Electric vehicle charging distribution adjusting method

Abstract

The invention discloses an electric vehicle charging distribution adjustment method, and relates to the technical field of electric vehicle charging, and the method comprises the steps: collecting the electric quantity information of a target electric vehicle driving into a target parking lot; predicting the charging probability of the target electric vehicle according to the electric quantity information; when the charging probability of the target electric vehicle is greater than a set probability value, determining the charging priority of the target electric vehicle according to the state information of the target electric vehicle; the state information comprises the distance between the target electric vehicle and the nearest charging pile, the parking time and the required electric quantity; matching a target charging pile which is in an idle state and corresponds to the charging priority for the target electric vehicle; each charging pile corresponds to one charging pile priority, and each charging pile priority provides a corresponding charging power range; and when the target electric vehicle is charged by adopting the target charging pile, performing electric energy distribution optimization on the target charging pile by adopting the mixed integer linear programming model. The energy utilization rate of electric vehicle charging in the parking lot can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicle charging, and in particular to a method for adjusting charging distribution of electric vehicles. Background Art

[0002] With the development of society, the number of cars in China has exploded, and the contradiction between supply and demand of parking and charging has become prominent. At present, the charging power of each charging pile in the parking lot is fixed and does not have the function of charging resource scheduling. Therefore, the utilization rate of energy in the parking lot needs to be improved. Summary of the invention

[0003] The purpose of this application is to provide an electric vehicle charging distribution adjustment method, which can improve the energy utilization rate of electric vehicle charging in a parking lot.

[0004] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a method for adjusting charging distribution of an electric vehicle, comprising: Collecting power information of a target electric vehicle entering a target parking lot; a plurality of charging piles are arranged in the target parking lot; Predicting a charging probability of the target electric vehicle according to the power information; When the charging probability of the target electric vehicle is greater than a set probability value, the charging priority of the target electric vehicle is determined according to the state information of the target electric vehicle; the state information includes the distance between the target electric vehicle and the nearest charging pile, the parking time and the required power; the required power is the difference between the remaining power of the target electric vehicle and the power required for the adjacent trip; Matching a target charging pile for the target electric vehicle; the target charging pile is a charging pile that is in an idle state and corresponds to the charging priority; each of the charging piles corresponds to a charging pile priority, and each charging pile priority provides a corresponding charging power range; When the target electric vehicle is charged by the target charging pile, a mixed integer linear programming model is used to optimize the power distribution of the target charging pile.

[0005] Optionally, the power information includes the remaining power and the power required for the adjacent trip.

[0006] Optionally, predicting the charging probability of the target electric vehicle according to the power information specifically includes: A Bayesian probability model is used to predict the charging probability of the target electric vehicle according to the power information.

[0007] Optionally, the Bayesian probability model is expressed as: ; in, Indicates the remaining power of the target electric vehicle; Indicates the power required for the adjacent trip of the target electric vehicle; represents the charging probability of the target electric vehicle, represents the probability of the power information under the charging probability condition, represents the probability of the power information, represents the charging probability of the target electric vehicle under the condition of the power information, represents the probability of the kth remaining power interval, For the The sum of the probabilities of the power intervals required for adjacent trips is 100%, and the sum of the probabilities of the power intervals required for n adjacent trips is 100%. Indicates that the target electric vehicle is in the k The remaining power interval and The probability of the required power interval of adjacent trips.

[0008] Optionally, when the charging probability of the target electric vehicle is greater than a set probability value, determining the charging priority of the target electric vehicle according to the state information of the target electric vehicle specifically includes: When the charging probability of the target electric vehicle is greater than a set probability value, a fuzzy logic algorithm is used to determine the charging priority of the target electric vehicle according to the state information of the target electric vehicle.

[0009] Optionally, according to the state information of the target electric vehicle, a fuzzy logic algorithm is used to determine the charging priority of the target electric vehicle, specifically including: Normalizing the distance, the parking time and the required power in the status information respectively to obtain a fuzzy distance factor, a fuzzy time factor and a fuzzy required power factor; Mapping the fuzzy distance factor into a first language variable according to a first setting rule; Mapping the fuzzy time factor into a second language variable according to a second setting rule; Mapping the fuzzy power demand factor into a third language variable according to a third setting rule; The charging priority of the target electric vehicle is determined by adopting an if / then rule according to the first language variable, the second language variable and the third language variable.

[0010] Optionally, the electric vehicle charging allocation adjustment method further includes: allocating charging pile priorities to each charging pile in the target parking lot every unit time, specifically including: A simulated annealing algorithm is used to optimize the grading scheme of charging piles; the grading scheme includes the charging pile priority of each charging pile in the target parking lot; during the optimization process using the simulated annealing algorithm, the first objective function in each iteration is determined according to the difference between the actual load and the target load of each charging pile in the current unit time, and the target load is determined according to the charging pile priority.

[0011] Optionally, the first objective function is expressed as: ; in, E is the value of the first objective function, N is the number of charging piles, Indicates the actual load of the i-th charging pile in the current unit time; Represents the target load of the i-th charging pile in the current unit time.

[0012] Optionally, when the target electric vehicle is charged by the target charging pile, a mixed integer linear programming model is used to optimize the power distribution of the target charging pile, specifically including: The second objective function of optimizing the power distribution of the target charging pile using the mixed integer linear programming model is expressed as: ; in, represents the mean square error of the grid load, represents the charging cost of the charging pile, represents the management cost of the energy storage system, , and are target weight coefficients.

[0013] Optionally, the constraints of the second objective function include charging pile power constraints, grid load balance constraints and vehicle charging demand constraints.

[0014] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides an electric vehicle charging distribution adjustment method. When the predicted charging probability is greater than a set probability value, the charging priority of a target electric vehicle is determined. In order to match a target charging pile for the target electric vehicle according to the charging priority, a mixed-integer linear programming (MILP) model is used to optimize the power distribution of the target charging pile during charging, thereby achieving more targeted charging pile matching. The power distribution is optimized again during charging, thereby achieving distributed energy optimization of each charging pile and improving the energy utilization rate of electric vehicle charging in a parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a method for adjusting charging distribution of an electric vehicle provided in one embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0019] The present application provides a method for adjusting charging distribution of electric vehicles, such as Figure 1 As shown, the electric vehicle charging distribution adjustment method includes: Step 101: Collecting power information of a target electric vehicle entering a target parking lot; a plurality of charging piles are arranged in the target parking lot.

[0020] Step 102: predicting the charging probability of the target electric vehicle according to the power information.

[0021] Step 103: When the charging probability of the target electric vehicle is greater than a set probability value, the charging priority of the target electric vehicle is determined according to the status information of the target electric vehicle; the status information includes the distance between the target electric vehicle and the nearest charging pile, the parking time and the required power; the required power is the difference between the remaining power of the target electric vehicle and the power required for the adjacent trip.

[0022] Step 104: Match a target charging pile for the target electric vehicle; the target charging pile is a charging pile that is in an idle state and corresponds to the charging priority; each of the charging piles corresponds to a charging pile priority, and each charging pile priority provides a corresponding charging power range.

[0023] Step 105: When the target electric vehicle is charged by the target charging pile, a mixed integer linear programming model is used to optimize the power distribution of the target charging pile.

[0024] This application achieves two power dispatches by matching target charging piles for target electric vehicles and optimizing power distribution during charging, thus achieving overall distributed energy optimization of each charging pile and improving the energy utilization rate of electric vehicle charging in the parking lot.

[0025] The power information includes the remaining power and the power required for the adjacent trip.

[0026] The vehicle information collected in step 101 includes not only power information but also electric vehicle types, and the electric vehicle types include hybrid electric vehicles, plug-in hybrid electric vehicles, extended-range electric vehicles and pure electric vehicles.

[0027] For vehicles that are being charged, the vehicle information obtained includes: (1) the charging start time, the estimated time required to fully charge or charge to the user-specified power, and the real-time recording of the charging time and the charged power, a total of four information; (2) the real-time charging voltage, current and their changes (the charging power is also obtained), the real-time battery charging temperature and its changes (taking the average temperature of the battery cells); (3) the total actual charging time of the vehicle and the parking time of the vehicle (not leaving the parking space after charging is completed).

[0028] The power required for the adjacent trip is the power required for the next trip of the target electric vehicle. For the parking time, if the target electric vehicle is not entering the target parking lot for the first time, the parking time is the time from the target electric vehicle entering the target parking lot to parking in a certain parking space. If the target electric vehicle is entering the target parking lot for the first time, the parking time is the default time.

[0029] Wherein, step 102 specifically includes: predicting the charging probability of the target electric vehicle by using a Bayesian probability model according to the power information.

[0030] The power information is input into a Bayesian probability model to obtain the charging probability of the target electric vehicle.

[0031] The charging probability of the target electric vehicle can also be said to be the user's charging willingness.

[0032] The Bayesian probability model is expressed as: .

[0033] in, Indicates the remaining power of the target electric vehicle; Indicates the power required for the adjacent trip of the target electric vehicle; represents the charging probability of the target electric vehicle, represents the probability of the power information under the charging probability condition, represents the probability of the power information, represents the charging probability of the target electric vehicle under the condition of the power information, represents the probability of the kth remaining power interval, For the The sum of the probabilities of the power intervals required for adjacent trips is 100%, and the sum of the probabilities of the power intervals required for n adjacent trips is 100%. Indicates that the target electric vehicle is in the k The remaining power interval and The probability of the required power interval of adjacent trips. Indicates that the remaining power in the range of 0-100% is divided into m small intervals; It means that the power required for the user's adjacent trip is divided into n intervals within the range of 0-100%.

[0034] The remaining power and the power required for the next trip are combined to predict whether the user will charge. When the remaining power is low and the power required for the next trip is high, the user is more willing to charge.

[0035] Wherein, step 103 specifically includes: when the charging probability of the target electric vehicle is greater than the set probability value, according to the state information of the target electric vehicle, a fuzzy logic algorithm is used to determine the charging priority of the target electric vehicle, specifically including: The distance, the parking time and the required power in the status information are normalized respectively to obtain a fuzzy distance factor, a fuzzy time factor and a fuzzy required power factor.

[0036] The formula for normalizing the distance between the target electric vehicle and the nearest charging pile is: .

[0037] in, It is represented as the fuzzy distance factor between the target electric vehicle i and the charging pile j, is the actual distance between the target electric vehicle i and the charging pile j, is the minimum distance, is the maximum distance, the minimum distance is the minimum distance from all electric vehicles to the designated charging pile, and the maximum distance is the maximum distance from all electric vehicles to the designated charging pile.

[0038] The formula for normalizing parking time is: .

[0039] in, represents the fuzzy time factor, Indicates parking time.

[0040] The fuzzy distance factor, fuzzy time factor and fuzzy power demand factor are fuzzified: the input function is represented by using predefined language variables and membership functions, and the fuzzy distance factor is mapped to a first language variable according to a first setting rule. The fuzzy time factor is mapped to a second language variable according to a second setting rule. The fuzzy power demand factor is mapped to a third language variable according to a third setting rule. Specifically: the distance is mapped to the first language variable: near, medium, and far; the parking time is mapped to the second language variable: short, medium, and long; the power demand is mapped to the third language variable: urgent, medium, and slow. Through this fuzzification process, the system can process continuous variables and convert them into language variables for fuzzy reasoning.

[0041] According to the first language variable, the second language variable and the third language variable, the charging priority of the target electric vehicle is determined by using an IF / THEN rule. Specifically, through the IF / THEN rule, fuzzy logic can combine multiple inputs into an output priority, and the input combination is a combination of the first language variable, the second language variable and the third language variable. The rules are shown in Table 1.

[0042] Table 1 Mapping and combination of IF / THEN rules

[0043] The determination of the rules in Table 1 specifically includes: by combining multiple rules, the system can obtain different priority weight values ​​based on different input combinations. The extreme value standardization (Min-Max) method is used for combination, and the minimum value of the fuzzy value in each rule is taken as the result of the rule, that is, the charging priority, and then the maximum value of all rule results is taken for integration.

[0044] Defuzzification: After the fuzzy reasoning is completed, the weight value is defuzzified by the centroid method. That is, the centroid position in the fuzzy set is used to determine the final weight value (priority). The larger the weight value, the higher the priority of the electric vehicle. Finally, the charging management system generates a weight matrix based on the calculated weight value and uses it in the charging scheduling algorithm. In Table 1, the first priority is the highest priority and the sixth priority is the lowest priority.

[0045] Determination of the centroid position: The goal of the centroid method is to find the centroid position of the fuzzy set and use this position as the final clear numerical output. The specific steps are as follows: (1) Calculate the centroid (center of mass) of each point in the fuzzy set through mathematical integration. This centroid is the center position of the entire fuzzy set. (2) The centroid of the fuzzy set can be calculated by the formula calculate.

[0046] in, μ( x ) is a fuzzy set in x The degree of membership of the position, represents the centroid, the numerator is the centroid of each point multiplied by the membership of the point, and the denominator is the sum of the membership of the entire fuzzy set. By calculating the integral in the above formula, the system can get the center position of the fuzzy set, which is the centroid, representing the "balance point" of the entire fuzzy set. The centroid method uses this balance point to determine the final charging priority value in the rule.

[0047] In an exemplary embodiment, the electric vehicle charging allocation adjustment method further includes: allocating charging pile priorities to each charging pile in the target parking lot every unit time, specifically including: A simulated annealing algorithm is used to optimize the grading scheme of charging piles; the grading scheme includes the charging pile priority of each charging pile in the target parking lot; during the optimization process using the simulated annealing algorithm, the first objective function in each iteration is determined according to the difference between the actual load and the target load of each charging pile in the current unit time, and the target load is determined according to the charging pile priority.

[0048] In this embodiment, the unit time is one day, that is, the priority allocation of charging piles is re-performed at a set time every day, and then the latest charging pile classification scheme is executed.

[0049] The first objective function is expressed as: .

[0050] in, E is the value of the first objective function, N is the number of charging piles, Indicates the actual load of the i-th charging pile in the current unit time; Represents the target load of the i-th charging pile in the current unit time.

[0051] The optimization process of the charging pile classification scheme using the simulated annealing algorithm specifically includes: randomly initializing the charging pile classification scheme, that is, assigning an initial charging pile priority to each charging pile. The priority of the charging pile can be divided according to the real-time parking and charging status of the vehicle and the regional power load.

[0052] The optimization goal is to minimize the value of the first objective function, that is, to minimize the gap between the actual load and the target load, so as to achieve balanced distribution of the charging pile load.

[0053] State update: In each iteration, the current charging pile classification scheme is randomly adjusted, and the new energy value (the value of the first objective function) is calculated according to the first objective function. If the new classification scheme has a smaller energy value than the current classification scheme, the classification scheme is accepted. If the energy value of the new classification scheme is higher, the classification scheme is accepted with a certain probability (the probability is controlled by the current temperature). This process imitates the annealing process in the physical system, allowing the simulated annealing algorithm to explore the global optimal solution.

[0054] Stop condition: When the temperature drops to the preset threshold, or when the energy value changes little after multiple iterations, the simulated annealing algorithm stops iterating and outputs the current optimal charging pile classification scheme.

[0055] The charging pile priority includes high priority, medium priority and low priority. The first and second priorities in the charging priority match the high priority in the charging pile priority; the third and fourth priorities in the charging priority match the medium priority in the charging pile priority; the fifth and sixth priorities in the charging priority match the low priority in the charging pile priority.

[0056] High-priority charging piles have a higher power to connect to the grid and are suitable for vehicles that need to charge quickly. The charging system will prioritize the allocation of vehicles to high-priority charging piles to ensure efficient use of power resources; medium-priority charging piles have a more balanced load and are suitable for vehicles that park for a long time. By reasonably allocating charging power, medium-priority charging piles can provide stable charging services for vehicles; low-priority charging piles are suitable for vehicles that do not require high charging time. These charging piles can reduce the pressure on the grid by dispersing the charging load.

[0057] Wherein, step 105 specifically includes: using a mixed integer linear programming model to optimize the power distribution of the target charging pile, the second objective function is expressed as: .

[0058] in, represents the mean square error of the grid load, that is, the minimization target of grid load fluctuation, represents the charging cost of the charging pile, and optimizes this cost to maximize the economic benefits of the charging station, Represents the management cost of the energy storage system. By scheduling the charging and discharging of the energy storage system, optimal management under the difference in peak and valley electricity prices can be achieved. , and They are all target weight coefficients, which are used to balance the three goals of grid load, electric vehicle charging and energy storage management.

[0059] The mean square error of the power grid load is expressed as: .

[0060] in, Indicates The grid load in the time interval is represents the average load of the power grid, Indicates the total number of time intervals.

[0061] The charging cost is expressed as: .

[0062] in, Indicates The output power of each charging station, Indicates Charging time of each charging station, Indicates The charging price of a charging station.

[0063] The energy storage system management cost is expressed as: .

[0064] in, Indicates The charge and discharge capacity of each energy storage unit, Indicates the time interval, represents the unit cost of energy storage management, is the number of energy storage units.

[0065] In step 105, data collection is first performed, including key parameters such as vehicle charging demand, remaining power of electric vehicles, battery health status, power resource conditions of charging stations, and real-time load of the power grid. This data is obtained in real time through IoT devices and used as input data for the power distribution optimization algorithm.

[0066] Vehicle charging demand data: including the vehicle's current remaining power, required charging amount, estimated charging time and charging priority.

[0067] Charging station status information: including charging pile availability, charging pile power output capacity, station load and connection to the power grid.

[0068] Grid load conditions: including real-time changes in grid load, and the power generation and storage of distributed energy (such as photovoltaics and energy storage systems).

[0069] After data collection is completed, a mixed integer linear programming model is used to optimize the power distribution of charging facilities.

[0070] The constraints of the second objective function include charging pile power constraints, grid load balance constraints and vehicle charging demand constraints.

[0071] The charging pile power constraint is expressed as: .

[0072] in, Indicates the power output of the target charging pile at the current moment, It is the maximum output power of the target charging pile.

[0073] The grid load balance constraint is expressed as: .

[0074] in, represents the current vehicle charging power demand of the i-th charging pile; Indicates the total power input from the main grid; Represents the total power provided by distributed renewable energy sources (such as photovoltaic systems or wind systems); Represents the total power resources (including main grid and renewable energy) available in the target area.

[0075] This constraint ensures that at each point in time, the total grid load does not exceed the system capacity, while taking into account the input from distributed energy resources (such as photovoltaics).

[0076] The vehicle charging demand constraint is expressed as: .

[0077] in, represents the battery power status of the target electric vehicle at time t, Indicates the battery power status of the target electric vehicle at time t+1, For charging efficiency, is the output power of the target charging pile at the current moment, is the time step.

[0078] This application uses mixed integer linear programming and simulated annealing algorithms to solve the optimization model. By iteratively solving the optimal solution, it ensures dynamic adjustment of power resources at different time periods. The system calculates the vehicle charging demand and grid load at each time point, and achieves grid load smoothing by adjusting the input of distributed energy and the charging and discharging behavior of the energy storage system.

[0079] In actual applications, the optimization model monitors the usage of charging piles, the charging needs of vehicles, and the load of the power grid in real time. The system dynamically adjusts the power distribution of each charging station based on real-time data to ensure that the power grid is not overloaded during peak hours, while improving charging efficiency and maximizing the utilization of distributed energy.

[0080] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for adjusting charging distribution of electric vehicles, characterized in that: The electric vehicle charging distribution adjustment method comprises: Collecting power information of a target electric vehicle entering a target parking lot; a plurality of charging piles are arranged in the target parking lot; Predicting a charging probability of the target electric vehicle according to the power information; When the charging probability of the target electric vehicle is greater than a set probability value, the charging priority of the target electric vehicle is determined according to the state information of the target electric vehicle; the state information includes the distance between the target electric vehicle and the nearest charging pile, the parking time and the required power; the required power is the difference between the remaining power of the target electric vehicle and the power required for the adjacent trip; Matching a target charging pile for the target electric vehicle; the target charging pile is a charging pile that is in an idle state and corresponds to the charging priority; each of the charging piles corresponds to a charging pile priority, and each charging pile priority provides a corresponding charging power range; When the target electric vehicle is charged by the target charging pile, a mixed integer linear programming model is used to optimize the power distribution of the target charging pile.

2. The electric vehicle charging distribution adjustment method according to claim 1, characterized in that: The power information includes the remaining power and the power required for the adjacent trip.

3. The electric vehicle charging distribution adjustment method according to claim 2, characterized in that: Predicting the charging probability of the target electric vehicle according to the power information specifically includes: A Bayesian probability model is used to predict the charging probability of the target electric vehicle according to the power information.

4. The electric vehicle charging distribution adjustment method according to claim 3 is characterized in that: The Bayesian probability model is expressed as: ； in, Indicates the remaining power of the target electric vehicle; Indicates the power required for the adjacent trip of the target electric vehicle; represents the charging probability of the target electric vehicle, represents the probability of the power information under the charging probability condition, represents the probability of the power information, represents the charging probability of the target electric vehicle under the condition of the power information, represents the probability of the kth remaining power interval, For the The sum of the probabilities of the power intervals required for adjacent trips is 100%, and the sum of the probabilities of the power intervals required for n adjacent trips is 100%. Indicates that the target electric vehicle is in the k The remaining power interval and The probability of the required power interval of adjacent trips.

5. The electric vehicle charging distribution adjustment method according to claim 1, characterized in that: When the charging probability of the target electric vehicle is greater than a set probability value, determining the charging priority of the target electric vehicle according to the state information of the target electric vehicle specifically includes: When the charging probability of the target electric vehicle is greater than a set probability value, a fuzzy logic algorithm is used to determine the charging priority of the target electric vehicle according to the state information of the target electric vehicle.

6. The electric vehicle charging distribution adjustment method according to claim 5, characterized in that: According to the state information of the target electric vehicle, a fuzzy logic algorithm is used to determine the charging priority of the target electric vehicle, specifically including: Normalizing the distance, the parking time and the required power in the status information respectively to obtain a fuzzy distance factor, a fuzzy time factor and a fuzzy required power factor; Mapping the fuzzy distance factor into a first language variable according to a first setting rule; Mapping the fuzzy time factor into a second language variable according to a second setting rule; Mapping the fuzzy power demand factor into a third language variable according to a third setting rule; The charging priority of the target electric vehicle is determined by adopting an if / then rule according to the first language variable, the second language variable and the third language variable.

7. The electric vehicle charging distribution adjustment method according to claim 1, characterized in that: The electric vehicle charging allocation adjustment method further includes: allocating charging pile priorities to each charging pile in the target parking lot every unit time, specifically including: A simulated annealing algorithm is used to optimize the grading scheme of charging piles; the grading scheme includes the charging pile priority of each charging pile in the target parking lot; during the optimization process using the simulated annealing algorithm, the first objective function in each iteration is determined according to the difference between the actual load and the target load of each charging pile in the current unit time, and the target load is determined according to the charging pile priority.

8. The electric vehicle charging distribution adjustment method according to claim 7, characterized in that: The first objective function is expressed as: ; in, E is the value of the first objective function, N is the number of charging piles, Indicates the actual load of the i-th charging pile in the current unit time; Represents the target load of the i-th charging pile in the current unit time.

9. The electric vehicle charging distribution adjustment method according to claim 1, characterized in that: When the target electric vehicle is charged by the target charging pile, a mixed integer linear programming model is used to optimize the power distribution of the target charging pile, specifically including: The second objective function of optimizing the power distribution of the target charging pile using the mixed integer linear programming model is expressed as: ; in, represents the mean square error of the grid load, represents the charging cost of the charging pile, represents the management cost of the energy storage system, , and are target weight coefficients.

10. The electric vehicle charging distribution adjustment method according to claim 9, characterized in that: The constraints of the second objective function include charging pile power constraints, grid load balance constraints and vehicle charging demand constraints.

Images