An intelligent management system and method for electric vehicle charging load balancing

Abstract

The present invention discloses an intelligent management system and method for electric vehicle charging load balancing, which relates to the field of charging load balancing management. It includes obtaining the battery pack type characteristics of different models of electric vehicles and establishing a battery pack type characteristic library for electric vehicles; obtaining the charging time of electric vehicles to be charged and establishing a charging time matrix of electric vehicles to be charged in the whole region; setting the rated power and the number of electric vehicle charging devices in this region; determining the fuzzy comprehensive evaluation matrix of the battery pack state of electric vehicles to be charged; establishing a fuzzy neural network comprehensive evaluation model for the battery pack state of electric vehicles to be charged; and establishing a human-computer interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles. The advantages of the present invention are as follows: effectively evaluating the operation of electric vehicle charging in the whole region, reasonably allocating the optimal charging power and charging time to each charging electric vehicle, thereby improving the charging efficiency and ensuring the stable operation of the regional power grid.

Description

Technical Field

[0001] The present invention relates to the field of charging load balancing management, and specifically to an intelligent management system and method for electric vehicle charging load balancing. Background Art

[0002] With the increase in the number and demand of electric vehicles, the requirement for the grid expansion capacity of the area where electric vehicle charging devices are set is getting higher and higher. When the number and charging power of electric vehicle charging devices are unbalanced, due to the untimely grid expansion and deficiencies, problems such as power supply shortage and voltage instability will occur, thus affecting the normal electricity use of residents. Therefore, when setting electric vehicle charging devices, it is necessary to reasonably plan the layout and quantity of charging piles according to the actual situation of the community and electricity demand. At the same time, considering the status of different types of electric vehicle battery packs, optimizing the intelligent management of electric vehicle charging load balancing will be of great significance.

[0003] The existing electric vehicle charging device technology mainly focuses on charging electric vehicles throughout the day with a fixed charging power. However, such a method lacks a comprehensive analysis and evaluation of the regional electricity demand and electric vehicle charging power, as well as a comprehensive distribution of the charging power of different types of electric vehicle battery packs to be charged, resulting in problems such as power supply shortage and voltage instability during peak electricity consumption periods, thus affecting the normal electricity use of residents. Summary of the Invention

[0004] To solve the above technical problems, an intelligent management system and method for electric vehicle charging load balancing are provided. This technical solution solves the problems of the lack of comprehensive analysis and evaluation of regional electricity demand and electric vehicle charging power, as well as the comprehensive distribution of the charging power of different types of electric vehicle battery packs to be charged, resulting in problems such as power supply shortage and voltage instability during peak electricity consumption periods, thus affecting the normal electricity use of residents as mentioned in the above background art.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] An intelligent management method for electric vehicle charging load balancing, characterized by comprising:

[0007] Based on big data, obtain the type characteristics of electric vehicle battery packs of different models and establish a type characteristic library of electric vehicle battery packs;

[0008] According to the ampere-hour integration method, obtain the charging time of the electric vehicle to be charged and establish a charging time matrix of all electric vehicles to be charged in the whole region;

[0009] According to the actual demand situation of the area where the electric vehicle charging device is set, set the rated power and the number of electric vehicle charging devices in this area;

[0010] According to the fuzzy comprehensive evaluation algorithm, determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged;

[0011] Based on the neural network algorithm, combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged;

[0012] Establish a human-computer interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles.

[0013] Preferably, the obtaining of the battery pack type characteristics of different models of electric vehicles based on big data and the establishment of a battery pack type characteristic library of electric vehicles specifically include:

[0014] Based on big data, extract the battery pack type characteristics of different models of electric vehicles, and determine the change range of the battery pack type characteristics of different models of electric vehicles according to the factory information of the battery packs of different models of electric vehicles;

[0015] The battery pack type characteristics of different models of electric vehicles include: rated voltage, battery capacity, maximum input current, charging power, maximum input power, and limited temperature;

[0016] According to the change range of the battery pack type characteristics of different models of electric vehicles, according to the normalization formula, perform dimension elimination and normalization processing on the battery pack type characteristic data of different models of electric vehicles;

[0017] Classify and organize the battery pack type characteristic data of different models of electric vehicles after normalization processing, and establish a battery pack type characteristic library of electric vehicles;

[0018] The normalization formula is:

[0019] In the formula, is the battery pack type characteristic data of different models of electric vehicles after normalization, is the original data of the battery pack type characteristics of different models of electric vehicles, is the mean value of the original data of the battery pack type characteristics of different models of electric vehicles, is the standard deviation of the original data of the battery pack type characteristics of different models of electric vehicles.

[0020] Preferably, the obtaining of the charging time of the electric vehicle to be charged according to the ampere-hour integration method and the establishment of a charging time matrix of all-region electric vehicles to be charged specifically include:

[0021] Set up a hardware reading device for the battery pack state of the electric vehicle to be charged to obtain the state information of the battery pack of the electric vehicle to be charged;

[0022] Obtain the battery usage and remaining power of the battery pack of the electric vehicle to be charged according to the usage of the battery pack of the electric vehicle to be charged;

[0023] Obtain the power to be charged of the battery pack of the electric vehicle to be charged according to the battery usage and remaining power of the battery pack of the electric vehicle to be charged;

[0024] Determine the charging time to be charged of the battery pack of the electric vehicle to be charged according to the ampere-hour integration method and in combination with the power to be charged of the battery pack of the electric vehicle to be charged;

[0025] Obtain the charging time to be charged of all electric vehicles to be charged in the whole area according to the charging time to be charged of the battery pack of the electric vehicle to be charged, and establish a matrix of the charging time to be charged of all electric vehicles to be charged in the whole area;

[0026] The expression of the ampere-hour integration method is:

[0027] In the formula, is the state of charge of the battery pack of the charging electric vehicle at the th moment, is the value of the power of the initial state of charge, is the total capacity of the battery pack of the charging electric vehicle, is the charging current of the battery pack of the charging electric vehicle at the th moment, is the charging time of the battery pack of the charging electric vehicle.

[0028] Preferably, the setting of the rated power and the number of electric vehicle charging devices in this area according to the actual demand situation of the area where the electric vehicle charging device is set specifically includes:

[0029] Obtain the actual power consumption and power demand in different time periods of this area according to the actual demand situation of the area where the electric vehicle charging device is set;

[0030] Set the rated power and the number of electric vehicle charging devices in this area according to the power consumption of the area where the electric vehicle charging device is to be set, in combination with the specifications and standards for setting the electric vehicle charging device;

[0031] Based on the power consumption of the area where the electric vehicle charging device is to be set, initially set the initial value of the rated charging power for each electric vehicle charging device on average.

[0032] Based on big data, set the highest rated charging power threshold for electric vehicle charging in different time periods.

[0033] Preferably, the determination of the fuzzy comprehensive evaluation matrix of the state of the battery pack of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm specifically includes:

[0034] Determine the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm based on the battery pack type characteristics of electric vehicles of different models, the matrix of charging times of electric vehicles to be charged in the entire area, and the maximum rated charging power thresholds for charging electric vehicles in different time periods;

[0035] Determine the fuzzy subset of the battery pack state of the electric vehicle to be charged according to the ordered pair representation method expression;

[0036] Determine the fuzzy subset of the battery pack state of the electric vehicle to be charged according to the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm membership function;

[0037] Based on big data analysis, set the important weights of different data in the battery pack type characteristics of electric vehicles of different models, the matrix of charging times of electric vehicles to be charged in the entire area, and the maximum rated charging power thresholds for charging electric vehicles in different time periods ;

[0038] According to the universe of discourse of the battery pack state of the electric vehicle to be charged , membership degree and the important weights of different data , establish a fuzzy comprehensive evaluation matrix for the battery pack state of the electric vehicle to be charged;

[0039] The relational expression of the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm is:

[0040] In the formula, is the fuzzy subset of the battery pack state of the electric vehicle to be charged, referring to the set of all data of the battery pack type characteristics of electric vehicles of different models, the matrix of charging times of electric vehicles to be charged in the entire area, and the maximum rated charging power thresholds for charging electric vehicles in different time periods, is the universe of discourse of the fuzzy subset , is the membership function of the fuzzy subset , is the element value in the fuzzy subset , is 's membership degree to the fuzzy subset , that is, the membership degree, is the interval range of the universe of discourse;

[0041] The expression of the fuzzy subset of the battery pack state of the electric vehicle to be charged is:

[0042] In the formula, is the th element value in the fuzzy subset , is a fuzzy subset in the degree of membership of the th element value

[0043] The fuzzy subset of the state of the battery pack of the electric vehicle to be charged has a membership function as follows:

[0044] In the formula, , are parameters for evaluating the boundary value of the state of the battery pack of the electric vehicle to be charged

[0045] Preferably, the establishment of a fuzzy neural network comprehensive evaluation model for the state of the battery pack of the electric vehicle to be charged based on the neural network algorithm and combined with the fuzzy comprehensive evaluation matrix of the state of the battery pack of the electric vehicle to be charged specifically includes:

[0046] Normalize the data in the matrix according to the fuzzy comprehensive evaluation matrix of the state of the battery pack of the electric vehicle to be charged;

[0047] Use the normalized data of the fuzzy comprehensive evaluation matrix of the state of the battery pack of the electric vehicle to be charged as the input matrix of the neural network algorithm model;

[0048] Based on big data, establish a training sample set and a target sample set in combination with the data of the fuzzy comprehensive evaluation matrix of the state of the battery pack of the electric vehicle to be charged;

[0049] Establish a fuzzy neural network comprehensive evaluation model for the state of the battery pack of the electric vehicle to be charged, and combine the training sample set and the target sample set to screen out the optimal charging power and charging duration of the electric vehicle to be charged.

[0050] Preferably, the establishment of a human-computer interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles specifically includes:

[0051] Establish a human-computer interaction platform for building the hardware environment for the operation of the fuzzy neural network comprehensive evaluation model of the state of the battery pack of the electric vehicle to be charged;

[0052] Based on the human-computer interaction platform, it is convenient for users to obtain the status of the electric vehicle charging device and the charging situation of the electric vehicle through the display interface;

[0053] Based on the human-computer interaction platform, it is used to update and optimize the parameters and sample data of the fuzzy neural network comprehensive evaluation model of the state of the battery pack of the electric vehicle to be charged;

[0054] Based on the human-computer interaction platform, it is used to receive and feedback user experience and feedback to ensure good interoperability of electric vehicle charging.

[0055] Furthermore, this solution proposes an intelligent management system for electric vehicle charging load balancing, which is used to implement the intelligent management method for electric vehicle charging load balancing as described above, including:

[0056] A feature extraction module, which is used to obtain the battery pack type features of different models of electric vehicles based on big data and establish a battery pack type feature library for electric vehicles;

[0057] A hardware setting module, which is used to set the rated power and the number of electric vehicle charging devices in this area according to the actual demand situation of the area where the electric vehicle charging device is set;

[0058] An optimal charging module, which is used to obtain the charging time of the electric vehicle to be charged according to the ampere-hour integration method and establish a charging time matrix for all electric vehicles to be charged in the area; determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm; based on the neural network algorithm, combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged;

[0059] An interaction platform module, which is used to establish a human-machine interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles.

[0060] Preferably, the optimal charging module includes:

[0061] A global charging time unit, which is used to obtain the charging time of the electric vehicle to be charged according to the ampere-hour integration method and establish a charging time matrix for all electric vehicles to be charged in the area;

[0062] A state evaluation unit, which is used to determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm;

[0063] An optimal charging unit, which is used to establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged based on the neural network algorithm and combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged.

[0064] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0065] By obtaining the battery pack type characteristics of different models of electric vehicles, normalizing the battery pack type characteristics of different models of electric vehicles, and obtaining the status information of the battery pack of the electric vehicle to be charged, based on the ampere-hour integration method, the charging time of the electric vehicle to be charged is calculated, so as to determine the charging time of all-region electric vehicles to be charged. Secondly, through the fuzzy comprehensive evaluation algorithm, according to the battery pack type characteristics of different models of electric vehicles, the charging time matrix of all-region electric vehicles to be charged, and the data of the maximum rated charging power threshold of electric vehicle charging in different time periods, the fuzzy comprehensive evaluation of the battery pack status of the electric vehicle to be charged is carried out, and a fuzzy comprehensive evaluation matrix of the battery pack status of the electric vehicle to be charged is established. Finally, based on the neural network algorithm, combined with the fuzzy comprehensive evaluation matrix of the battery pack status of the electric vehicle to be charged, a fuzzy neural network comprehensive evaluation model of the battery pack status of the electric vehicle to be charged is established, and the optimal charging power and charging duration of the electric vehicle to be charged are screened out, so as to effectively evaluate the operation of all-region electric vehicle charging, reasonably allocate the optimal charging power and charging time for each charging electric vehicle, thereby improving the charging efficiency, ensuring the stable operation of the regional power grid, and avoiding problems such as power supply shortage and voltage instability during peak electricity consumption periods. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flowchart of an intelligent management method for load balancing of electric vehicle charging according to the present invention;

[0067] Figure 2 It is a flowchart of obtaining the charging time of an electric vehicle to be charged according to the ampere-hour integration method and establishing a charging time matrix of all-region electric vehicles to be charged according to the present invention;

[0068] Figure 3 It is a flowchart of determining a fuzzy comprehensive evaluation matrix of the battery pack status of an electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0069] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0070] Refer to Figure 1 As shown, an intelligent management method for load balancing of electric vehicle charging includes:

[0071] Based on big data, obtain the battery pack type characteristics of different models of electric vehicles and establish a battery pack type characteristic library of electric vehicles;

[0072] According to the ampere-hour integration method, obtain the charging time of the electric vehicle to be charged and establish a charging time matrix of all-region electric vehicles to be charged;

[0073] Set the rated power of the area and the number of electric vehicle charging devices according to the actual demand of the area where the electric vehicle charging device is set;

[0074] Determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm;

[0075] Based on the neural network algorithm, combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged;

[0076] Establish a human-computer interaction platform for querying, reserving, displaying and updating the queuing information and charging information of electric vehicles.

[0077] It can be explained that this solution obtains the battery pack type characteristics of different models of electric vehicles, normalizes the battery pack type characteristics of different models of electric vehicles, and obtains the state information of the battery pack of the electric vehicle to be charged. Based on the ampere-hour integration method, calculates the charging time of the electric vehicle to be charged, so as to determine the charging time of all electric vehicles to be charged in the whole area. Secondly, through the fuzzy comprehensive evaluation algorithm, according to the battery pack type characteristics of different models of electric vehicles, the charging time matrix of all electric vehicles to be charged in the whole area and the data of the highest rated charging power threshold for electric vehicle charging in different time periods, conduct a fuzzy comprehensive evaluation of the battery pack state of the electric vehicle to be charged, and establish a fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged. Finally, based on the neural network algorithm, combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged, screen out the optimal charging power and charging duration of the electric vehicle to be charged, so as to effectively evaluate the operation of electric vehicle charging in the whole area and reasonably allocate the optimal charging power and charging time to each charging electric vehicle.

[0078] Refer to Figure 2 As shown, the specific steps of obtaining the charging time of the electric vehicle to be charged according to the ampere-hour integration method and establishing the charging time matrix of all electric vehicles to be charged in the whole area include:

[0079] Set the hardware reading device for the battery pack state of the electric vehicle to be charged to obtain the state information of the battery pack of the electric vehicle to be charged;

[0080] According to the usage of the battery pack of the electric vehicle to be charged, obtain the battery usage and remaining power of the battery pack of the electric vehicle to be charged;

[0081] According to the battery usage and remaining power of the battery pack of the electric vehicle to be charged, obtain the power to be charged of the battery pack of the electric vehicle to be charged;

[0082] According to the ampere-hour integration method, combined with the power to be charged of the battery pack of the electric vehicle to be charged, determine the charging time of the battery pack of the electric vehicle to be charged;

[0083] Obtain the waiting charging times of all waiting charging electric vehicles in the whole area according to the waiting charging time of the battery pack of the electric vehicle to be charged, and establish a waiting charging time matrix of all waiting charging electric vehicles in the whole area;

[0084] The expression of the ampere-hour integration method is as follows:

[0085] In the formula, is the state of charge of the battery pack of the charging electric vehicle at the th moment, is the power value of the initial state of charge, is the total capacity of the battery pack of the charging electric vehicle, is the charging current of the battery pack of the charging electric vehicle at the th moment, is the charging time of the battery pack of the charging electric vehicle.

[0086] It can be explained that when considering the charging load balance of electric vehicles, it is necessary to start from the overall situation and comprehensively consider the charging situations of all charging electric vehicles and the regional power consumption situation. On the premise of ensuring the stable regional power consumption, through reasonable allocation, preferentially configure reasonable charging power, and efficiently and distributedly complete the charging arrangement of all-region electric vehicles. This solution determines the waiting charging time of the battery pack of the electric vehicle to be charged by reading the status information of the battery pack of the electric vehicle to be charged, according to the ampere-hour integration method, combined with the waiting charging power of the battery pack of the electric vehicle to be charged, so as to determine the comprehensive evaluation data in terms of the waiting charging time.

[0087] Referring to Figure 3 as shown, the fuzzy comprehensive evaluation matrix for determining the state of the battery pack of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm specifically includes:

[0088] Determine the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm according to the type characteristics of the battery packs of different models of electric vehicles, the waiting charging time matrix of all waiting charging electric vehicles in the whole area, and the maximum rated charging power threshold for electric vehicle charging in different time periods;

[0089] Determine the expression of the fuzzy subset of the state of the battery pack of the electric vehicle to be charged according to the ordered pair representation method;

[0090] Determine the membership function of the fuzzy subset of the state of the battery pack of the electric vehicle to be charged according to the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm;

[0091] Based on big data analysis, set the important weights of different data in the type characteristics of the battery packs of different models of electric vehicles, the waiting charging time matrix of all waiting charging electric vehicles in the whole area, and the maximum rated charging power threshold for electric vehicle charging in different time periods ;

[0092] According to the universe of discourse of the battery pack state of the electric vehicle to be charged , membership degree and the importance weights of different data , establish a fuzzy comprehensive evaluation matrix for the battery pack state of the electric vehicle to be charged;

[0093] The relational expression of the fuzzy subset and membership degree of the fuzzy comprehensive evaluation algorithm is:

[0094] In the formula, is the fuzzy subset of the battery pack state of the electric vehicle to be charged, referring to the set of all data of the battery pack type characteristics of electric vehicles of different models, the matrix of the charging time of all electric vehicles to be charged in the whole region, and the maximum rated charging power threshold of electric vehicle charging in different time periods, is the universe of discourse of the fuzzy subset , is the membership function of the fuzzy subset , is the element value in the fuzzy subset , is 's membership degree to the fuzzy subset , that is, the membership degree, is the interval range of the universe of discourse;

[0095] The expression of the fuzzy subset of the battery pack state of the electric vehicle to be charged is:

[0096] In the formula, is the -th element value in the fuzzy subset , is the -th element value in the fuzzy subset , 's membership degree to ;

[0097] The membership function of the fuzzy subset of the battery pack state of the electric vehicle to be charged is:

[0098] In the formula, , are parameters for evaluating the boundary value of the battery pack state of the electric vehicle to be charged.

[0099] It can be explained that conventional neural network models require a large amount of training sample data and target sample data for support. For the types of electric vehicle charging battery packs that are uncertain, conventional neural network models are prone to overfitting, resulting in inaccurate model judgments. Therefore, in this solution, by adding a fuzzy comprehensive evaluation algorithm, through setting and limiting the data of the characteristics of different models of electric vehicle battery packs, the full-region waiting time matrix of electric vehicles to be charged, and the maximum rated charging power thresholds for electric vehicle charging at different time periods in the early stage, the comprehensive evaluation interval of the data is expanded, the robustness and adaptability of the model are improved, thereby effectively improving the acceptability and adaptability to different types of electric vehicle charging battery packs and reducing the overfitting phenomenon.

[0100] Furthermore, based on the same inventive concept as the above intelligent management method for electric vehicle charging load balancing, this solution proposes an intelligent management system for electric vehicle charging load balancing, including:

[0101] A feature extraction module, which is used to obtain the characteristics of different models of electric vehicle battery packs based on big data and establish a feature library of electric vehicle battery pack types;

[0102] A hardware setting module, which is used to set the rated power and the number of electric vehicle charging devices in this area according to the actual demand situation of the electric vehicle charging device area;

[0103] An optimal charging module, which is used to obtain the waiting time of electric vehicles to be charged according to the ampere-hour integration method and establish a full-region waiting time matrix of electric vehicles to be charged; according to the fuzzy comprehensive evaluation algorithm, determine the fuzzy comprehensive evaluation matrix of the state of the electric vehicle battery pack to be charged; based on the neural network algorithm, combine the fuzzy comprehensive evaluation matrix of the state of the electric vehicle battery pack to be charged to establish a fuzzy neural network comprehensive evaluation model of the state of the electric vehicle battery pack to be charged;

[0104] An interaction platform module, which is used to establish a human-machine interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles;

[0105] The optimal charging module includes:

[0106] A global charging time unit, which is used to obtain the waiting time of electric vehicles to be charged according to the ampere-hour integration method and establish a full-region waiting time matrix of electric vehicles to be charged;

[0107] A state evaluation unit, which is used to determine the fuzzy comprehensive evaluation matrix of the state of the electric vehicle battery pack to be charged according to the fuzzy comprehensive evaluation algorithm;

[0108] Optimal charging unit, which is used to establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged based on the neural network algorithm and combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged.

[0109] In summary, the advantages of the present invention are as follows: it can effectively evaluate the operation of electric vehicle charging in the whole region, reasonably allocate the optimal charging power and charging time for each charging electric vehicle, thereby improving the charging efficiency, ensuring the stable operation of the regional power grid, and avoiding problems such as power supply shortage and voltage instability during peak electricity consumption periods.

[0110] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent management method for electric vehicle charging load balancing, characterized in that, Including: Based on big data, obtain the battery pack type characteristics of different models of electric vehicles, and establish a battery pack type characteristic library for electric vehicles; According to the ampere-hour integration method, obtain the charging time of the electric vehicle to be charged, and establish a charging time matrix of electric vehicles to be charged in the whole area; According to the actual demand situation of setting the electric vehicle charging device area, set the rated power and the number of electric vehicle charging devices in this area; According to the fuzzy comprehensive evaluation algorithm, determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged; Based on the neural network algorithm, combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged; Establish a human-computer interaction platform for querying, reserving, displaying and updating the queuing information and charging information of electric vehicles.

2. The intelligent management method for electric vehicle charging load balancing according to claim 1, characterized in that The specific steps of obtaining the battery pack type characteristics of different models of electric vehicles based on big data and establishing a battery pack type characteristic library for electric vehicles include: Based on big data, extract the battery pack type characteristics of different models of electric vehicles, and determine the change range of the battery pack type characteristics of different models of electric vehicles according to the factory information of the battery packs of different models of electric vehicles; The battery pack type characteristics of different models of electric vehicles include: rated voltage, battery capacity, maximum input current, charging power, maximum input power and limited temperature; According to the change range of the battery pack type characteristics of different models of electric vehicles, according to the normalization formula, eliminate the dimension and normalize the battery pack type characteristic data of different models of electric vehicles; Classify and sort out the normalized battery pack type characteristic data of different models of electric vehicles, and establish a battery pack type characteristic library for electric vehicles; The normalization formula is: In the formula, is the normalized characteristic data of the battery pack types of different models of electric vehicles, is the original data of the battery pack type characteristics of different models of electric vehicles, is the mean value of the original data of the battery pack type characteristics of different models of electric vehicles, is the standard deviation of the original data of the battery pack type characteristics of different models of electric vehicles.

3. An intelligent management method for electric vehicle charging load balancing according to claim 2, characterized in that, The specific steps of obtaining the charging time of the electric vehicle to be charged according to the ampere-hour integration method and establishing a charging time matrix of electric vehicles to be charged in the whole area include: Set the hardware reading device for the battery pack state of the electric vehicle to be charged, and obtain the state information of the battery pack of the electric vehicle to be charged; According to the usage of the battery pack of the electric vehicle to be charged, obtain the battery usage and remaining power of the battery pack of the electric vehicle to be charged; According to the battery usage and remaining power of the battery pack of the electric vehicle to be charged, obtain the charging power of the battery pack of the electric vehicle to be charged; According to the ampere-hour integration method, combined with the charging power of the battery pack of the electric vehicle to be charged, determine the charging time of the battery pack of the electric vehicle to be charged; According to the charging time of the battery pack of the electric vehicle to be charged, obtain the charging time of electric vehicles to be charged in the whole area, and establish a charging time matrix of electric vehicles to be charged in the whole area; The expression of the ampere-hour integration method is: In the formula, For charging electric vehicle battery packs The state of charge at the moment, is the charge value of the initial state of charge, is the total capacity of the battery pack for charging electric vehicles, For charging electric vehicle batteries The charging current at the moment, Charging time for charging electric vehicle battery packs.

4. An intelligent management method for electric vehicle charging load balancing according to claim 3, characterized in that, The specific steps of setting the rated power and the number of electric vehicle charging devices in this area according to the actual demand situation of setting the electric vehicle charging device area include: According to the actual demand situation of setting the electric vehicle charging device area, obtain the actual power consumption and power demand of different time periods in this area; According to the power consumption of the area where the electric vehicle charging device is to be set, combined with the specifications and standards of setting the electric vehicle charging device, set the rated power and the number of electric vehicle charging devices in this area; Combine the electricity consumption of the area where the electric vehicle charging device is to be set, and set the initial value of the rated charging power for each electric vehicle charging device on average; Based on big data, set the maximum rated charging power threshold for electric vehicle charging in different time periods.

5. The intelligent management method for load balancing of electric vehicle charging according to claim 4, characterized in that, The specific steps of determining the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm include: Determine the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm according to the battery pack type characteristics of different models of electric vehicles, the matrix of the charging time of all electric vehicles to be charged in the whole area, and the maximum rated charging power threshold for electric vehicle charging in different time periods; Determine the fuzzy subset of the battery pack state of the electric vehicle to be charged according to the ordered pair representation method expression; Determine the membership function of the fuzzy subset of the battery pack of the electric vehicle to be charged according to the fuzzy subset and membership degree of the fuzzy comprehensive evaluation algorithm ; Based on big data analysis, set the important weights of different data in the battery pack type characteristics of electric vehicles of different models, the matrix of the waiting charging time of electric vehicles to be charged in the whole region, and the maximum rated charging power threshold for electric vehicle charging in different time periods ; According to the universe of discourse of the state of the battery pack of the electric vehicle to be charged , membership degree and the important weights of different data , establish a fuzzy comprehensive evaluation matrix for the state of the battery pack of the electric vehicle to be charged; The relational expression of the fuzzy subsets and membership degrees of the fuzzy comprehensive evaluation algorithm is: In the formula, is a fuzzy subset of the state of the battery pack of the electric vehicle to be charged, referring to the set of all data of the battery pack type characteristics of electric vehicles of different models, the matrix of the charging time of all electric vehicles to be charged in the whole area, and the highest rated charging power threshold of electric vehicles charging in different time periods, is the fuzzy subset of the universe of discourse, is the fuzzy subset of the membership function, is the fuzzy subset in the element value, is of the fuzzy subset of the degree of membership, that is, the membership degree, is the interval range of the universe of discourse; The fuzzy subset of the state of the electric vehicle battery pack to be charged is expressed as: In the formula, is the -th element value in the fuzzy subset ; is the -th element value in the fuzzy subset ; and The fuzzy subset of the state of the electric vehicle battery pack to be charged has the following membership function: In the formula, , are parameters for evaluating the state boundary value of the battery pack of the electric vehicle to be charged.

6. The intelligent management method for load balancing of electric vehicle charging according to claim 5, characterized in that, The specific steps of establishing a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged based on the neural network algorithm and combining the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged include: According to the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, perform normalization processing on the data in the matrix; Use the normalized data of the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged as the input matrix of the neural network algorithm model; Based on big data, combine the data of the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged, and establish a training sample set and a target sample set; Establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged, and combine the training sample set and the target sample set to screen out the optimal charging power and charging duration of the electric vehicle to be charged.

7. The intelligent management method for load balancing of electric vehicle charging according to claim 6, characterized in that, The specific steps of establishing a human-computer interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles include: Establish a human-computer interaction platform for building the hardware environment for the operation of the fuzzy neural network comprehensive evaluation model of the battery pack state of the electric vehicle to be charged; Based on the human-computer interaction platform, it is convenient for users to obtain the status of the electric vehicle charging device and the charging situation of the electric vehicle through the display interface; Based on the human-computer interaction platform, it is used to update and optimize the parameters and sample data of the fuzzy neural network comprehensive evaluation model of the battery pack state of the electric vehicle to be charged; Based on the human-computer interaction platform, it is used to receive and feedback user experience and feedback, and ensure good interoperability of electric vehicle charging.

8. An intelligent management system for load balancing of electric vehicle charging, characterized in that, For implementing the intelligent management method for electric vehicle charging load balancing as described in any one of claims 1-7, including: A feature extraction module, which is used to obtain the battery pack type characteristics of different models of electric vehicles based on big data and establish a battery pack type characteristic library of electric vehicles; A hardware setting module, which is used to set the rated power and the number of electric vehicle charging devices in this area according to the actual demand situation of the area where the electric vehicle charging device is set; An optimal charging module, which is used to obtain the charging time of the electric vehicle to be charged according to the ampere-hour integration method and establish a matrix of the charging time of all electric vehicles to be charged in the whole area; determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm; establish a fuzzy neural network comprehensive evaluation model for the battery pack state of the electric vehicle to be charged based on the neural network algorithm and combining the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged; An interaction platform module, which is used to establish a human-machine interaction platform for querying, reserving, displaying, and updating the queuing information and charging information of electric vehicles.

9. The intelligent management system for load balancing of electric vehicle charging according to claim 8, characterized in that, The optimal charging module includes: A global charging time unit, which is used to obtain the charging time of the electric vehicle to be charged according to the ampere-hour integration method and establish a matrix of the charging times of all electric vehicles to be charged in the whole area; A state evaluation unit, which is used to determine the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged according to the fuzzy comprehensive evaluation algorithm; An optimal charging unit, which is used to establish a fuzzy neural network comprehensive evaluation model of the battery pack state of the electric vehicle to be charged based on the neural network algorithm and combined with the fuzzy comprehensive evaluation matrix of the battery pack state of the electric vehicle to be charged.

Images