Electric vehicle charging load regulation and control method and system for diverse application scenarios

Abstract

The present invention provides an electric vehicle charging load regulation and control method and system for diverse application scenarios. In different application scenarios, suitable electric vehicle charging loads are selected for optimized combination and coordinated regulation and control, so that the electric vehicle charging load regulation and control system can quickly and accurately respond to a power grid dispatch instruction, and the overall economy and safety of the electric vehicle charging load regulation and control system can be considered.

Description

A method and system for regulating electric vehicle charging load for multiple application scenarios Technical Field

[0001] The present invention relates to the field of electric vehicle intelligent charging technology, and in particular to a method and system for regulating electric vehicle charging load for multiple application scenarios. Background Art

[0002] With the societal deployment and advancement of the carbon peak and carbon neutrality strategies, the power industry, as one of the core carbon emission sectors, has proposed a medium- and long-term development path for power system construction centered on new energy. By firmly implementing the dual-carbon goals through the large-scale, all-round construction of a new power system, the proportion of new energy consumption has increased significantly, and the decarbonization process has been further accelerated. However, the randomness and volatility of new energy sources have exacerbated the instability of the power system. The gradual replacement of thermal power units with new energy units has significantly reduced the inertia of the power system, making it increasingly difficult for the power system to cope with frequent disturbances of various types. There is an urgent need for more flexible resources to participate in grid balancing and regulation. Electric vehicles are widely distributed and highly flexible, possessing a certain degree of regulation capability. If they can be guided through incentives and other means to assist in the operation of the power system or participate in electricity market transactions, they can effectively alleviate the pressure on grid regulation and support the safe and stable operation of the power system.

[0003] Different application scenarios have different operational requirements for electric vehicle charging loads. For example, frequency regulation scenarios require electric vehicle charging loads with fast response speeds and high charging efficiency, while energy interaction is more closely related to charging capacity. Therefore, how to select appropriate electric vehicle charging loads in different application scenarios for optimal combination and coordinated regulation, so that the electric vehicle charging load regulation system can quickly and accurately respond to grid dispatch instructions while also taking into account the overall economic and safety of the electric vehicle charging load regulation system, is a difficult problem that needs to be urgently addressed in the current electric vehicle charging load regulation system in the process of coordinated regulation of large-scale electric vehicle charging loads.

[0004] Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for regulating the charging load of electric vehicles in multiple application scenarios, so as to solve the problems raised in the above background technology.

[0006] The present invention is achieved through the following technical solutions:

[0007] A method for regulating electric vehicle charging load for multiple application scenarios, comprising the following steps:

[0008] Step S1: Based on the market participation of the electric vehicle charging load flexible control system and the dispatch instructions issued by the power grid, the application scenario identification module identifies the application scenario of the electric vehicle charging load control system, outputs the identification results, and formulates a three-level control system architecture;

[0009] Step S2: Using electric vehicle charging efficiency, charging time, charging capacity, and response rate as key indicators of the membership function, the entropy weight method is introduced to balance the relative importance of multiple indicators, and the clustering results of electric vehicle charging load under the multiple indicators are calculated to achieve cluster division of electric vehicle charging load;

[0010] Step S3: Match application scenario requirements based on application scenario identification results and cluster division results;

[0011] Step S4: Select the most suitable cluster based on the application scenario and grid capacity requirements. When the most suitable cluster can meet the capacity requirements of the application scenario, construct an optimized collaborative control model with the lowest control cost and the best SOC as the objective function;

[0012] Step S5: When the most suitable cluster cannot meet the capacity requirements of the application scenario, it will automatically extend to the second most suitable cluster, and so on, until the capacity requirements of the application scenario are met, and the optimized coordinated control model as described in step S4 is constructed in the last electric vehicle charging load cluster that meets the capacity requirements;

[0013] Step S6: Selecting a suitable electric vehicle charging load according to the optimized coordinated control model.

[0014] Specifically, the application scenarios include three application scenarios: power system peak regulation, power system frequency regulation and electric energy interaction.

[0015] Specifically, the three-level control system architecture includes three levels. The first level is the electric vehicle charging load flexible control system platform, which is used to receive the dispatching instructions issued by the power grid and match the instructions to the next level of control according to the application scenario matching module. The second level is the cluster division and matching level, which is used to cluster all electric vehicles in the electric vehicle charging load flexible control system and match the most suitable cluster according to the corresponding scenario. The third level is the dispatching instruction decomposition level, which is used to decompose the power grid dispatching instructions within the appropriate cluster.

[0016] Specifically, the step S2 includes:

[0017] Step S2.1: sorting and normalizing the raw data from the electric vehicle charging load information acquisition module, extracting the electric vehicle charging efficiency, charging time, charging capacity, and response rate indicators, and calculating the relative importance of different indicators using the entropy weight method;

[0018] Step S2.2: Based on the calculation results of different indicator weights, the improved fuzzy C-means clustering method is used to distinguish the similarities and differences of charging load samples to different cluster centers, so as to achieve accurate clustering of different electric vehicle charging loads;

[0019] Step S2.3: Dynamically modify the cluster division of electric vehicle charging loads in real time based on the application scenario identification results.

[0020] Specifically, the specific process of step S2.1 is as follows:

[0021] The data such as electric vehicle charging efficiency, charging time, charging capacity and response rate indicators are extracted from the electric vehicle charging load information acquisition module, which can be specifically expressed as: F = {η, T, R, S}

[0022] Among them, F represents the set of clustering indicators of electric vehicle charging load; η represents the charging efficiency indicator of electric vehicle charging load; T represents the charging time indicator of electric vehicle charging load; R represents the charging capacity indicator of electric vehicle charging load; S represents the response rate indicator of electric vehicle charging load.

[0023] The original data of different indicators of electric vehicle charging load can be expressed in matrix form:

[0024] Among them, M represents the number of electric vehicle charging loads, N represents the number of aggregated indicators, and B is the relative importance of quantitative different indicators. The entropy weight method is used to calculate the weight of each indicator, specifically:

[0025] Among them, z mn Represents the original data b of the nth aggregate indicator of the mth electric vehicle charging load mn After normalization, the data mn represents the proportion of the nth aggregate index of the mth electric vehicle charging load, e n The information entropy value of the nth electric vehicle charging load aggregation index, ω n Represents the weight of the nth electric vehicle charging load aggregation indicator.

[0026] Then the comprehensive clustering index of the mth electric vehicle charging load can be expressed as: ω n ={ω1,ω2,ω3,ω4} C m =ω1η m +ω2T m +ω3R m +ω4S m

[0027] Among them, ω1, ω2, ω3 and ω4 represent the charging efficiency, charging time, charging capacity and response rate index weights of the electric vehicle charging load respectively, C m represents the comprehensive clustering index value of the mth electric vehicle charging load; η i represents the charging efficiency of the mth electric vehicle charging load, T m represents the charging time of the mth electric vehicle charging load, R m represents the charging capacity of the mth electric vehicle charging load, S m represents the charging load response rate of the mth electric vehicle.

[0028] Specifically, the specific process of step S2.2 is as follows:

[0029] The improved fuzzy C-means clustering method is used to cluster the electric vehicle charging load and divide it into clusters. The specific steps are as follows:

[0030] First, the cluster centers c of different clusters mj The calculation formula is:

[0031] Among them, r is the neighborhood radius; j is the number of clusters, and A is the number of samples within the neighborhood radius.

[0032] Second, initialize the membership matrix U. After the tth iteration, the membership matrix after updating is: U t ={u mj}

[0033] in, It indicates the degree of membership of the mth EV charging load to the jth cluster after the tth iteration; represents the value of the mth electric vehicle charging load to the jth cluster center after the tth iteration; represents the value of the charging load of the mth electric vehicle to the cluster center of the gth cluster after the tth iteration;

[0034] The cluster center matrix after the tth iteration update is:

[0035] in, represents the value of the charging load of the mth electric vehicle to the cluster center of the jth cluster after the tth iteration, and K represents the proportional coefficient;

[0036] Third, when the number of iterations reaches the set termination number or ξ represents a very small number, the iteration is terminated, and the calculation result is output; otherwise, it returns to the second step for the next round of iteration.

[0037] Specifically, the specific process of step S2.3 is as follows:

[0038] The calculation results of different indicator weights are updated by combining manual setting with entropy weight method, so as to correct the cluster division of electric vehicle charging load. The manual setting will be made according to different application scenarios, specifically:

[0039] After some indicators are manually set in the above-mentioned specified scenario, the remaining indicators will be recalculated according to the entropy weight method in step S2.1, thereby updating the weight calculation results of each indicator and the cluster division results will also be updated accordingly.

[0040] Specifically, the specific process of step S4 is as follows:

[0041] The calculation formula with the lowest control cost as the objective function is:

[0042] Among them, F1 is the objective function with the lowest control cost, represents the most suitable charging capacity of the hth electric vehicle charging load in the cluster at time period t, p t represents the charging price of electric vehicle charging load in time period t, T represents the total number of time periods, and H represents the total number of electric vehicle charging loads included in the most suitable cluster;

[0043] The calculation formula with the optimal SOC of electric vehicle charging load as the objective function is:

[0044] Among them, F2 is the optimal objective function for the electric vehicle charging load SOC, represents the state of charge value of the most suitable cluster h-th electric vehicle charging load in time period t; p t Indicates the optimal state of charge value of the electric vehicle charging load;

[0045] The optimized coordinated control model of electric vehicle charging load can be expressed as: F = αF1 + (1-α)F2

[0046] Here, α represents the synergy coefficient.

[0047] A system for regulating and controlling electric vehicle charging loads for multiple application scenarios, the system being applied to the aforementioned method for regulating and controlling electric vehicle charging loads for multiple application scenarios, the system comprising an application scenario identification module, a charging load dynamic clustering module, an application scenario matching module, a charging load information collection module, and a charging load control module;

[0048] The application scenario identification module is used to analyze the types of power market transactions in which the electric vehicle charging load participates and the dispatch instructions issued by the power grid, determine the specific application scenarios in which the electric vehicle charging load control system participates in the power grid interaction in the future, and upload the judgment results to the application scenario matching module;

[0049] The charging load dynamic clustering module is used to cluster the electric vehicle charging load according to clustering indicators such as charging time, charging capacity, charging efficiency and response rate, and upload the clustering results to the application scenario matching module;

[0050] The application scenario matching module is used to select the most suitable cluster of the electric vehicle charging load flexible control system to match the application scenario requirements based on the application scenario identification results and the electric vehicle charging load clustering results;

[0051] The charging load information acquisition module is used to collect and monitor information related to the operating status of the electric vehicle charging load, and upload the data to the application scenario identification module, the charging load dynamic clustering module and the charging load control module;

[0052] The charging load control module is used to receive the charging instructions decomposed by the electric vehicle charging load control system, control the charging of the electric vehicle charging load, and perceive the charging process of the electric vehicle charging load based on the operating data uploaded by the charging load information acquisition module.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention provides an electric vehicle charging load control system and method for multiple application scenarios. The system selects appropriate electric vehicle charging loads in different application scenarios for optimized combination and coordinated control, so that the electric vehicle charging load control system can respond quickly and accurately to power grid dispatch instructions while also taking into account the overall economy and safety of the electric vehicle charging load control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] FIG1 is a flowchart of the steps of a method for controlling charging load of electric vehicles for multiple application scenarios provided by the present invention.

[0057] FIG2 is a structural diagram of an electric vehicle charging load control system for multiple application scenarios provided by the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the present invention more apparent, exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present invention.

[0059] In the following description, numerous specific details are provided to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without one or more of these details. In other instances, certain technical features well known in the art are not described to avoid confusion with the present invention.

[0060] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make disclosure thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0061] The purpose of the terms used herein is only to describe specific embodiments and is not intended to limit the present invention. When used herein, the singular forms "a", "an", and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0062] In order to fully understand the present invention, a detailed structure will be provided in the following description to illustrate the technical solution proposed by the present invention. Optional embodiments of the present invention are described in detail below. However, in addition to these detailed descriptions, the present invention may also have other implementations.

[0063] Referring to FIG1 , a first aspect of the present invention discloses a method for regulating electric vehicle charging load in multiple application scenarios, the method comprising the following steps:

[0064] Step S1: Based on the market participation of the electric vehicle charging load flexible control system and the dispatch instructions issued by the power grid, the application scenario identification module identifies the application scenario of the electric vehicle charging load control system, outputs the identification results, and formulates a three-level control system architecture;

[0065] Step S2: Using electric vehicle charging efficiency, charging time, charging capacity, and response rate as key indicators of the membership function, the entropy weight method is introduced to balance the relative importance of multiple indicators, and the clustering results of electric vehicle charging load under the multiple indicators are calculated to achieve cluster division of electric vehicle charging load;

[0066] Step S3: Match application scenario requirements based on application scenario identification results and cluster division results;

[0067] Step S4: Select the most suitable cluster according to the application scenario and grid capacity requirements. When the most suitable cluster can meet the capacity requirements of the application scenario, construct an optimized collaborative control model with the lowest control cost and the best SOC as the objective function; achieve the goal of meeting the capacity requirements of the application scenario while taking into account the economy of the flexible control system and the safety of electric vehicles.

[0068] Step S5: When the most suitable cluster cannot meet the capacity requirements of the application scenario, it will automatically extend to the second most suitable cluster, and so on, until the capacity requirements of the application scenario are met, and the optimized coordinated control model as described in step S4 is constructed in the last electric vehicle charging load cluster that meets the capacity requirements;

[0069] Step S6: Selecting a suitable electric vehicle charging load according to the optimized coordinated control model.

[0070] Specifically, the application scenarios include three application scenarios: power system peak regulation, power system frequency regulation and electric energy interaction.

[0071] Specifically, the three-level control system architecture includes three levels. The first level is the electric vehicle charging load flexible control system platform, which is used to receive the dispatching instructions issued by the power grid and perform the next level of control according to the application scenario matching module. The second level is the cluster division and matching level, which is used to cluster all electric vehicles in the electric vehicle charging load flexible control system and match the most suitable cluster according to the corresponding scenario. The third level is the dispatching instruction decomposition level, which is used to decompose the power grid dispatching instructions within the appropriate cluster.

[0072] Specifically, the step S2 includes:

[0073] Step S2.1: sort out and normalize the raw data from the electric vehicle charging load information acquisition module, extract indicators such as electric vehicle charging efficiency, charging time, charging capacity, and response rate, and introduce the entropy weight method to calculate the relative importance of different indicators;

[0074] In step S2.2, based on the calculation results of different indicator weights, the improved fuzzy C-means clustering method is used to distinguish the similarities and differences of charging load samples to different cluster centers, so as to achieve accurate clustering of different electric vehicle charging loads;

[0075] Step S2.3 dynamically modifies the cluster division of electric vehicle charging loads in real time based on the application scenario identification results.

[0076] Specifically, the specific process of step S2.1 is as follows:

[0077] The data such as electric vehicle charging efficiency, charging time, charging capacity and response rate indicators are extracted from the electric vehicle charging load information acquisition module, which can be specifically expressed as: F = {η, T, R, S}

[0078] Among them, F represents the set of clustering indicators of electric vehicle charging load; η represents the charging efficiency indicator of electric vehicle charging load; T represents the charging time indicator of electric vehicle charging load; R represents the charging capacity indicator of electric vehicle charging load; S represents the response rate indicator of electric vehicle charging load.

[0079] The original data of different indicators of electric vehicle charging load can be expressed in matrix form:

[0080] Among them, M represents the number of electric vehicle charging loads, N represents the number of aggregated indicators, and B is the relative importance of quantitative different indicators. The entropy weight method is used to calculate the weight of each indicator, specifically:

[0081] Among them, z mn Represents the original data b of the nth aggregate indicator of the mth electric vehicle charging load mn After normalization, the data mn represents the proportion of the nth aggregate index of the mth electric vehicle charging load, e n The information entropy value of the nth electric vehicle charging load aggregation index, ω n Represents the weight of the nth electric vehicle charging load aggregation indicator.

[0082] Then the comprehensive clustering index of the mth electric vehicle charging load can be expressed as: ω n ={ω1,ω2,ω3,ω4} C m =ω1η m+ω2T m +ω3R m +ω4S m

[0083] Among them, ω1, ω2, ω3 and ω4 represent the charging efficiency, charging time, charging capacity and response rate index weights of the electric vehicle charging load respectively, C m represents the comprehensive clustering index value of the mth electric vehicle charging load; η i represents the charging efficiency of the mth electric vehicle charging load, T m represents the charging time of the mth electric vehicle charging load, R m represents the charging capacity of the mth electric vehicle charging load, S m represents the charging load response rate of the mth electric vehicle.

[0084] Specifically, the specific process of step S2.2 is as follows:

[0085] The improved fuzzy C-means clustering method is used to cluster the electric vehicle charging load and divide it into clusters. The specific steps are as follows:

[0086] First, the cluster centers c of different clusters mj The calculation formula is:

[0087] Among them, r is the neighborhood radius; j is the number of clusters, and A is the number of samples within the neighborhood radius.

[0088] Second, initialize the membership matrix U. After the tth iteration, the membership matrix after updating is: U t ={u mj}

[0089] in, It indicates the membership degree of the mth electric vehicle charging load to the jth cluster after the tth iteration, u mj ∈[0,1]; represents the value of the mth electric vehicle charging load to the jth cluster center after the tth iteration; represents the value of the charging load of the mth electric vehicle to the gth cluster center after the tth iteration, g∈[1,j];

[0090] The cluster center matrix after the tth iteration update is:

[0091] in, It represents the value of the charging load of the mth electric vehicle to the cluster center of the jth cluster after the tth iteration, and K represents the proportional coefficient;

[0092] Third, when the number of iterations reaches the set termination number or ξ represents a very small number, the iteration is terminated, and the calculation result is given; otherwise, it returns to the second step for the next round of iteration.

[0093] Specifically, the specific process of step S2.3 is as follows:

[0094] Taking into account the obvious differences in the preference for electric vehicle charging loads with different charging characteristics in different application scenarios, a combination of manual setting and entropy weight method is used to update the calculation results of different indicator weights, thereby correcting the cluster division of electric vehicle charging loads. The manual setting will be carried out according to different application scenarios, specifically as follows:

[0095] After some indicators are manually set in the above-mentioned specified scenario, the remaining indicators will be recalculated according to the entropy weight method in step S2.1, thereby updating the weight calculation results of each indicator and the cluster division results will also be updated accordingly.

[0096] Specifically, the specific process of step S4 is as follows:

[0097] The calculation formula with the lowest control cost as the objective function is:

[0098] Among them, F1 is the objective function with the lowest control cost, represents the most suitable charging capacity of the hth electric vehicle charging load in the cluster at time period t, p t represents the charging price of electric vehicle charging load in time period t, T represents the total number of time periods, the time interval is 15 minutes, T = 96, and H represents the total number of electric vehicle charging loads included in the most suitable cluster;

[0099] The calculation formula with the optimal SOC of electric vehicle charging load as the objective function is:

[0100] Among them, F2 is the optimal objective function for the electric vehicle charging load SOC, represents the state of charge value of the most suitable cluster h-th electric vehicle charging load in time period t; p t Indicates the optimal state of charge value of the electric vehicle charging load;

[0101] The optimized coordinated control model of electric vehicle charging load can be expressed as: F = αF1 + (1-α)F2

[0102] Here, α represents the synergy coefficient.

[0103] Referring to FIG2 , a second aspect of the present invention discloses a system for regulating and controlling an electric vehicle charging load for multiple application scenarios. The system is applied to the aforementioned method for regulating and controlling an electric vehicle charging load for multiple application scenarios. The system includes an application scenario identification module, a charging load dynamic clustering module, an application scenario matching module, a charging load information collection module, and a charging load control module.

[0104] The application scenario identification module is used to analyze the types of power market transactions in which the electric vehicle charging load participates and the dispatch instructions issued by the power grid, determine the specific application scenarios in which the electric vehicle charging load control system participates in the power grid interaction in the future, and upload the judgment results to the application scenario matching module;

[0105] The charging load dynamic clustering module is used to cluster the electric vehicle charging load according to clustering indicators such as charging time, charging capacity, charging efficiency and response rate, and upload the clustering results to the application scenario matching module;

[0106] The application scenario matching module is used to select the most suitable cluster of the electric vehicle charging load flexible control system to match the application scenario requirements based on the application scenario identification results and the electric vehicle charging load clustering results;

[0107] The charging load information acquisition module is used to collect and monitor information related to the operating status of the electric vehicle charging load, and upload the data to the application scenario identification module, the charging load dynamic clustering module and the charging load control module;

[0108] The charging load control module is used to receive the charging instructions decomposed by the electric vehicle charging load control system, control the charging of the electric vehicle charging load, and perceive the charging process of the electric vehicle charging load based on the operating data uploaded by the charging load information acquisition module.

[0109] 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 scope of protection of the present invention.

Claims

1. A method for regulating the charging load of electric vehicles for multiple application scenarios, characterized in that, The method includes the following steps: Step S1: According to the market participation of the electric vehicle charging load flexible regulation system and the dispatching instructions issued by the power grid, the application scenarios faced by the electric vehicle charging load regulation system are identified through the application scenario identification module, the identification results are output, and a three-level regulation system architecture is formulated; Step S2: Taking the electric vehicle charging efficiency, charging duration, charging capacity, and response rate as the key indicators of the membership function respectively, the entropy weight method is introduced to balance the relative importance of multiple indicators, and the clustering results of the electric vehicle charging load under multiple indicators are calculated to achieve the clustering division of the electric vehicle charging load; Step S3: Perform application scenario demand matching according to the application scenario identification results and the clustering division results; Step S4: Select the most suitable cluster according to the application scenario and the power grid capacity requirements. When the most suitable cluster can meet the capacity requirements of the application scenario, an optimized collaborative regulation model with the lowest regulation cost and the best SOC as the objective function is constructed; Step S5: When the most suitable cluster cannot meet the capacity requirements of the application scenario, it will automatically extend to the second most suitable cluster, and so on, until the capacity requirements of the application scenario are met, and an optimized collaborative regulation model as described in Step S4 is constructed for the electric vehicle charging load cluster that finally meets the capacity requirements; Step S6: Select the appropriate electric vehicle charging load according to the optimized collaborative regulation model.

2. The electric vehicle charging load regulation method for diversified application scenarios according to claim 1, characterized in that The application scenarios include three application scenarios: power system peak shaving, power system frequency modulation, and electric energy interaction.

3. A method for regulating the charging load of electric vehicles for multiple application scenarios according to claim 1, characterized in that, The three-level regulation system architecture includes three levels. The first level is the electric vehicle charging load flexible regulation system platform, which is used to receive the dispatching instructions issued by the power grid and forward the instructions to the next level of regulation according to the application scenario matching module. The second level is the clustering division and matching level, which is used to cluster all electric vehicles in the electric vehicle charging load flexible regulation system and select the most suitable cluster according to the corresponding scenario. The third level is the dispatching instruction decomposition level, which is used to decompose the power grid dispatching instructions within the suitable cluster.

4. A method for regulating the charging load of electric vehicles for multiple application scenarios according to claim 1, characterized in that, The specific content of Step S2 is as follows: Step S2.1: Sort out and normalize the original data of the electric vehicle charging load information collection module, extract the indicators of electric vehicle charging efficiency, charging duration, charging capacity, and response rate, and use the entropy weight method to calculate the relative importance of different indicators; Step S2.2: According to the calculation results of different indicator weights, use the improved fuzzy C-means clustering method to distinguish the similarities and differences between the charging load samples and different clustering centers, and achieve accurate clustering of different electric vehicle charging loads; Step S2.3: Dynamically correct the clustering division of the electric vehicle charging load in real time according to the application scenario identification results.

5. A method for regulating the charging load of electric vehicles for multiple application scenarios according to claim 4, characterized in that, The specific process of Step S2.1 is as follows: Extract data such as the indicators of electric vehicle charging efficiency, charging duration, charging capacity, and response rate from the electric vehicle charging load information collection module, which can be specifically expressed as: F = {η, T, R, S} Among them, F represents the set of clustering index of electric vehicle charging load; η represents the charging efficiency index of electric vehicle charging load; T represents the charging duration index of electric vehicle charging load; R represents the charging capacity index of electric vehicle charging load; S represents the response rate index of electric vehicle charging load. The original data of different indicators of the electric vehicle charging load can be represented by a matrix as follows: Among them, M represents the number of electric vehicle charging loads, N represents the number of aggregation indicators, and B quantifies the relative importance of different indicators. The entropy weight method is used to calculate the weights of each indicator, specifically as follows: Among them, z mn represents the original data b of the nth aggregation index of the mth electric vehicle charging load mn data p after normalization mn represents the proportion e of the nth aggregation index of the mth electric vehicle charging load n represents the information entropy value ω of the nth aggregation index of the electric vehicle charging load n represents the weight of the nth aggregation index of the electric vehicle charging load. Then the comprehensive clustering index of the m-th electric vehicle charging load can be expressed as: ω n = {ω1, ω2, ω3, ω4} C m = ω1η m + ω2T m + ω3R m + ω4S m Among them, ω1, ω2, ω3, and ω4 respectively represent the charging efficiency, charging duration, charging capacity, and response rate index weights of the electric vehicle charging load, C m represents the comprehensive clustering index value of the m-th electric vehicle charging load; η i represents the charging efficiency of the m-th electric vehicle charging load, T m represents the charging duration of the m-th electric vehicle charging load, R m represents the charging capacity of the m-th electric vehicle charging load, S m represents the response rate of the m-th electric vehicle charging load.

6. A method for regulating the charging load of electric vehicles for multiple application scenarios according to claim 5, characterized in that, The specific process of step S2.2 is as follows: Use the improved fuzzy C-means clustering method to cluster the electric vehicle charging load and divide it into clusters. The specific steps are as follows: First, the cluster centers c of different clusters mj The calculation formula is as follows: Among them, r is the neighborhood radius; j is the number of clusters, and A is the number of samples within the neighborhood radius. Second, initialize the membership matrix U. The membership matrix after the t-th iteration update is: U t = {u mj} Among them, Indicates the membership degree that the charging load of the m-th electric vehicle belongs to the j-th cluster after the t-th iteration; Indicates the value from the charging load of the m-th electric vehicle to the clustering center of the j-th cluster after the t-th iteration; Represents the value of the m-th electric vehicle charging load to the g-th cluster center after the t-th iteration; The cluster center matrix after the t-th iterative update is as follows: Among them, Represents the value of the m-th electric vehicle charging load to the j-th cluster center after the t-th iteration, and K represents the proportionality coefficient; Third, when the number of iterations reaches the set termination number or ξ represents a very small number, the iteration terminates, and the calculation result is output; otherwise, return to the second step for the next round of iteration.

7. A method for regulating the charging load of electric vehicles for multiple application scenarios according to claim 6, characterized in that, The specific process of step S2.3 is as follows: The calculation results of different index weights are updated by combining artificial setting with the entropy weight method, so as to correct the clustering division of the electric vehicle charging load. The artificial setting will be carried out according to different application scenarios, specifically as follows: After some indicators are artificially set in the above specified scenario, the remaining indicators will be recalculated according to the entropy weight method in step S2.1, so as to update the weight calculation results of each indicator, and the cluster division results will also be updated accordingly.

8. A method for regulating the charging load of electric vehicles for multiple application scenarios according to claim 1, characterized in that The specific process of step S4 is as follows: The calculation formula with the lowest control cost as the objective function is: Among them, F1 is the objective function with the lowest regulation cost. represents the charging capacity of the h-th electric vehicle charging load in the most suitable cluster at time period t, p t represents the charging price of the electric vehicle charging load at time period t, T represents the total number of time periods, and H represents the total number of electric vehicle charging loads included in the most suitable cluster; The calculation formula with the best SOC of the electric vehicle charging load as the objective function is as follows: Among them, F2 is the objective function for the best SOC of the electric vehicle charging load, represents the state of charge value of the h-th electric vehicle charging load in the most suitable cluster at time t; p t represents the optimal state of charge value of the electric vehicle charging load; The optimal collaborative control model of electric vehicle charging load can be expressed as: F = αF1+(1 - α)F2 Among them, α represents the collaborative coefficient.

9. A charging load regulation system for electric vehicles in multiple application scenarios, which is applied to a charging load regulation method for electric vehicles in multiple application scenarios according to any one of claims 1-8, characterized in that The system includes an application scenario identification module, a charging load dynamic clustering module, an application scenario matching module, a charging load information collection module, and a charging load control module; The application scenario identification module is used to analyze the power market trading varieties participated by the electric vehicle charging load and the dispatching instructions issued by the power grid, judge the specific application scenarios of the electric vehicle charging load regulation system participating in the power grid interaction in the next period of time, and upload the judgment results to the application scenario matching module; The charging load dynamic clustering module is used to cluster and divide the electric vehicle charging load according to clustering indexes such as charging duration, charging capacity, charging efficiency and response rate, and upload the clustering results to the application scenario matching module; The application scenario matching module is used to select the most suitable cluster of the electric vehicle charging load flexible regulation system for application scenario demand matching according to the application scenario identification result and the electric vehicle charging load clustering result; The charging load information collection module is used to collect and monitor the operation state related information of the electric vehicle charging load, and upload the data to the application scenario identification module, the charging load dynamic clustering module and the charging load control module; The charging load control module is used to receive the charging instructions decomposed by the electric vehicle charging load regulation system, control the charging of the electric vehicle charging load, and sense the state of the charging process of the electric vehicle charging load according to the operation data uploaded by the charging load information collection module.

Images