Electric vehicle cluster aggregation load prediction method and system for power distribution network

Abstract

The invention discloses an electric vehicle cluster aggregation load prediction method and system for a power distribution network. The method comprises the following steps: calculating the total number of vehicles in a charging station after charging of k parts of vehicles in the current time period is completed and the vehicles leave; calculating the SOC mean value and the standard deviation of the remaining vehicles after the charging of the k parts of vehicles in the current time period is completed and the vehicles leave; calculating the total number of vehicles after the k parts of vehicles arrive at the current time period; calculating a mean value and a variance of the combined SOC distribution of the vehicles after the k parts of the vehicles arrive at the current time period; and calculating the charging rate of each vehicle, performing maximum likelihood estimation to aggregate the vehicle load to obtain the vehicle aggregate load, and updating the SOC mean value and variance of the vehicles in the charging station after charging is completed. The invention aims to realize accurate electric vehicle charge state prediction for the power distribution network, so as to dispatch the electric vehicle for orderly charging to reduce the load fluctuation of the power distribution network and keep the voltage stable.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicles, and in particular to a method and system for predicting electric vehicle cluster aggregated load for a distribution network. Background Art

[0002] Large-scale electric vehicle access causes disordered charging. This irregular charging behavior will bring challenges to the stability of the power grid and power generation scheduling, increase the complexity of power grid management and operation, and bring great pressure to the operation of transformers in residential areas. It is urgent to study the real-time charging needs of electric vehicles in the community, cooperate with the power grid to formulate appropriate operation plans, and ensure the safe and stable operation of the power grid. Through the formulated scheduling strategy, the charging load is transferred to the low power consumption or regular time period to alleviate the impact of load fluctuations and voltage drops. The basis for electric vehicle access operation analysis, charging facility planning and other collaborative interactions is the modeling of electric vehicle charging load. At present, there are many methods for charging load fitting, including random simulation with deterministic time variables, queuing theory as the theoretical basis, building a charging demand model based on the traffic fluid model, and combining random simulation methods with multiple scenarios. These methods and models usually require some simplified assumptions. These assumptions may differ from the actual situation, which may affect the accuracy of the prediction results. Summary of the invention

[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a method and system for predicting the state of charge of an electric vehicle and orderly charging of an electric vehicle are provided. The present invention aims to achieve accurate prediction of the state of charge of an electric vehicle for a distribution network, so as to schedule electric vehicles for orderly charging to reduce load fluctuations in the distribution network and maintain voltage stability.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for predicting electric vehicle cluster aggregate load for a distribution network comprises the following steps: S1, calculate the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period; S2, calculate the SOC mean and standard deviation of the remaining vehicles after some k vehicles have completed charging and left in the current period; S3, combining the total number of vehicles at the charging station after the k-th part of the vehicles in the current period have completed charging and left, and calculating the total number of vehicles after the k-th part of the vehicles in the current period have arrived; S4, combining the SOC mean and variance of the remaining vehicles after the k-part vehicles in the current period have completed charging and left, and calculating the mean and variance of the joint SOC distribution of the vehicles after the k-part vehicles in the current period arrive; S5, calculating the charging rate of each vehicle, performing maximum likelihood estimation to aggregate the vehicle load to obtain the vehicle aggregate load, and updating the SOC mean and variance of the vehicles at the charging station after charging is completed.

[0005] Optionally, the function expression for calculating the total number of vehicles in the charging station after the k-th part of the vehicles in the current period have completed charging and left in step S1 is: , in, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, is the total number of vehicles at the previous moment k-1, is the number of vehicles leaving in the current period k.

[0006] Optionally, in step S2, the function expression for calculating the SOC mean and standard deviation of the remaining vehicles after the k-th part of the vehicles in the current period have completed charging and left is: , , in, and are the mean and standard deviation of the SOC of the i-th vehicle cluster among the remaining vehicles after the k-th vehicle has completed charging and left in the current period, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after some k vehicles have completed charging and left in the current period, is the mean SOC value of the k-1 ith vehicle cluster at the previous moment, is the departure ratio factor of the i-th vehicle cluster in the current period k, is the average SOC value of the vehicle leaving the vehicle after charging in the current period k, is the SOC variance of the k-1 ith vehicle cluster at the previous moment, is the correlation coefficient between the SOC of the vehicle leaving the current time period k and the SOC of the vehicle leaving the previous time period k-1, is the SOC standard deviation of the k-1 ith vehicle cluster at the previous moment, The SOC standard deviation of the vehicle leaving the vehicle after charging is completed in the current period k, The SOC variance of the vehicle leaving the vehicle after charging is completed in the current period k, and: , in, is the number of vehicles leaving in the current period k, and is the market share and penetration rate of the number of vehicles leaving the i-th vehicle cluster in the current period k, is the total number of vehicles at the previous moment k-1, and are the penetration rates of the k-1 ith vehicle cluster in the number of arriving vehicles and the total number of vehicles at the previous moment, It is the total number of vehicles at the charging station after some k-1 vehicles have completed charging and left at the previous moment.

[0007] Optionally, the function expression for calculating the total number of vehicles after the k-part vehicles arrive in the current time period in step S3 is: , in, is the total number of vehicles after the k-th vehicle arrives in the current period, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, is the number of vehicles arriving in the current period k.

[0008] Optionally, in step S4, the function expression for calculating the mean and variance of the joint SOC distribution of vehicles after the k-part vehicles in the current period arrive is as follows: , , in, and are the mean and variance of the joint SOC distribution of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, and are the mean and standard deviation of the SOC of the remaining vehicles after some vehicles in the i-th vehicle cluster in the current period k have completed charging and left, is the ratio of the number of arriving vehicles in the i-th vehicle cluster to the total number of vehicles in the current period k, and is the mean and standard deviation of the SOC of the arriving vehicles in the i-th vehicle cluster in the current period k, is the correlation coefficient between the arriving vehicle of the i-th vehicle cluster in the current period k and the SOC at the current time point, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after some k vehicles have completed charging and left in the current period, and there are: , in, is the number of vehicles arriving in the current period k, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, , are the market shares of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current period, , are the penetration rates of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current period k, respectively.

[0009] Optionally, the function expression for calculating the charging rate of each vehicle in step S5 is: , in, is the charging rate of the jth electric vehicle in the i-th vehicle cluster in the current period k, is the fairness factor, is the SOC value of the jth electric vehicle in the i-th vehicle cluster in the current period k after it arrives, is the scaling factor, For charging time, is a constant related to the battery capacity, and: , in, is the rated charging power, is the battery capacity; In step S5, the maximum likelihood estimation of the aggregated vehicle load is performed to obtain the functional expression of the aggregated vehicle load: , in, is the aggregated vehicle load in the current period k, is the number of electric vehicle clusters, is the fairness factor, is the mean SOC value after the i-th vehicle cluster arrives in the current period k, is the mean SOC value of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, is the proportion of the i-th vehicle cluster in the total number of vehicles, yes The cumulative distribution function of is the updated joint SOC distribution of the i-th vehicle cluster in the current period k, is the scaling factor, is the battery capacity, For charging time; The function expressions of the mean and variance of the SOC of the vehicles at the charging station after the charging is completed in step S5 are as follows: , , in, and are the mean and variance of the joint SOC distribution at the next moment k+1, and are the mean and variance of the joint SOC distribution of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, yes The cumulative distribution function of is the updated joint SOC distribution of the i-th vehicle cluster in the current period k, is the fairness factor, is the scaling factor, is the time step.

[0010] Optionally, after step S5, the method further includes adjusting the real-time electricity price of the charging station according to the real-time electricity price model of the charging station shown in the following formula to guide the electric vehicle to charge: , In the above formula, is the electricity price in the current period k, is the fixed part of the electricity price in the current period k, and is the weight parameter, is the relative voltage level, The mean square error of regional charging station load is: , , In the above formula, is the node voltage of the charging station in the current period k, is the total number of time periods in a day, The number of electric vehicles counted in a day, is the aggregated vehicle load in the current period k, It is the average of the aggregated vehicle load in each time period.

[0011] In addition, the present invention also provides an electric vehicle cluster aggregated load forecasting system for a distribution network, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network.

[0012] In addition, the present invention also provides a computer-readable storage medium, in which a computer program or instruction is stored, and the computer program or instruction is programmed or configured to execute the electric vehicle cluster aggregate load forecasting method for the distribution network through a processor.

[0013] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network through a processor.

[0014] Compared with the prior art, the present invention mainly has the following advantages: the electric vehicle cluster aggregate load prediction method for distribution network of the present invention includes collecting the historical data of the state of charge of electric vehicles (EV) in residential areas, constructing a probabilistic day-ahead prediction model for charging load, and using the maximum likelihood method to estimate the parameters in the model, such as the mean and variance of the state of charge (SOC) consumption, the charging request rate, etc., which has a high accuracy in predicting the electric vehicle load, and realizes accurate prediction of the state of charge of electric vehicles for distribution network, so as to schedule electric vehicles for orderly charging to reduce the load fluctuation of distribution network and maintain voltage stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0016] Figure 2 Schematic diagram of a real-time electricity price-guided electric vehicle charging strategy in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] The electric vehicle cluster aggregate load forecasting method for the distribution network of this embodiment first collects the historical data of the state of charge of electric vehicles (EVs) in residential areas, considers the dynamics of the combined state of charge (SOC) distribution of the electric vehicle cluster, and charges any electric vehicle in the population with a lower SOC at a higher rate, thereby ensuring the fairness of charging, and vice versa. Furthermore, a probabilistic day-ahead forecasting model for charging load is constructed based on the dynamic SOC changes; then, the maximum likelihood method is used to estimate the parameters in the model, such as the mean and variance of the SOC consumption, the charging request rate, etc. The combined SOC distribution change from one time point to the next is determined by estimating the parameters, thereby achieving accurate electric vehicle state of charge forecasting for the distribution network, which can be used to schedule electric vehicles for orderly charging to reduce load fluctuations in the distribution network and maintain voltage stability. Figure 1 As shown, the electric vehicle cluster aggregate load prediction method for a distribution network in this embodiment includes the following steps: S1, calculate the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period; S2, calculate the SOC mean and standard deviation of the remaining vehicles after some k vehicles have completed charging and left in the current period; S3, combining the total number of vehicles at the charging station after the k-th part of the vehicles in the current period have completed charging and left, and calculating the total number of vehicles after the k-th part of the vehicles in the current period have arrived; S4, combining the SOC mean and variance of the remaining vehicles after the k-part vehicles in the current period have completed charging and left, and calculating the mean and variance of the joint SOC distribution of the vehicles after the k-part vehicles in the current period arrive; S5, calculating the charging rate of each vehicle, performing maximum likelihood estimation to aggregate the vehicle load to obtain the vehicle aggregate load, and updating the SOC mean and variance of the vehicles at the charging station after charging is completed.

[0019] The charging station is connected to the electric vehicle battery management system through the charging pile, or monitors its state of charge (SOC) by measuring the output / input power. The power can be estimated from the measured voltage and current according to the standard BS EN 61851. The function expression for calculating the total number of vehicles in the charging station after the k vehicles in the current period have completed charging and left in step S1 of this embodiment is: , in, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, is the total number of vehicles at the previous moment k-1, is the number of vehicles leaving in the current period k.

[0020] In step S2 of this embodiment, the function expression for calculating the SOC mean and standard deviation of the remaining vehicles after the k-th part of the vehicles in the current period have completed charging and left is: , , in, and are the mean and standard deviation of the SOC of the i-th vehicle cluster among the remaining vehicles after the k-th vehicle has completed charging and left in the current period, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after some k vehicles have completed charging and left in the current period, is the mean SOC value of the k-1 ith vehicle cluster at the previous moment, is the departure ratio factor of the i-th vehicle cluster in the current period k, is the average SOC value of the vehicle leaving the vehicle after charging in the current period k, is the SOC variance of the k-1 ith vehicle cluster at the previous moment, is the correlation coefficient between the SOC of the vehicle leaving the current time period k and the SOC of the vehicle leaving the previous time period k-1, is the SOC standard deviation of the k-1 ith vehicle cluster at the previous moment, The SOC standard deviation of the vehicle leaving the vehicle after charging is completed in the current period k, The SOC variance of the vehicle leaving after charging is completed in the current period k, and there is a leaving proportional factor, that is, the ratio of the leaving vehicle to the total number of vehicles. The calculation function expression is: , in, is the number of vehicles leaving in the current period k, and is the market share and penetration rate of the number of vehicles leaving the i-th vehicle cluster in the current period k, is the total number of vehicles at the previous moment k-1, and are the penetration rates of the k-1 ith vehicle cluster in the number of arriving vehicles and the total number of vehicles at the previous moment, It is the total number of vehicles at the charging station after some k-1 vehicles have completed charging and left at the previous moment.

[0021] In step S3 of this embodiment, the function expression for calculating the total number of vehicles after the arrival of k vehicles in the current time period is: , in, is the total number of vehicles after the k-th vehicle arrives in the current period, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, is the number of vehicles arriving in the current period k.

[0022] In step S4 of this embodiment, the function expression for calculating the mean and variance of the joint SOC distribution of vehicles after the k-part vehicles in the current period have arrived is as follows: , , in, and are the mean and variance of the joint SOC distribution of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, and are the mean and standard deviation of the SOC of the remaining vehicles after some vehicles in the i-th vehicle cluster in the current period k have completed charging and left, is the ratio of the number of arriving vehicles in the i-th vehicle cluster to the total number of vehicles in the current period k, and is the mean and standard deviation of the SOC of the arriving vehicles in the i-th vehicle cluster in the current period k, is the correlation coefficient between the arriving vehicle of the i-th vehicle cluster in the current period k and the SOC at the current time point, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after some k vehicles have completed charging and left in the current period, and there are: , in, is the number of vehicles arriving in the current period k, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, , are the market shares of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current period, , are the penetration rates of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current period k, respectively.

[0023] The function expression for calculating the charging rate of each vehicle in step S5 of this embodiment is: , in, is the charging rate of the jth electric vehicle in the i-th vehicle cluster in the current period k, is the fairness factor, is the SOC value of the jth electric vehicle in the i-th vehicle cluster in the current period k after it arrives, is the scaling factor, For charging time, is a constant related to the battery capacity, and: , in, is the rated charging power, is the battery capacity; the “ " indicates the state of the vehicle after arrival, the i in the subscript is the index number of the electric vehicle cluster, the k in the subscript is the time sequence number, and the j in the subscript is usually used to indicate a specific electric vehicle (EV) individual; an electric vehicle cluster refers to a certain type of electric vehicle, such as an electric vehicle brand, an electric vehicle of an operational nature, etc., which can be classified and divided according to actual needs; In step S5, the maximum likelihood estimation of the aggregated vehicle load is performed to obtain the functional expression of the aggregated vehicle load: , in, is the aggregated vehicle load in the current period k, is the number of electric vehicle clusters, is the fairness factor, is the mean SOC value after the i-th vehicle cluster arrives in the current period k, is the mean SOC value of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, is the proportion of the i-th vehicle cluster in the total number of vehicles, yes The cumulative distribution function of is the updated joint SOC distribution of the i-th vehicle cluster in the current period k, is the scaling factor, is the battery capacity, For charging time; The function expressions of the mean and variance of the SOC of the vehicles at the charging station after the charging is completed in step S5 are as follows: , , in, and are the mean and variance of the joint SOC distribution at the next moment k+1, and are the mean and variance of the joint SOC distribution of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, yes The cumulative distribution function of is the updated joint SOC distribution of the i-th vehicle cluster in the current period k, is the fairness factor, is the scaling factor, is the time step.

[0024] The electric vehicle cluster aggregate load forecasting method used in the distribution network of this embodiment has a good guiding significance for the orderly charging scheduling of electric vehicles. By formulating a more reasonable real-time electricity price, it guides electric vehicles in residential areas to charge in an orderly manner, reduces the load fluctuation of the distribution network, and maintains voltage stability. In this embodiment, the power flow of the distribution network is calculated by predicting the charging load of electric vehicles based on historical charging data, and then the voltage level of the charging station where each node is located is evaluated. A real-time electricity price strategy is formulated based on the floating electricity price of the basic retail electricity price of the power grid considering the charging demand, and the real-time electricity price is used to guide the charging behavior of electric vehicle users in the community. Specifically, after step S5, this embodiment also includes adjusting the real-time electricity price of the charging station according to the real-time electricity price model of the charging station shown in the following formula to guide the charging of electric vehicles: , In the above formula, is the electricity price in the current period k, is the fixed part of the electricity price in the current period k, and is the weight parameter, is the relative voltage level, The mean square error of regional charging station load is: , , In the above formula, is the node voltage of the charging station in the current period k, is the total number of time periods in a day, The number of electric vehicles counted in a day, is the aggregated vehicle load in the current period k, is the average of the aggregated load of vehicles in each period. Considering the impact of load fluctuations on the stable operation of the distribution network, the floating electricity price is set with the mean square error between the node voltage level and the charging station load as the objective function. When the node voltage is higher than the average voltage level, the charging service fee is increased to make full use of the time-shifting characteristics of the flexible load and balance the load distribution of the entire network. Figure 2 Schematic diagram of the real-time electricity price-guided electric vehicle charging strategy in an embodiment of the present invention, see Figure 2 It can be seen that the charging station operator can use the real-time electricity price formulated in the previous step to formulate the charging strategy for electric vehicles. The specific strategy is: 1) The predicted vehicle aggregate load in the current period k in the city is Upload to each charging station; 2) Electric vehicles receive the operating status of each charging station in the city, including (charging price at a charging station at a certain time), (the number of charging posts in a charging station), (charging piles available in a charging station), (charging power of a charging pile in a charging station), where The value ranges from 1 to m, where m is the number of charging stations; 3) The electric vehicle pre-selects a charging station based on the operating status of the charging station and transmits the information to the charging station; 4) The charging station operator sets a strategy to consider the real-time electricity price formulated by the floating electricity price of charging demand on the basic retail electricity price of the power grid; 5) The formulated real-time dynamic electricity price will guide electric vehicles to charging stations with more available charging piles and target charging power for electric vehicles. The real-time electricity price formulated based on the stable operation of the power grid to guide the charging behavior of electric vehicles can effectively ensure the orderly charging of electric vehicles and the safety and stability of the distribution network, which is of great significance for improving the power quality of the system, reducing network losses, and enhancing the economy of system operation.

[0025] In addition, the present embodiment also provides an electric vehicle cluster aggregated load forecasting system for a distribution network, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network.

[0026] In addition, this embodiment also provides a computer-readable storage medium, in which a computer program or instruction is stored. The computer program or instruction is programmed or configured to execute the electric vehicle cluster aggregate load forecasting method for the distribution network through a processor.

[0027] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network through a processor.

[0028] Those skilled in the art should understand that the technical solutions provided by the embodiments of the present application may be in the form of methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0029] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for predicting electric vehicle cluster aggregate load for distribution network, characterized in that: The steps include: S1, calculate the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period; S2, calculate the SOC mean and standard deviation of the remaining vehicles after some k vehicles have completed charging and left in the current period; S3, combining the total number of vehicles at the charging station after the k-th part of the vehicles in the current period have completed charging and left, and calculating the total number of vehicles after the k-th part of the vehicles in the current period have arrived; S4, combining the SOC mean and variance of the remaining vehicles after the k-part vehicles in the current period have completed charging and left, and calculating the mean and variance of the joint SOC distribution of the vehicles after the k-part vehicles in the current period arrive; S5, calculating the charging rate of each vehicle, performing maximum likelihood estimation to aggregate the vehicle load to obtain the vehicle aggregate load, and updating the SOC mean and variance of the vehicles at the charging station after charging is completed.

2. The method for predicting electric vehicle cluster aggregate load for distribution network according to claim 1, characterized in that: The function expression for calculating the total number of vehicles in the charging station after the k-th vehicle in the current period has completed charging and left in step S1 is: ， in, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, is the total number of vehicles at the previous moment k-1, is the number of vehicles leaving in the current period k.

3. The electric vehicle cluster aggregate load forecasting method for distribution network according to claim 1, characterized in that: The function expression for calculating the SOC mean and standard deviation of the remaining vehicles after the k-th vehicle has completed charging and left the current period in step S2 is: ， ， in, and are the mean and standard deviation of the SOC of the i-th vehicle cluster among the remaining vehicles after the k-th vehicle has completed charging and left in the current period, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after some k vehicles have completed charging and left in the current period, is the mean SOC value of the k-1 ith vehicle cluster at the previous moment, is the departure ratio factor of the i-th vehicle cluster in the current period k, is the average SOC value of the vehicle leaving the vehicle after charging in the current period k, is the SOC variance of the k-1 ith vehicle cluster at the previous moment, is the correlation coefficient between the SOC of the vehicle leaving the current time period k and the SOC of the vehicle leaving the previous time period k-1, is the SOC standard deviation of the k-1 ith vehicle cluster at the previous moment, The SOC standard deviation of the vehicle leaving the vehicle after charging is completed in the current period k, The SOC variance of the vehicle leaving the vehicle after charging is completed in the current period k, and: ， in, is the number of vehicles leaving in the current period k, and is the market share and penetration rate of the number of vehicles leaving the i-th vehicle cluster in the current period k, is the total number of vehicles at the previous moment k-1, and are the penetration rates of the k-1 ith vehicle cluster in the number of arriving vehicles and the total number of vehicles at the previous moment, It is the total number of vehicles at the charging station after some k-1 vehicles have completed charging and left at the previous moment.

4. The method for predicting electric vehicle cluster aggregate load for distribution network according to claim 1, characterized in that: The function expression for calculating the total number of vehicles after the k-th vehicle arrives in the current time period in step S3 is: ， in, is the total number of vehicles after the k-th vehicle arrives in the current period, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, is the number of vehicles arriving in the current period k.

5. The method for predicting electric vehicle cluster aggregate load for distribution network according to claim 1, characterized in that: In step S4, the function expression for calculating the mean and variance of the joint SOC distribution of vehicles after the k-part vehicles in the current period have arrived is as follows: ， ， in, and are the mean and variance of the joint SOC distribution of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, and are the mean and standard deviation of the SOC of the remaining vehicles after some vehicles in the i-th vehicle cluster in the current period k have completed charging and left, is the ratio of the number of arriving vehicles in the i-th vehicle cluster to the total number of vehicles in the current period k, and is the mean and standard deviation of the SOC of the arriving vehicles in the i-th vehicle cluster in the current period k, is the correlation coefficient between the arriving vehicle of the i-th vehicle cluster in the current period k and the SOC at the current time point, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after some k vehicles have completed charging and left in the current period, and there are: ， in, is the number of vehicles arriving in the current period k, is the total number of vehicles at the charging station after some k vehicles have completed charging and left the charging station in the current period, , are the market shares of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current period, , are the penetration rates of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current period k, respectively.

6. The method for predicting electric vehicle cluster aggregate load for distribution network according to claim 1, characterized in that: The function expression for calculating the charging rate of each vehicle in step S5 is: ， in, is the charging rate of the jth electric vehicle in the i-th vehicle cluster in the current period k, is the fairness factor, is the SOC value of the jth electric vehicle in the i-th vehicle cluster in the current period k after it arrives, is the scaling factor, For charging time, is a constant related to the battery capacity, and: ， in, is the rated charging power, is the battery capacity; In step S5, the maximum likelihood estimation of the aggregated vehicle load is performed to obtain the functional expression of the aggregated vehicle load: ， in, is the aggregated vehicle load in the current period k, is the number of electric vehicle clusters, is the fairness factor, is the mean SOC value after the i-th vehicle cluster arrives in the current period k, is the mean SOC value of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, is the proportion of the i-th vehicle cluster in the total number of vehicles, yes The cumulative distribution function of is the updated joint SOC distribution of the i-th vehicle cluster in the current period k, is the scaling factor, is the battery capacity, For charging time; The function expressions of the mean and variance of the SOC of the vehicles at the charging station after the charging is completed in step S5 are as follows: ， ， in, and are the mean and variance of the joint SOC distribution at the next moment k+1, and are the mean and variance of the joint SOC distribution of the vehicles in the i-th vehicle cluster in the current period k after the vehicle arrives, yes The cumulative distribution function of is the updated joint SOC distribution of the i-th vehicle cluster in the current period k, is the fairness factor, is the scaling factor, is the time step.

7. The method for predicting electric vehicle cluster aggregate load for distribution network according to claim 1, characterized in that: After step S5, the method further includes adjusting the real-time electricity price of the charging station according to the real-time electricity price model of the charging station shown in the following formula to guide the electric vehicle to charge: ， In the above formula, is the electricity price in the current period k, is the fixed part of the electricity price in the current period k, and is the weight parameter, is the relative voltage level, The mean square error of regional charging station load is: ， ， In the above formula, is the node voltage of the charging station in the current period k, is the total number of time periods in a day, The number of electric vehicles counted in a day, is the aggregated vehicle load in the current period k, It is the average of the aggregated vehicle load in each time period.

8. An electric vehicle cluster aggregate load forecasting system for a distribution network, comprising an interconnected microprocessor and a memory, characterized in that: The microprocessor is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network as described in any one of claims 1 to 7 through a processor.

10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a distribution network as described in any one of claims 1 to 7 through a processor.

Images