Charging pile control system

By randomly generating initial populations and multi-objective optimization algorithms, the charging power distribution is optimized, and the problems of waste of resources and poor charging speed of the charging pile system are solved, efficient and stable charging services are achieved, and user experience is improved.

CN118977599AInactive Publication Date: 2024-11-19JIANGYIN CHUANGREN SOFTWARE TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410916649.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing charging pile systems have problems of waste and poor charging speed in resource allocation, especially when the charging power demand of a vehicle exceeds the output capacity of a single charger, or the charging power of multiple vehicles is different, resulting in uneven charging. , affects the user experience.

Method used

The charging pile control system that randomly generates the initial population is adopted, and the charging power distribution is optimized through multi-objective optimization algorithm and random disturbance and cross-operation to ensure the rationality of the charging process and resource utilization, avoid resource waste, and improve system flexibility and adaptability.

Benefits of technology

Achieve more efficient, stable and personalized charging services, improve user experience, evaluate the performance of charging solutions by calculating objective functions and sorting, identifying highly competitive solutions, dynamically adjusting the power distribution of chargers, and meeting the needs of different vehicles. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118977599A_ABST
    Figure CN118977599A_ABST
Patent Text Reader

Abstract

The invention discloses a charging pile control system, particularly relates to the field of charging pile management, is used for solving the problem of charging power distribution optimization, and avoids the condition of non-uniform charging or resource waste when a charging power distribution scheme is generated by randomly generating an initial population. By calculating the objective function and sorting, the performance of each charging scheme, such as charging efficiency, waiting time and resource utilization rate, can be better evaluated so as to select a scheme with better performance. Random disturbance and crossover operation are introduced to increase the diversity of the population, individuals in the population are continuously optimized in the whole scheme optimization iteration process, and the optimal solution is gradually approached. Measuring the flexibility and adaptability of each solution, comprehensively calculating to obtain a normalized coefficient, further representing the comprehensive quality of each solution, and sorting each solution in the non-inferior solution set according to the normalized coefficient. These steps help identify solutions with higher competitiveness and flexibility.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of charging pile management, and more specifically, to a charging pile control system. Background Art

[0002] In order to save space, some existing charging piles have multiple gun heads. Multiple chargers are installed inside the charging pile, and each charger is fixed to serve a designated gun head.

[0003] However, even if multiple chargers are equipped, there may still be a waste of resources and poor charging speed. For example, when only one gun head is charging, but the charging power required by the vehicle exceeds the output capacity of the single charger of the gun head, the charger cannot meet the needs of the vehicle, while other chargers are idle. Another situation is that when multiple gun heads are charging at the same time, the charging power of different vehicles is different, and some vehicles may have excessive charging power while other vehicles have insufficient charging power. In this case, the charging speed will be affected and the user experience will not be ideal.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a charging pile control system. First, by randomly generating an initial population, it is ensured that the charging pile system takes into account the diversity of different charging requirements, thereby helping the system to find a better charging solution. When generating a charging power allocation scheme, the constraints are met to ensure that the charging process is reasonable and avoid uneven charging or waste of resources. By calculating the objective function and sorting it, the performance of each charging scheme, such as charging efficiency, waiting time and resource utilization, can be better evaluated to select a scheme with better performance. The introduction of random perturbations and crossover operations increases the diversity of the population, helps the system avoid falling into a local optimal solution, and improves the flexibility and adaptability of the system. Finally, in the entire solution optimization iterative process, the individuals in the population are continuously optimized, gradually approaching the optimal solution, and providing vehicles with more efficient, stable and personalized charging services. And for obtaining the latest non-inferior solution set, the flexibility and adaptability of each solution are measured and the normalization coefficient is calculated comprehensively, thereby representing the comprehensive quality of each solution, and each solution in the non-inferior solution set is sorted according to the normalization coefficient. It helps to identify solutions with higher competitiveness and flexibility, and provides an important reference for the design and optimization of vehicle charging systems. Specifically, during the charging process, the gun head on each side can freely schedule the charger to work according to changes in vehicle power demand, thereby realizing dynamic power allocation of the charger to solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solution: comprising an integration module, an optimization module, a measurement module and a sorting module;

[0007] The integration module counts multiple objectives and constraints that need to be optimized in the dynamic allocation of vehicle charging power, integrates the objective function and constraints into a standard form of multi-objective optimization, and sends the objective function and constraints in the standard form to the optimization module;

[0008] The optimization module uses a multi-objective optimization algorithm to optimize the objective function, obtain a set of non-inferior solutions, and send the non-inferior solutions to the measurement module;

[0009] The measurement module measures the flexibility and adaptability of each solution and sends the measurement results to the sorting module;

[0010] The sorting module sorts each solution in the non-inferior solution set according to the specific values ​​of the measured flexibility and adaptability.

[0011] In a preferred embodiment, S1 specifically includes the following contents:

[0012] S1-1, determine multiple optimization objectives, including maximizing charging efficiency, minimizing charging waiting time, and maximizing charging pile resource utilization;

[0013] S1-2, converting the optimization objective into an objective function;

[0014] S1-3, convert the constraint target into a standard form.

[0015] In a preferred embodiment, S2 includes the following contents:

[0016] S2-1, randomly generate a specified number of individuals as the initial population;

[0017] S2-1-1, determine the size of the initial population;

[0018] S2-1-2, for each individual, a charging power allocation scheme is randomly generated to satisfy the constraints;

[0019] For each vehicle, randomly assign charging power to each gun head, ensuring that each gun head is connected to at least one charger and does not exceed the number of chargers;

[0020] For each charger, randomly generate its output power to meet the constraints of the charger output power;

[0021] S2-1-3, use the objective function formula to calculate the charging efficiency, charging waiting time and charging pile resource utilization rate of each individual;

[0022] S2-1-5, saving the charging power allocation scheme of each individual and its corresponding fitness value;

[0023] S2-1-6, repeatedly execute steps S2-1-2 to S2-1-4 until a sufficient number of individuals are generated;

[0024] S2-1-7, returns all generated individuals as the initial population as the starting point of the optimization algorithm.

[0025] In a preferred embodiment, S2-2, sorting the individuals in the population according to the performance of the non-inferior solutions to obtain a set of non-inferior solutions;

[0026] S2-2-1, initialize an empty set of non-inferior solutions;

[0027] S2-2-2, for each individual in the population, determine whether it is a non-inferior solution;

[0028] If there is another individual that is at least higher than or equal to the current individual in all objective functions, then the current individual is not a non-inferior solution;

[0029] If the current individual is a non-inferior solution, add it to the non-inferior solution set;

[0030] S2-2-3, updating the non-inferior solution set according to the non-inferior solution determination condition;

[0031] If the current individual is a non-inferior solution, add it to the non-inferior solution set; otherwise, remove it from the population;

[0032] S2-2-4, repeatedly perform steps S2-2-3 and S2-2-4 until all individuals in the population are determined to be non-inferior solutions or the set of non-inferior solutions already contains all non-inferior solutions;

[0033] S2-2-5, returns the obtained non-inferior solution set as the result of the optimization algorithm.

[0034] In a preferred embodiment, S2-3, individuals are selected from the population for reproduction, a rated number of non-inferior solution individuals are retained, and a diversity maintenance strategy is adopted to ensure the diversity of the population;

[0035] S2-3-1, use the objective function to calculate the fitness value of each individual, and select the individual with the largest fitness from a group of randomly selected individuals;

[0036] S2-3-2, determine the number of individuals to be retained based on the rated proportion of the population size, and retain the rated number of non-inferior solution individuals;

[0037] S2-3-3, for each pair of individuals in the population, calculate the similarity between them to evaluate the diversity of solutions in the population;

[0038] If the similarity between individuals is higher than the similarity threshold, a diversity increase strategy signal is generated; if the similarity between individuals is lower than or equal to the similarity threshold, a diversity preservation signal is generated;

[0039] In the case of obtaining a signal of increasing diversity strategy, the diversity of the population is increased by introducing random perturbations and crossover operations, new individuals are generated, the generated new individuals are added to the population, and the fitness of the newly generated individuals is calculated;

[0040] S2-4, repeatedly iterate and execute step S2-2 to step S2-3 until the maximum number of iterations is reached.

[0041] In a preferred embodiment, S3 includes the following contents:

[0042] The latest set of non-inferior solutions is obtained, and for each solution in the set, the flexibility index and adaptability index of each solution are obtained through simulation calculation.

[0043] In a preferred embodiment, the process of obtaining the flexibility index is as follows:

[0044] For each solution, its behavior pattern is obtained by simulating its execution process in different environments;

[0045] Suppose there are N environmental scenarios and M performance indicators. For each solution, its M performance indicators in different environmental scenarios are represented as a matrix with a size of M×N.

[0046] Calculate the mean vector and covariance matrix of each solution on each performance indicator;

[0047] First, the difference between the performance index vector of each solution in each environmental scenario and the mean vector of the performance index in all environmental scenarios is calculated;

[0048] Then, transpose this difference vector to get the row vector;

[0049] Next, the difference vector is linearly transformed using the inverse matrix of the covariance matrix of the performance indicators in all environmental scenarios;

[0050] Perform an inner product operation on the linearly transformed vector and the original vector to obtain a value, which indicates the degree of change of the performance indicator in each environmental scenario;

[0051] Finally, the degree of change of the performance indicators of the solution in all environmental scenarios is averaged to obtain the flexibility index of the solution.

[0052] In a preferred embodiment, the calculation process of the adaptation index is:

[0053] According to the calculation process of the flexibility index, the mean vector and covariance matrix of each solution on each performance index are obtained;

[0054] Normalize the value of each performance indicator to make it fall within the range of [0,1];

[0055] For each solution, calculate its distance to every other solution on the Pareto front;

[0056] For each solution, calculate the distance to every other solution and add them together to get the total distance;

[0057] Normalize the total distance, that is, add 1 to each distance and then take the reciprocal;

[0058] All normalized distances are summed to obtain the fitness index.

[0059] In a preferred embodiment, S4 includes the following contents:

[0060] The flexibility index and the adaptability index are de-dimensionalized and normalized to obtain the normalized coefficient. Each solution in the non-inferior solution set is sorted from large to small according to the normalized coefficient, and the solution corresponding to the first-ranked solution is used to modify the charging power of the distribution gun head.

[0061] The technical effects and advantages of a charging pile control system of the present invention are as follows:

[0062] 1. First, the present invention randomly generates an initial population to ensure that the charging pile system takes into account the diversity of different charging needs, which helps the system to find a better charging solution. Secondly, when generating a charging power allocation plan, satisfying the constraints ensures the rationality of the charging process and prevents uneven charging or waste of resources. By calculating the objective function and sorting it, the system can better evaluate the performance of each charging solution, such as charging efficiency, waiting time, and resource utilization, which helps to select a solution with better performance. The introduction of random perturbations and crossover operations increases the diversity of the population, which helps the system avoid falling into a local optimal solution and improves the flexibility and adaptability of the system. Finally, during the entire iterative process of solution optimization, the system continuously optimizes the individuals in the population and gradually approaches the optimal solution, thereby providing vehicles with more efficient, stable and personalized charging services and improving the user's charging experience.

[0063] 2. The present invention obtains the latest set of non-inferior solutions and calculates the flexibility index and adaptability index for each solution. The flexibility index obtains the degree of change of the performance indicators of the solution in different environmental scenarios by simulating the execution process of the solution in different environments, and is used to evaluate the adaptability and flexibility of the solution. The adaptability index evaluates the overall performance of the solution set in the multi-objective optimization problem by calculating the distance from the solution to other solutions on the Pareto front. The normalization coefficients of these indicators are used to represent the comprehensive quality of each solution, and each solution in the non-inferior solution set is ranked according to the normalization coefficient. These steps help to identify solutions with higher competitiveness and flexibility, and provide an important reference for the design and optimization of vehicle charging systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a structural schematic diagram of a charging pile control system of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Example 1

[0067] Figure 1 The present invention provides a charging pile control system, comprising: an integration module, an optimization module, a measurement module and a sorting module;

[0068] The integration module counts multiple objectives and constraints that need to be optimized in the dynamic allocation of vehicle charging power, integrates the objective function and constraints into a standard form of multi-objective optimization, and sends the objective function and constraints in the standard form to the optimization module;

[0069] The optimization module uses a multi-objective optimization algorithm to optimize the objective function, obtain a set of non-inferior solutions, and send the non-inferior solutions to the measurement module;

[0070] The measurement module measures the flexibility and adaptability of each solution and sends the measurement results to the sorting module;

[0071] The sorting module sorts each solution in the non-inferior solution set according to the specific values ​​of the measured flexibility and adaptability.

[0072] S1 specifically includes the following:

[0073] S1-1, determine multiple optimization objectives, including maximizing charging efficiency, minimizing charging waiting time, and maximizing charging pile resource utilization;

[0074] Maximizing charging efficiency means allocating the total output power of the charging pile to the vehicle, hoping to utilize the power of the charging pile as much as possible to maximize the charging efficiency of the vehicle;

[0075] Minimizing the charging waiting time is to avoid wasting time waiting for charging. It is necessary to minimize the charging waiting time of all vehicles.

[0076] Maximize the utilization rate of charging pile resources. Make full use of the total power of the charging piles and maximize the utilization rate of charging pile resources.

[0077] S1-2, converting the optimization objective into an objective function;

[0078] Charging efficiency f1:

[0079] Charging efficiency can be defined as the sum of the ratios of all vehicle charging powers to their maximum charging powers.

[0080] The formula is:

[0081] Among them, P i represents the actual charging power of vehicle i, P maxi is the maximum charging power of vehicle i.

[0082] Charging efficiency is an important indicator to measure whether the charging system can effectively utilize the power of the charging pile. By maximizing the charging efficiency, it can ensure that the charging pile system can fully meet the charging needs of the vehicle at a given power and improve the energy utilization efficiency of the system. This is of great significance for reducing energy waste and saving energy costs. It can also shorten the charging time of the vehicle and improve the utilization rate of the charging pile.

[0083] Charging waiting time f2:

[0084] The charging waiting time can be defined as The sum of waiting times.

[0085] The calculation formula is:

[0086] Among them, Wait i represents the charging waiting time of vehicle i.

[0087] Charging waiting time is a key indicator for measuring the efficiency of charging services. By minimizing the charging waiting time, the time users wait for charging can be shortened, improving user experience and satisfaction. Reducing the charging waiting time can also increase the turnover rate of charging piles, reduce the idle time of charging piles, and improve the efficiency of charging piles. This is of great significance to improving the efficiency and quality of charging services and helps attract more users to use charging piles.

[0088] Charging pile resource utilization rate f3:

[0089] The resource utilization rate of charging piles can be defined as the ratio of the sum of the actual power used by all charging piles to the total power of the charging piles.

[0090] The calculation formula is:

[0091] in, represents the power used by charging pile i, P total is the total power of the charging pile.

[0092] The resource utilization rate of charging piles is a key indicator to measure the resource utilization efficiency of charging pile systems. By maximizing the resource utilization rate of charging piles, it is possible to ensure that the charging pile system fully utilizes its available charging power and improves the utilization efficiency and economy of charging piles. This is of great significance for optimizing the energy utilization of the charging pile system, reducing energy waste, and reducing charging costs, and helps to improve the overall operating efficiency and economic benefits of the charging pile system.

[0093] S1-3, convert the constraint target into a standard form;

[0094] Charging power limit:

[0095] The charging power of each vehicle shall not exceed its maximum charging power;

[0096] Its constraints can be expressed as: i=1,2,…,n;

[0097] Limiting the charging power of each vehicle to no more than its maximum charging power is to ensure the safety of the vehicle's battery and charging equipment during the charging process. Exceeding the maximum charging power may cause battery overheating or damage, and it can also avoid the risk of overloading or overloading the charging equipment.

[0098] Charging pile power balance:

[0099] The sum of the charging power of all vehicles must not exceed the total power of the charging pile.

[0100] Its constraints can be expressed as:

[0101] Limiting the sum of the charging power of all vehicles to no more than the total power of the charging pile is to ensure that the charging pile system operates within the normal working range. By controlling the total power, the overload or overload of the charging pile can be avoided, ensuring the stability and reliability of the system.

[0102] Charger allocation constraints:

[0103] Each gun head must be connected to at least one charger, and the number of chargers cannot exceed.

[0104] For each gun head j, the number of chargers connected to it is k j The following conditions must be met: 1≤k j ≤m;

[0105] Each charger must be connected to at least one charger, and the number of chargers cannot exceed this limit to ensure the availability and fairness of the charging service provided by the charging pile. By limiting the number of chargers, it is possible to avoid the situation where some vehicles occupy all chargers for a long time, causing other vehicles to be unable to charge.

[0106] Charger output power constraints:

[0107] The output power of each charger shall not exceed its rated output power.

[0108] For each charger k, its output power k = 1, 2, ..., m;

[0109] Limiting the output power of each charger to no more than its rated output power is to protect the safety and reliability of the charging equipment. Exceeding the rated output power may cause the charger to overheat or be damaged, and it can also prevent the charging pile system from being overloaded and affecting the stability of the system.

[0110] Charging pile gun head power balance:

[0111] The sum of the charging power of each gun head shall not exceed the total power of the charging pile.

[0112] For each gun head j, the sum of the power of the charger connected to it is The total power of the charging pile shall not exceed P total ,Right now j=1,2,…,n;

[0113] in, represents the power of the kth charger connected to the gun head j, P total is the total power of the charging pile.

[0114] Limiting the sum of the power of the chargers connected to each gun head to not exceed the total power of the charging pile is to maintain the power balance and stability of the charging pile system. By controlling the charging power of the gun head, it is possible to avoid overloading some parts of the charging pile system while underloading other parts, thereby optimizing the utilization efficiency of the charging pile and improving the overall performance of the system.

[0115] S2 includes the following:

[0116] S2-1, randomly generate a specified number of individuals as the initial population;

[0117] S2-1-1, determine the size of the initial population, usually determined through experiments and experience;

[0118] S2-1-2, for each individual, a charging power allocation plan is randomly generated to meet the constraints.

[0119] For each vehicle, randomly assign charging power to each gun head to ensure that each gun head is connected to at least one charger and does not exceed the number of chargers.

[0120] For each charger, its output power is randomly generated to meet the constraints of the charger output power.

[0121] S2-1-3, use the objective function formula to calculate the charging efficiency, charging waiting time and charging pile resource utilization rate of each individual;

[0122] S2-1-5, saving the charging power allocation scheme of each individual and its corresponding fitness value;

[0123] S2-1-6, repeatedly execute steps S2-1-2 to S2-1-4 until a sufficient number of individuals are generated.

[0124] S2-1-7, returns all generated individuals as the initial population as the starting point of the optimization algorithm.

[0125] S2-2, sort the individuals in the population according to the performance of the non-inferior solutions to obtain a set of non-inferior solutions;

[0126] S2-2-1, initialize an empty set of non-inferior solutions;

[0127] S2-2-2, for each individual in the population, determine whether it is a non-inferior solution;

[0128] If there is another individual that is at least better than the current individual in all objective functions, then the current individual is not a non-inferior solution;

[0129] If the current individual is a non-inferior solution, add it to the non-inferior solution set;

[0130] S2-2-3, updating the non-inferior solution set according to the non-inferior solution determination condition;

[0131] If the current individual is a non-inferior solution, add it to the non-inferior solution set; otherwise, remove it from the population;

[0132] S2-2-4, repeatedly perform steps S2-2-3 and S2-2-4 until all individuals in the population are determined to be non-inferior solutions or the set of non-inferior solutions already contains all non-inferior solutions;

[0133] S2-2-5, returns the obtained non-inferior solution set as the result of the optimization algorithm.

[0134] Each solution in the non-inferior solution set corresponds to a specific solution for the charging system. These solutions may have different charging power allocation schemes, charging waiting time arrangements, charging pile resource utilization and other performance indicators. Each solution represents a feasible solution under given constraints, and these solutions will not be optimized by other solutions in multi-objective optimization problems. Therefore, each solution in the non-inferior solution set represents a charging solution with certain advantages and characteristics. These solutions constitute a diversified choice of charging systems and provide a variety of options to meet different user needs and scenarios.

[0135] S2-3, select individuals from the population for reproduction, retain a specified number of non-inferior solution individuals, and adopt a diversity maintenance strategy to ensure the diversity of the population;

[0136] S2-3-1, use the objective function to calculate the fitness value of each individual, and select the individual with the largest fitness from a group of randomly selected individuals;

[0137] S2-3-2, determine the number of individuals to be retained based on the rated proportion of the population size, and retain the rated number of non-inferior individuals to ensure the diversity and stability of the population;

[0138] S2-3-3, for each pair of individuals in the population, calculate the similarity between each other to evaluate the diversity of solutions in the population; the similarity between individuals can be evaluated using distance metrics (such as Euclidean distance or Manhattan distance) or correlation metrics (such as Pearson correlation coefficient or cosine similarity);

[0139] If the similarity between individuals is higher than the similarity threshold, a diversity increase strategy signal is generated; if the similarity between individuals is lower than or equal to the similarity threshold, a diversity preservation signal is generated;

[0140] In the case of obtaining a signal for a strategy to increase diversity, random perturbations and crossover operations are introduced to increase the diversity of the population, new individuals are generated, the generated new individuals are added to the population to increase the diversity of the population, and the fitness of the newly generated individuals is calculated.

[0141] To facilitate understanding, random perturbations and crossover operations are introduced to increase the diversity of the population, as shown below:

[0142] Suppose there is a charging pile with two gun heads, each of which is connected to two chargers, for a total of four chargers. There are several individuals in the population, and each individual represents a charging power allocation scheme.

[0143] For each individual, one or more chargers are randomly selected and their output power is randomly adjusted.

[0144] For example, for an individual, one of the chargers is randomly selected and its output power is randomly increased or decreased.

[0145] Randomly select two individuals to perform a crossover operation to generate new individuals.

[0146] For example, for two individuals, randomly select one of their gun heads and exchange the chargers they are connected to, thereby generating two new individuals.

[0147] For each individual, it is determined with a certain probability whether to apply a random perturbation operation or a crossover operation.

[0148] If a random perturbation operation needs to be applied, one or more chargers in the individual are randomly selected and their output power is randomly adjusted.

[0149] If a crossover operation needs to be applied, two individuals are randomly selected and the connected chargers are swapped between their gun heads.

[0150] The generated new individuals are added to the population to increase the diversity of the population.

[0151] S2-4, repeatedly iterate and execute step S2-2 to step S2-3 until the maximum number of iterations is reached.

[0152] First, the present invention randomly generates an initial population to ensure that the charging pile system takes into account the diversity of different charging needs, which helps the system to find a better charging solution. Secondly, when generating a charging power allocation plan, satisfying the constraints ensures the rationality of the charging process and prevents uneven charging or waste of resources. By calculating the objective function and sorting it, the system can better evaluate the performance of each charging scheme, such as charging efficiency, waiting time, and resource utilization, which helps to select a better performance scheme. The introduction of random perturbations and crossover operations increases the diversity of the population, which helps the system avoid falling into a local optimal solution and improves the flexibility and adaptability of the system. Finally, during the entire iterative process of scheme optimization, the system continuously optimizes the individuals in the population and gradually approaches the optimal solution, thereby providing vehicles with more efficient, stable, and personalized charging services and improving the user's charging experience.

[0153] S3 includes the following:

[0154] The latest set of non-inferior solutions is obtained, and for each solution in the set, the flexibility index and adaptability index of each solution are obtained through simulation calculation.

[0155] The process of obtaining the flexibility index is as follows:

[0156] For each solution, its behavior pattern is obtained by simulating its execution process in different environments.

[0157] Suppose there are N environmental scenarios and M performance indicators. For each solution, its M performance indicators in different environmental scenarios are represented as a matrix with a size of M×N.

[0158] Calculate the mean vector of each solution on each performance indicator and the covariance matrix ∑.

[0159] Calculate the flexibility index using the following formula:

[0160] The specific calculation process is as follows:

[0161] First, the difference between the performance index vector of each solution in each environmental scenario and the mean vector of the performance index in all environmental scenarios is calculated, that is,

[0162] Then, transpose this difference vector to get the row vector

[0163] Next, the inverse matrix of the covariance matrix of the performance indicators in all environmental scenarios is used to linearly transform the difference vector, that is,

[0164] Perform an inner product operation on the vector after linear transformation and the original vector to obtain a value, which indicates the degree of change of the performance index under the environment scenario j;

[0165] Finally, the degree of change of the performance indicators of the solution in all environmental scenarios is averaged to obtain the flexibility index of the solution.

[0166] This flexibility index is used to indicate the degree of change in the performance indicators of the solution in different environmental scenarios, that is, the adaptability and flexibility of the solution to different environments. The larger the flexibility index, the greater the degree of change in the performance indicators of the solution in various environmental scenarios, indicating that the solution has higher flexibility and can respond more adaptively in different situations. The smaller the flexibility index, the smaller the degree of change in the performance indicators of the solution, and the relatively low adaptability and flexibility of the solution in different environmental scenarios. In the vehicle charging scenario, a solution with a higher flexibility index can better cope with the charging needs of different vehicles and the utilization of different charging pile resources, improving charging efficiency and user experience.

[0167] The calculation process of the adaptation index is:

[0168] According to the calculation process of the flexibility index, the mean vector of each solution on each performance index is obtained. and covariance matrix ∑;

[0169] Normalize the solution value on each performance indicator so that it falls within the range of [0,1]. This ensures that the value range of different performance indicators will not affect the final calculation result;

[0170] For each solution, calculate its distance to every other solution on the Pareto front.

[0171] For each solution, calculate the distance of each other solution and add them up to get the total distance. The distance can be calculated using the Euclidean distance.

[0172] Normalize the total distance, that is, add 1 to each distance and then take the reciprocal;

[0173] Add up all normalized distances to get the adaptation index;

[0174] The specific calculation formula is as follows:

[0175] Among them, AverageDistance refers to the average distance from each solution to its nearest solution on the Pareto frontier, which is used to measure the distribution of a set of solutions in multi-objective optimization problems.

[0176] The adaptability index is used to represent the overall performance of the solution set in the multi-objective optimization problem. The larger the adaptability index, the closer the solution set is to the Pareto frontier, that is, it has superior diversity and comprehensiveness, can better cover a variety of optimization objectives, and provide more options. This means that the solutions in the solution set are more competitive and can meet a wider range of needs, thereby providing more possible charging solutions in vehicle charging scenarios, increasing the flexibility and adaptability of the system. On the contrary, a smaller adaptability index may mean that the solution set is unevenly distributed, lacks diversity, and has limited solution selection, which may not meet a variety of different optimization objectives, resulting in limitations and deficiencies in system performance.

[0177] S4 includes the following:

[0178] The flexibility index and the adaptability index are dimensionless and their values ​​are normalized to obtain the normalized coefficient. For example, it can be calculated by the following calculation formula:

[0179] Among them, F′ and A′ are the normalized flexibility index and adaptation index respectively, ω1 and ω2 are the preset proportional coefficients of the normalized flexibility index and adaptation index respectively, and both are greater than zero.

[0180] The normalization coefficient is used to indicate the comprehensive quality of the solution corresponding to each solution in the set of non-inferior solutions. The larger the normalization coefficient, the higher the comprehensive quality of the solution, and its performance under multiple performance indicators is better, with better flexibility and adaptability. This means that the solution is more able to meet various needs in vehicle charging scenarios, provide a more comprehensive charging solution, and have stronger competitiveness and sustainability. On the contrary, a smaller normalization coefficient may indicate that the overall quality of the solution is low, and its performance in various performance indicators is not good enough, and it may not be able to effectively meet the diverse charging needs, resulting in limited performance of the charging system.

[0181] Sort each solution in the non-inferior solution set from large to small according to the normalization coefficient, and use the solution corresponding to the solution with the first place in the sorting to modify the charging power of the distribution gun head.

[0182] Sorting each solution in the set of non-inferior solutions from large to small according to the normalized coefficient means arranging these solutions from high to low according to their comprehensive quality. Such a sorting can help determine which solutions have superior performance and adaptability in multi-objective optimization problems, so as to make more reasonable choices in practical applications. Through this sorting, the most potential and competitive solutions can be quickly identified, providing an important reference for the design and optimization of the charging system.

[0183] The present invention obtains the latest set of non-inferior solutions and calculates the flexibility index and adaptability index for each solution. The flexibility index obtains the degree of change of the performance indicators of the solution in different environmental scenarios by simulating the execution process of the solution in different environments, and is used to evaluate the adaptability and flexibility of the solution. The adaptability index evaluates the overall performance of the solution set in the multi-objective optimization problem by calculating the distance from the solution to other solutions on the Pareto front. The normalization coefficients of these indicators are used to represent the comprehensive quality of each solution, and each solution in the non-inferior solution set is sorted according to the normalization coefficient. These steps help to identify solutions with higher competitiveness and flexibility, and provide an important reference for the design and optimization of vehicle charging systems.

[0184] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0185] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0186] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0187] In the several embodiments provided in the present application, it should be understood that the disclosed systems and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0190] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0191] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0192] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A charging pile control system, characterized in that: It includes integration module, optimization module, measurement module and sorting module; The integration module counts multiple objectives and constraints that need to be optimized in the dynamic allocation of vehicle charging power, integrates the objective function and constraints into a standard form of multi-objective optimization, and sends the objective function and constraints in the standard form to the optimization module; The optimization module uses a multi-objective optimization algorithm to optimize the objective function, obtain a set of non-inferior solutions, and send the non-inferior solutions to the measurement module; The measurement module measures the flexibility and adaptability of each solution and sends the measurement results to the sorting module; The sorting module sorts each solution in the non-inferior solution set according to the specific values ​​of the measured flexibility and adaptability.

2. A charging pile control system according to claim 1, characterized in that: S1 specifically includes the following: S1-1, determine multiple optimization objectives, including maximizing charging efficiency, minimizing charging waiting time, and maximizing charging pile resource utilization; S1-2, converting the optimization objective into an objective function; S1-3, convert the constraint target into a standard form.

3. A charging pile control system according to claim 2, characterized in that: S2 includes the following: S2-1, randomly generate a specified number of individuals as the initial population; S2-1-1, determine the size of the initial population; S2-1-2, for each individual, a charging power allocation scheme is randomly generated to satisfy the constraints; For each vehicle, randomly assign charging power to each gun head, ensuring that each gun head is connected to at least one charger and does not exceed the number of chargers; For each charger, randomly generate its output power to meet the constraints of the charger output power; S2-1-3, use the objective function formula to calculate the charging efficiency, charging waiting time and charging pile resource utilization rate of each individual; S2-1-5, saving the charging power allocation scheme of each individual and its corresponding fitness value; S2-1-6, repeatedly execute steps S2-1-2 to S2-1-4 until a sufficient number of individuals are generated; S2-1-7, returns all generated individuals as the initial population as the starting point of the optimization algorithm.

4. A charging pile control system according to claim 3, characterized in that: S2-2, sort the individuals in the population according to the performance of the non-inferior solutions to obtain a set of non-inferior solutions; S2-2-1, initialize an empty set of non-inferior solutions; S2-2-2, for each individual in the population, determine whether it is a non-inferior solution; If there is another individual that is at least higher than or equal to the current individual in all objective functions, then the current individual is not a non-inferior solution; If the current individual is a non-inferior solution, add it to the non-inferior solution set; S2-2-3, updating the non-inferior solution set according to the non-inferior solution determination condition; If the current individual is a non-inferior solution, add it to the non-inferior solution set; otherwise, remove it from the population; S2-2-4, repeatedly perform steps S2-2-3 and S2-2-4 until all individuals in the population are determined to be non-inferior solutions or the set of non-inferior solutions already contains all non-inferior solutions; S2-2-5, returns the obtained non-inferior solution set as the result of the optimization algorithm.

5. A charging pile control system according to claim 4, characterized in that: S2-3, select individuals from the population for reproduction, retain a specified number of non-inferior solution individuals, and adopt a diversity maintenance strategy to ensure the diversity of the population; S2-3-1, use the objective function to calculate the fitness value of each individual, and select the individual with the largest fitness from a group of randomly selected individuals; S2-3-2, determine the number of individuals to be retained based on the rated proportion of the population size, and retain the rated number of non-inferior solution individuals; S2-3-3, for each pair of individuals in the population, calculate the similarity between them to evaluate the diversity of solutions in the population; If the similarity between individuals is higher than the similarity threshold, a diversity increase strategy signal is generated; if the similarity between individuals is lower than or equal to the similarity threshold, a diversity preservation signal is generated; In the case of obtaining a signal of increasing diversity strategy, the diversity of the population is increased by introducing random perturbations and crossover operations, new individuals are generated, the generated new individuals are added to the population, and the fitness of the newly generated individuals is calculated; S2-4, repeatedly iterate and execute step S2-2 to step S2-3 until the maximum number of iterations is reached.

6. A charging pile control system according to claim 5, characterized in that: S3 includes the following: The latest set of non-inferior solutions is obtained, and for each solution in the set, the flexibility index and adaptability index of each solution are obtained through simulation calculation.

7. A charging pile control system according to claim 6, characterized in that: The process of obtaining the flexible index is as follows: For each solution, its behavior pattern is obtained by simulating its execution process in different environments; Suppose there are N environmental scenarios and M performance indicators. For each solution, its M performance indicators in different environmental scenarios are represented as a matrix with a size of M×N. Calculate the mean vector and covariance matrix of each solution on each performance indicator; First, the difference between the performance index vector of each solution in each environmental scenario and the mean vector of the performance index in all environmental scenarios is calculated; Then, transpose this difference vector to get the row vector; Next, the difference vector is linearly transformed using the inverse matrix of the covariance matrix of the performance indicators in all environmental scenarios; Perform an inner product operation on the linearly transformed vector and the original vector to obtain a value, which indicates the degree of change of the performance indicator in each environmental scenario; Finally, the degree of change of the performance indicators of the solution in all environmental scenarios is averaged to obtain the flexibility index of the solution.

8. A charging pile control system according to claim 7, characterized in that: The calculation process of the adaptation index is: According to the calculation process of the flexibility index, the mean vector and covariance matrix of each solution on each performance index are obtained; Normalize the value of each performance indicator to make it fall within the range of [0,1]; For each solution, calculate its distance to every other solution on the Pareto front; For each solution, calculate the distance to every other solution and add them together to get the total distance; Normalize the total distance, that is, add 1 to each distance and then take the reciprocal; All normalized distances are summed to obtain the fitness index.

9. A charging pile control system according to claim 8, characterized in that: S4 includes the following: The flexibility index and the adaptability index are de-dimensionalized and normalized to obtain the normalized coefficient. Each solution in the non-inferior solution set is sorted from large to small according to the normalized coefficient, and the solution corresponding to the first-ranked solution is used to modify the charging power of the distribution gun head.

Citation Information

Cited By

  • Management service system

    CN120471473A