An electric vehicle cluster aggregated load prediction method and system for a power distribution network

Abstract

The application discloses a kind of electric vehicle cluster aggregation load prediction method and system for power distribution network, the present application includes calculating the total vehicle number of charging station after part vehicle charging is completed and leaves in current period k;The mean and standard deviation of the SOC of remaining vehicle after part vehicle charging is completed and leaves in current period k are calculated;The total vehicle number after part vehicle arrives in current period k is calculated;The mean and variance of the joint SOC distribution of vehicle after part vehicle arrives in current period k are calculated;The charging rate of each vehicle is calculated, the maximum likelihood estimation aggregation vehicle load is obtained vehicle aggregation load, and the mean and variance of the SOC of vehicle after charging is completed are updated.Charging station.The present application aims to accurately predict the state of charge of electric vehicle for power distribution network, to schedule electric vehicle for orderly charging to reduce power distribution network load fluctuation and maintain voltage stability.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of electric vehicles, in particular to an electric vehicle cluster aggregated load prediction method and system for a power distribution network. BACKGROUND

[0002] Large-scale electric vehicle access causes disordered charging, and such 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 demand of electric vehicles in residential areas and develop appropriate operation plans in coordination with the power grid to ensure the safe and stable operation of the power grid. Through the developed scheduling strategy, the charging load is transferred to the low electricity consumption valley or the regular period, to alleviate the impact of load fluctuation and voltage drop. The analysis of electric vehicle grid operation, the planning of charging facilities and other collaborative interactions are based on the modeling of electric vehicle charging load. At present, there are various methods for fitting charging load, such as random simulation based on deterministic time variables, queuing theory as the theoretical basis, constructing charging demand models based on traffic flow models, and methods combining multi-scenario random simulation. These methods and models usually need to make some simplified assumptions. These assumptions may differ from the actual situation, thus affecting the accuracy of the prediction results. SUMMARY

[0003] The technical problem to be solved by the present application is to provide an electric vehicle state of charge prediction and electric vehicle orderly charging method and system to solve the above problems in the prior art. The present application aims to accurately predict the state of charge of electric vehicles for a power distribution network, to schedule electric vehicles for orderly charging to reduce power distribution network load fluctuations and maintain voltage stability.

[0004] To solve the above technical problems, the technical scheme adopted by the present application is:

[0005] An electric vehicle cluster aggregated load prediction method for a power distribution network, comprising the following steps:

[0006] S1, calculating the total number of vehicles at the charging station after the partial vehicles in the current period k complete charging and leave;

[0007] S2, calculating the mean and standard deviation of the SOC of the remaining vehicles after the partial vehicles in the current period k complete charging and leave;

[0008] S3, calculating the total number of vehicles after the partial vehicles in the current period k arrive, in combination with the total number of vehicles at the charging station after the partial vehicles in the current period k complete charging and leave;

[0009] S4, calculating the mean and variance of the joint SOC distribution of the vehicles after the partial vehicles in the current period k arrive, in combination with the mean and variance of the SOC of the remaining vehicles after the partial vehicles in the current period k complete charging and leave.

[0010] S5, calculate the charging rate of each vehicle, aggregate the vehicle load by maximum likelihood estimation to obtain the vehicle aggregated load, and update the mean and variance of the SOC of the vehicle at the charging station after charging is completed.

[0011] Optionally, the function expression for calculating the total number of vehicles at the charging station after the partial vehicles have left after charging is completed in step S1 is:

[0012] ,

[0013] wherein, is the total number of vehicles at the charging station after the partial vehicles have left after charging is completed in the current time period k, is the total number of vehicles in the last time period k-1, is the number of vehicles that have left in the current time period k.

[0014] Optionally, the function expression for calculating the mean and standard deviation of the SOC of the remaining vehicles after the partial vehicles have left after charging is completed in step S2 is:

[0015] ,

[0016] ,

[0017] wherein, and are the mean and standard deviation of the SOC of the i-th vehicle cluster among the remaining vehicles after the partial vehicles have left after charging is completed in the current time period k, is the SOC variance of the i-th vehicle cluster among the remaining vehicles after the partial vehicles have left after charging is completed in the current time period k, is the mean of the SOC of the i-th vehicle cluster in the last time period k-1, is the departure proportion factor of the i-th vehicle cluster in the current time period k, is the mean of the SOC of the vehicle that has left after charging is completed in the current time period k, is the SOC variance of the i-th vehicle cluster in the last time period k-1, is the correlation coefficient between the SOC of the vehicle that has left in the current time period k and the SOC in the last time period k-1, is the standard deviation of the SOC of the i-th vehicle cluster in the last time period k-1, is the standard deviation of the SOC of the vehicle that has left after charging is completed in the current time period k, is the SOC variance of the vehicle that has left after charging is completed in the current time period k, and has:

[0018] ,

[0019] wherein, is the number of vehicles that have left in the current time period k, and is the market share and penetration rate of the i-th vehicle cluster in the current time period k, is the total number of vehicles at the last time period k-1, and are the penetration rates of the i-th vehicle cluster in the total number of vehicles and the number of arriving vehicles at the last time period k-1, respectively, is the total number of vehicles at the charging station after the partial vehicles leave after charging at the last time period k-1.

[0020] Optionally, the function expression for calculating the total number of vehicles after the partial vehicles arrive in the current time period k in step S3 is:

[0021] ,

[0022] wherein, is the total number of vehicles after the partial vehicles arrive in the current time period k, is the total number of vehicles at the charging station after the partial vehicles leave after charging in the current time period k, is the number of vehicles arriving in the current time period k.

[0023] Optionally, the function expression for calculating the mean and variance of the joint SOC distribution of the vehicles after the partial vehicles arrive in the current time period k in step S4 is:

[0024] ,

[0025] ,

[0026] wherein, and are the mean and variance of the joint SOC distribution of the vehicles after the partial vehicles arrive in the current time period k, and are the mean and standard deviation of the SOC of the remaining vehicles after the partial vehicles leave after charging in the current time period k, is the proportion of the arriving vehicles of the i-th vehicle cluster relative to the total number of vehicles in the current time period k, and are the mean and standard deviation of the SOC of the arriving vehicles of the i-th vehicle cluster in the current time period k, is the correlation coefficient between the arriving vehicles and the SOC at the current time point of the i-th vehicle cluster in the current time period k, is the SOC variance of the i-th vehicle cluster in the remaining vehicles after the partial vehicles leave after charging in the current time period k, and has:

[0027] ,

[0028] in, Let k be the number of vehicles that arrive in the current time period. This represents the total number of vehicles at the charging station after the k-group of vehicles have finished charging and left during the current time period. , These represent the market share of the i-th vehicle cluster in the current time period k, in terms of the number of arriving vehicles and the total number of vehicles, respectively. , These represent the penetration rates of the i-th vehicle cluster in the current time period k in terms of the number of arriving vehicles and the total number of vehicles, respectively.

[0029] Optionally, the functional expression for calculating the charging rate of each vehicle in step S5 is:

[0030] ,

[0031] in, Let $\frac{i}{j}$ be the charging rate of the $j$-th electric vehicle in the $i$-th vehicle cluster at the current time period. As a fairness factor, Let SOC be the value of the j-th electric vehicle in the i-th vehicle cluster during the current time period k after its arrival. Scale factor For charging time, Let be a constant related to battery capacity, and we have:

[0032] ,

[0033] in, Rated charging power, Battery capacity;

[0034] In step S5, the maximum likelihood estimation is performed to aggregate the vehicle load, and the functional expression for the aggregated vehicle load is as follows:

[0035] ,

[0036] in, This represents the aggregated vehicle load for the current time period k. For the number of electric vehicle clusters, As a fairness factor, Let SOC be the average value of the i-th vehicle cluster after arrival in the current time period k. Let SOC be the average value of the vehicles in the i-th vehicle cluster after the arrival of the vehicles in the current time period k. Let be the proportion of the i-th vehicle cluster in the total number of vehicles. yes The cumulative distribution function, Let be the joint SOC distribution updated for the i-th vehicle cluster in the current time period k. is a scale factor, is the battery capacity, is the charging time;

[0037] The function expression for updating the mean and variance of the SOC of the charging station vehicles after the completion of charging in step S5 is:

[0038] ,

[0039] ,

[0040] wherein, and are the mean and variance of the joint SOC distribution at the next time k+1, and are the mean and variance of the joint SOC distribution of the vehicles after the vehicle arrives in the ith vehicle cluster in the current period k, is the cumulative distribution function of , is the updated joint SOC distribution of the ith vehicle cluster in the current period k, is a fairness factor, is a scale factor, is a time step.

[0041] Optionally, after step S5, the real-time electricity price of the charging station is adjusted to guide the charging of electric vehicles according to the real-time electricity price model of the charging station shown by the following formula:

[0042] ,

[0043] 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 are weight parameters, is the relative voltage level, is the regional charging station load mean square error, and has:

[0044] ,

[0045] ,

[0046] In the above formula, is the node voltage of the charging station in the current period k, is the total number of periods in a day, is the number of electric vehicles counted in a day, is the vehicle aggregated load in the current period k, is the mean of the vehicle aggregated load of each period.

[0047] Further, the present application also provides an electric vehicle cluster aggregated load prediction system for a power distribution network, comprising a microprocessor and a memory connected to each other, the microprocessor being programmed or configured to execute the electric vehicle cluster aggregated load prediction method for a power distribution network.

[0048] Further, the present application also provides a computer readable storage medium, wherein a computer program or instructions are stored, the computer program or instructions being programmed or configured to execute the electric vehicle cluster aggregated load prediction method for a power distribution network by a processor.

[0049] Further, the present application also provides a computer program product, comprising a computer program or instructions, the computer program or instructions being programmed or configured to execute the electric vehicle cluster aggregated load prediction method for a power distribution network by a processor.

[0050] Compared with the prior art, the present application mainly has the following advantages: the electric vehicle cluster aggregated load prediction method for a power distribution network of the present application comprises collecting electric vehicle (EV) state of charge historical data of a residential community, constructing a charging load probabilistic day-ahead prediction model, and estimating parameters in the model such as mean and variance of state of charge (SOC) consumption, charging request rate, etc. by using maximum likelihood method, so that the predicted electric vehicle load has higher accuracy, and the state of charge of the electric vehicle is accurately predicted for a power distribution network, so as to schedule the electric vehicle for orderly charging to reduce power distribution network load fluctuation and maintain voltage stability. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 It is a basic flowchart of the method of the embodiment of the present application.

[0052] Figure 2 It is a schematic diagram of the real-time electricity price guided electric vehicle charging strategy in the embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor fall within the scope of protection of the present application.

[0054] The electric vehicle cluster aggregation load prediction method for power distribution network of the embodiment first collects the state of charge historical data of electric vehicles (EV) in residential areas, considers the dynamic nature of the combined state of charge (SOC) distribution of electric vehicle clusters, 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. Further, a probabilistic day-ahead prediction model of charging load is constructed according to the dynamic SOC change; then, the parameters in the model, such as the mean and variance of the SOC consumption, the charging request rate, etc., are estimated by the maximum likelihood method, and the combined SOC distribution change from one time point to the next time point is determined by estimating the parameters, so as to accurately predict the state of charge of electric vehicles for the power distribution network, so as to schedule electric vehicles for orderly charging to reduce the load fluctuation of the power distribution network and maintain voltage stability. As shown in Figure 1 The electric vehicle cluster aggregation load prediction method for power distribution network of the embodiment includes the following steps:

[0055] S1, calculating the total number of vehicles at the charging station after the partial vehicles in the current time period k complete charging and leave;

[0056] S2, calculating the mean and standard deviation of the SOC of the remaining vehicles after the partial vehicles in the current time period k complete charging and leave;

[0057] S3, calculating the total number of vehicles after the partial vehicles in the current time period k arrive, in combination with the total number of vehicles at the charging station after the partial vehicles in the current time period k complete charging and leave;

[0058] S4, calculating the mean and variance of the joint SOC distribution of the vehicles after the partial vehicles in the current time period k arrive, in combination with the mean and variance of the SOC of the remaining vehicles after the partial vehicles in the current time period k complete charging and leave;

[0059] S5, calculating the charging rate of each vehicle, performing maximum likelihood estimation to aggregate the vehicle load to obtain the vehicle aggregation load, and updating the mean and variance of the SOC of the vehicles at the charging station after charging is completed.

[0060] The charging station accesses the electric vehicle battery management system through the charging pile, or monitors the 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 functional expression for calculating the total number of vehicles at the charging station after the partial vehicles in the current time period k complete charging and leave in step S1 of the embodiment is:

[0061]

[0062] wherein, is the total number of vehicles at the charging station after the partial vehicles in the current time period k complete charging and leave, is the total number of vehicles at the last time k-1.​ the number of vehicles leaving in the current time period k.

[0063] The function expression for calculating the mean and standard deviation of the SOC of the remaining vehicles after the vehicles leaving after charging completion in the current time period k in step S2 of the embodiment is:

[0064]

[0065]

[0066] wherein, and are the mean and standard deviation of the SOC of the i-th vehicle cluster among the remaining vehicles after the vehicles leaving after charging completion in the current time period k, is the variance of the SOC of the i-th vehicle cluster among the remaining vehicles after the vehicles leaving after charging completion in the current time period k, is the mean of the SOC of the i-th vehicle cluster at the previous time k-1, is the leaving proportion factor of the i-th vehicle cluster in the current time period k, is the mean of the SOC of the vehicles leaving after charging completion in the current time period k, is the variance of the SOC of the i-th vehicle cluster at the previous time k-1, is the correlation coefficient between the SOC of the vehicles leaving in the current time period k and the SOC at the previous time k-1, is the standard deviation of the SOC of the i-th vehicle cluster at the previous time k-1, is the standard deviation of the SOC of the vehicles leaving after charging completion in the current time period k, is the variance of the SOC of the vehicles leaving after charging completion in the current time period k, and has a leaving proportion factor, i.e., the proportion of the leaving vehicles relative to the total vehicles, and the function expression for calculating the leaving proportion factor is:

[0067]

[0068] wherein, is the number of vehicles leaving in the current time period k, and are the market share and penetration rate of the number of vehicles leaving of the i-th vehicle cluster in the current time period k, is the total number of vehicles at the previous time k-1, and are the penetration rates of the i-th vehicle cluster among the number of arriving vehicles and the total number of vehicles at the previous time k-1, is the total number of vehicles at the charging station after the vehicles leaving after charging completion in the previous time k-1.

[0069] The function expression for calculating the total number of vehicles after the vehicles arriving in the current time period k in step S3 of the embodiment is: ​​​

[0070] ,

[0071] wherein, is the total number of vehicles after the arrival of the partial vehicles in the current time period k, is the total number of vehicles at the charging station after the departure of the partial vehicles that have completed charging in the current time period k, is the number of vehicles that arrive in the current time period k.

[0072] The function expression of the mean and variance of the joint SOC distribution of the vehicles after the arrival of the partial vehicles in the current time period k is calculated in step S4 of the embodiment in combination with the mean and variance of the SOCs of the remaining vehicles after the departure of the partial vehicles that have completed charging in the current time period k, and is as follows:

[0073] ,

[0074] ,

[0075] wherein, and are the mean and variance of the joint SOC distribution of the vehicles after the arrival of the i-th vehicle cluster in the current time period k, and are the mean and standard deviation of the SOCs of the remaining vehicles of the i-th vehicle cluster after the departure of the partial vehicles that have completed charging in the current time period k, is the proportion of the arriving vehicles of the i-th vehicle cluster in the current time period k relative to the total vehicles, and are the mean and standard deviation of the SOCs of the arriving vehicles of the i-th vehicle cluster in the current time period k, is the correlation coefficient between the arriving vehicles of the i-th vehicle cluster in the current time 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 the departure of the partial vehicles that have completed charging in the current time period k, and has:

[0076] ,

[0077] wherein, is the number of vehicles that arrive in the current time period k, is the total number of vehicles at the charging station after the departure of the partial vehicles that have completed charging in the current time period k, , are the market share of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current time period k, , are the penetration rate of the i-th vehicle cluster in the number of arriving vehicles and the total number of vehicles in the current time period k.

[0078] The function expression for calculating the charging rate of each vehicle in step S5 of the embodiment is:

[0079] ,

[0080] wherein, is the charging rate of the jth electric vehicle in the ith vehicle cluster in the current time period k, is a fairness factor, is the SOC value of the jth electric vehicle in the ith vehicle cluster in the current time period k after the vehicle arrives, is a scaling factor, is the charging time, is a constant related to the battery capacity, and has:

[0081] ,

[0082] wherein, is the rated charging power, is the battery capacity; the superscript “ ” represents the state after the vehicle arrives, the subscript i is the index number of the electric vehicle cluster, the subscript k is the time sequence number, and the subscript j is usually used to represent a specific electric vehicle (EV) individual; the electric vehicle cluster refers to a certain type of electric vehicle, such as an electric vehicle brand, an electric vehicle of a certain operational nature, etc., which can be classified and divided according to actual needs;

[0083] The function expression for obtaining the vehicle aggregated load by maximum likelihood estimation in step S5 is:

[0084] ,

[0085] wherein, is the vehicle aggregated load in the current time period k, is the number of electric vehicle clusters, is a fairness factor, is the average SOC value of the ith vehicle cluster after the vehicle arrives in the current time period k, is the average SOC value of the vehicle after the vehicle arrives in the ith vehicle cluster in the current time period k, is the proportion of the ith vehicle cluster in the total number of vehicles, is the cumulative distribution function of , is the updated joint SOC distribution of the ith vehicle cluster in the current time period k, is a scaling factor, is the battery capacity, is the charging time;

[0086] The function expression for updating the mean and variance of the SOC of the charging station vehicle after the completion of step S5 is:

[0087] ,

[0088] ,

[0089] wherein, and are the mean and variance of the joint SOC distribution at the next time k+1, and are the mean and variance of the joint SOC distribution of the vehicles after the vehicle arrives in the i-th vehicle cluster in the current time period k, is the cumulative distribution function of , is the updated joint SOC distribution of the i-th vehicle cluster in the current time period k, is a fairness factor, is a scaling factor, is a time step.

[0090] The electric vehicle cluster aggregation load prediction method for the power distribution network in the embodiment has good guiding significance for the scheduling of orderly charging of electric vehicles. By formulating a more reasonable real-time electricity price, the orderly charging of electric vehicles in a residential community is guided, the load fluctuation of the distribution network is reduced, and the voltage stability is maintained. In the embodiment, the electric vehicle charging load predicted based on historical charging data is used to calculate the power flow of the power distribution network, and then the voltage level of each node at the charging station is evaluated. The floating electricity price considering the charging demand is used to formulate a real-time electricity price strategy on the basis of the basic retail electricity price of the power grid, and the real-time electricity price is used to guide the charging behavior of the electric vehicle users in the community. Specifically, the embodiment 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 charging of electric vehicles after step S5:

[0091] ,

[0092] In the above formula, is the electricity price in the current time period k, is the fixed part of the electricity price in the current time period k, and are weight parameters, is the relative voltage level, is the regional charging station load mean square deviation, and

[0093] ,

[0094] ,

[0095] In the above formula, Let k be the node voltage of the charging station in the current time period. This represents the total number of time periods within a day. This represents the number of electric vehicles counted in a single day. This represents the aggregated vehicle load for the current time period k. This represents the average aggregated vehicle load across different time periods. Considering the impact of load fluctuations on the stable operation of the distribution network, a floating electricity price is set using the mean square difference 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 fully utilize the time-shiftable characteristics of flexible loads and balance the load distribution across the entire network. Figure 2 This is a schematic diagram of the real-time electricity price-guided electric vehicle charging strategy in an embodiment of the present invention. See also... Figure 2 It can be seen that charging station operators can use the real-time electricity price established in the previous steps to formulate electric vehicle charging strategies. The specific strategies are: 1) Aggregate the predicted vehicle load in the city for the current time period k. 1) Upload data to each charging station; 2) Electric vehicles receive the operational status of each charging station in the city, including... (Charging price at a certain charging station at a certain time) (Number of charging piles in a certain charging station) (Available charging piles at a certain charging station) (Charging power of charging piles in a certain charging station), among which The value ranges from 1 to m, where m is the number of charging stations; 3) Electric vehicles pre-select a charging station based on its operational status and transmit this information to the charging station; 4) Charging station operators set a real-time electricity price based on a floating price that considers charging demand on top of the grid's basic retail electricity price; 5) The set real-time dynamic electricity price guides electric vehicles to charging stations with more available charging piles and higher target charging power. The real-time electricity price, based on the stable operation of the power grid, guides the charging behavior of electric vehicles, effectively ensuring the orderly charging of electric vehicles and the safety and stability of the distribution network. This is of great significance for improving the power quality of the system, reducing network losses, and enhancing the economic efficiency of system operation.

[0096] Furthermore, this embodiment also provides an electric vehicle cluster aggregated load forecasting system for a power distribution network, including a microprocessor and a memory interconnected, wherein the microprocessor is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for a power distribution network.

[0097] Furthermore, this embodiment also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute the electric vehicle cluster aggregation load forecasting method for a power distribution network via a processor.

[0098] In addition, the embodiment further provides a computer program product comprising a computer program or instructions programmed or configured to execute the method for aggregated load forecasting of an electric vehicle cluster of a power distribution network by a processor.

[0099] Those skilled in the art will understand that the technical solutions provided by the embodiments of the present application can be in the form of a method, a system or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in 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 code. The present application is described with reference to 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 flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, 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 produce a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0100] The above description is only the preferred embodiments of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical solutions falling within the concept of the present application shall be considered as falling within the protection scope of the present application. It should be noted that, for those skilled in the art, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A method for predicting aggregated loads of electric vehicle clusters in a power distribution network, characterized in that, Includes the following steps: S1, calculate the total number of vehicles at the charging station after the k-part vehicles have finished charging and left during the current time period; S2, calculate the mean and standard deviation of the SOC of the remaining vehicles after the k vehicles have finished charging and left during the current time period; S3, combined with the total number of vehicles at the charging station after the k-part vehicles have finished charging and left during the current time period, calculate the total number of vehicles after the k-part vehicles arrive during the current time period; S4. Combine the mean and variance of the SOC of the remaining vehicles after the k-part vehicles have finished charging and left during the current time period, and calculate the mean and variance of the joint SOC distribution of the vehicles after the k-part vehicles arrive during the current time period. S5, calculate the charging rate of each vehicle, perform maximum likelihood estimation to aggregate the vehicle load to obtain the aggregated vehicle load, and update the mean and variance of the SOC of the vehicles at the charging station after charging is completed. In step S2, the function expression for calculating the mean and standard deviation of the SOC of the remaining vehicles after the current period's k-part vehicles have finished charging and left is: ， ， in, and Let SOC be the mean and standard deviation of the i-th vehicle cluster among the remaining vehicles after k vehicles have finished charging and left during the current time period. Let SOC variance be the variance of the i-th vehicle cluster among the remaining vehicles after k vehicles have finished charging and left during the current time period. Let SOC be the mean value of the i-th vehicle cluster at time k-1 in the previous time step. This represents the departure rate factor for the i-th vehicle cluster in the current time period k. The average SOC (State of Charge) of the vehicle after charging is completed and the vehicle leaves during the current time period k. Let Variance be the SOC variance of the i-th vehicle cluster at time k-1 in the previous time step. This is the correlation coefficient between the vehicle leaving at time k and the SOC at time k-1 in the previous time period. Let SOC be the standard deviation of the i-th vehicle cluster at time k-1 in the previous time step. The standard deviation of the State of Charge (SOC) for the current time period k when the vehicle leaves after charging is complete. Let SOC variance be the sum of charges (SOC) of vehicles leaving the vehicle after charging is complete in the current time period k, and we have: ， in, Let k be the number of vehicles that left during the current time period. and Let's consider the market share and penetration rate of the number of vehicles leaving the i-th vehicle cluster in the current time period k. Let k-1 be the total number of vehicles at the previous time step. and These represent the penetration rates of the i-th vehicle cluster at time k-1 in terms of the number of arriving vehicles and the total number of vehicles, respectively. The total number of vehicles at the charging station after some vehicles (k-1) have finished charging and left at the previous time step.

2. The method for predicting aggregated loads of electric vehicle clusters in a power distribution network according to claim 1, characterized in that, The function expression for calculating the total number of vehicles at the charging station after the k groups of vehicles have finished charging and left during the current time period in step S1 is as follows: ， in, This represents the total number of vehicles at the charging station after the k-group of vehicles have finished charging and left during the current time period. Let k-1 be the total number of vehicles at the previous time step. This represents the number of vehicles that left during the current time period k.

3. The method for predicting aggregated loads of electric vehicle clusters in a power distribution network according to claim 1, characterized in that, The function expression for calculating the total number of vehicles after the arrival of k vehicles in the current time period in step S3 is as follows: ， in, This represents the total number of vehicles after the arrival of the k-group of vehicles in the current time period. This represents the total number of vehicles at the charging station after the k-group of vehicles have finished charging and left during the current time period. Let k be the number of vehicles that arrive in the current time period k.

4. The method for predicting aggregated loads of electric vehicle clusters in a power distribution network according to claim 1, characterized in that, In step S4, combining the mean and variance of the SOC of the remaining vehicles after the k groups of vehicles have finished charging and left during the current time period, the functional expression for calculating the mean and variance of the joint SOC distribution of the vehicles after the arrival of the k groups of vehicles in the current time period is as follows: ， ， in, and Let be the mean and variance of the joint SOC distribution of the i-th vehicle cluster in the current time period k after the arrival of the vehicles. and Let Si be the mean and standard deviation of the SOC of the remaining vehicles after some vehicles in the i-th vehicle cluster have finished charging and left during the current time period k. Let i be the proportion of arriving vehicles in the i-th vehicle cluster relative to the total number of vehicles in the current time period k. and Let SOC be the mean and standard deviation of the arriving vehicles in the i-th vehicle cluster during the current time period k. Let be the correlation coefficient between the arriving vehicles of the i-th vehicle cluster in the current time period k and the SOC at the current time point. Let SOC variance be the variance of the i-th vehicle cluster among the remaining vehicles after k vehicles have finished charging and left during the current time period, and we have: ， in, Let k be the number of vehicles that arrive in the current time period. This represents the total number of vehicles at the charging station after the k-group of vehicles have finished charging and left during the current time period. , These represent the market share of the i-th vehicle cluster in the current time period k, in terms of the number of arriving vehicles and the total number of vehicles, respectively. , These represent the penetration rates of the i-th vehicle cluster in the current time period k in terms of the number of arriving vehicles and the total number of vehicles, respectively.

5. The method for predicting aggregated loads of electric vehicle clusters in a power distribution network according to claim 1, characterized in that, The functional expression for calculating the charging rate of each vehicle in step S5 is as follows: ， in, Let $\frac{i}{j}$ be the charging rate of the $j$-th electric vehicle in the $i$-th vehicle cluster at the current time period. As a fairness factor, Let SOC be the value of the j-th electric vehicle in the i-th vehicle cluster during the current time period k after its arrival. Scale factor For charging time, Let be a constant related to battery capacity, and we have: ， in, Rated charging power, Battery capacity; In step S5, the maximum likelihood estimation is performed to aggregate the vehicle load, and the functional expression for the aggregated vehicle load is as follows: ， in, This represents the aggregated vehicle load for the current time period k. For the number of electric vehicle clusters, As a fairness factor, Let SOC be the average value of the i-th vehicle cluster after arrival in the current time period k. Let SOC be the average value of the vehicles in the i-th vehicle cluster after the arrival of the vehicles in the current time period k. Let be the proportion of the i-th vehicle cluster in the total number of vehicles. yes The cumulative distribution function, Let be the joint SOC distribution updated for the i-th vehicle cluster in the current time period k. Scale factor For battery capacity, This refers to charging time; The functional expressions for updating the mean and variance of the SOC of vehicles at the charging station after charging is completed in step S5 are as follows: ， ， in, and Let be the mean and variance of the joint SOC distribution at the next time step k+1, respectively. and Let be the mean and variance of the joint SOC distribution of the i-th vehicle cluster in the current time period k after the arrival of the vehicles. yes The cumulative distribution function, Let be the joint SOC distribution updated for the i-th vehicle cluster in the current time period k. As a fairness factor, Scale factor For time step.

6. The method for predicting aggregated loads of electric vehicle clusters in a power distribution network according to claim 1, characterized in that, Step S5 is followed by 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 electric vehicle charging: ， In the above formula, Let k be the electricity price for the current time period. This represents the fixed portion of the electricity price for the current time period k. and For weight parameters, Relative voltage level, The load variance of the regional charging stations is as follows: ， ， In the above formula, Let k be the node voltage of the charging station in the current time period. This represents the total number of time periods within a day. This represents the number of electric vehicles counted in a single day. This represents the aggregated vehicle load for the current time period k. This represents the average aggregate load of vehicles across different time periods.

7. A power grid electric vehicle cluster aggregation load forecasting system for power distribution networks, comprising interconnected microprocessors and memory, characterized in that, The microprocessor is programmed or configured to execute the electric vehicle cluster aggregated load forecasting method for distribution networks as described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the electric vehicle cluster aggregation load forecasting method for a distribution network as described in any one of claims 1 to 6.

9. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the electric vehicle cluster aggregation load forecasting method for a distribution network as described in any one of claims 1 to 6.

Images