probability, p bmin represents the minimum genetic variation probability, p b is the genetic mutation probability of the current iteration.

7. An electric vehicle charging optimization system, characterized in that: The optimization system comprises: A load analysis module, which obtains the electricity price and real-time load distribution of the day from the power grid, determines the load curve of the community transformer, and determines the starting and ending charging times of the day according to the low-power consumption section in the load curve; A monitoring module is used to monitor whether there are electric vehicles connected to charge within the charging start and end time range, and if so, drive the demand analysis module; at the same time, it also continuously monitors the charging status and whether there are new cars connected, and if there are new cars connected, drives the demand analysis module and the optimization module to update the charging strategy, and ends the charging if the charging requirements of the connected electric vehicles are met or the termination time is reached; A demand analysis module, which determines whether the connected electric vehicle is in urgent need of electricity according to the user's charging demand, and if so, adopts high-power fast charging, otherwise adopts low-power slow charging; An optimization module, wherein the optimization module uses an adaptive genetic algorithm to calculate a charging objective function and performs iterative optimization to solve a minimum value of the charging objective function to obtain an optimized charging strategy; And, a control module, wherein the control module controls the orderly charging of the electric vehicle according to the optimized charging strategy.

8. The electric vehicle charging optimization system according to claim 7, characterized in that: The optimization module also includes: A model building unit, wherein the model building unit builds the charging objective function based on the user charging fee, the peak-to-valley difference of the power grid load and the load variance and sets the constraint conditions of the charging objective function; And, a model solving unit, wherein the model solving unit uses an adaptive genetic algorithm to calculate the charging objective function and performs iterative optimization and solves and outputs an optimal charging strategy.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images