Charging station electrical load prediction method and system

Abstract

The invention discloses a charging station electrical load prediction method and system, and relates to the field of charging station load prediction. The problems that the energy storage capacity in the station building stage is not matched due to inaccurate energy consumption prediction numerical values in the prior art are solved. The method comprises the following steps: collecting related parameter data such as the existing single-day charging service order quantity and an address building area; predicting the load of the charging station in the address building area through the collected parameter data, and determining the coefficient value of the peak-period electricity price K1; predicting a station building condition and a charging station load in a proposed station building scale, and determining a coefficient value of a valley electricity price K2; predicting the load of the charging station of the step electricity price, and determining a K3 coefficient value of the flat electricity price; based on the prediction of the charging station load of the step electricity price, the average score of the peak, valley and flat section electricity prices is determined, the coefficient values K1 to K3 are determined through the average score and in combination with the score coefficient table, and the electricity load prediction of the charging station is completed. And optimizing the above predictions, and determining the optimal charging station electrical load prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of charging station load prediction, and in particular to a charging station power load prediction method and system. Background Art

[0002] Charging stations play an important role in the field of new energy. With the advancement of technology and policy support, the application scenarios of new energy services such as photovoltaics, charging, and battery replacement in charging stations need to optimize energy distribution and use through intelligent management systems. The accuracy of energy consumption prediction values ​​plays a decisive role in the photovoltaic and energy storage operation strategies of the site. At this stage, due to inaccurate energy consumption prediction values, there is a mismatch in energy storage capacity during the site construction stage, and there is a phenomenon of abandoned light in the pre-storage stage of energy storage devices in the application stage. It has not been fully integrated with the photovoltaic system, resulting in high operating costs for the energy storage system. Summary of the invention

[0003] The present invention aims to solve the problems in the prior art of inaccurate energy consumption prediction values, mismatched energy storage capacity in the station construction stage, abandoned light in the pre-storage stage of energy storage devices in the application stage, and failure to fully integrate with the photovoltaic system, resulting in high operating costs of the energy storage system. To solve the above technical problems, the present invention is implemented through the following technical solutions:

[0004] Solution 1: The present invention proposes a method for predicting the power load of a charging station, characterized in that the method comprises:

[0005] By collecting and analyzing the existing daily charging service order volume, the order volume and the parameters related to the site area, service vehicle type, and road traffic flow, a method for predicting the power load of the existing charging stations is constructed;

[0006] The prediction method comprises the following steps:

[0007] Step 1: Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic flow;

[0008] Step 2: Use the relevant parameter data collected in step 1 to predict the load of the charging station in the construction area and determine the coefficient value of the peak electricity price K1;

[0009] Step 3: Based on the relevant parameter data collected in step 1, the station construction conditions and the load of the charging station within the planned station construction scale are predicted to determine the coefficient value of the valley electricity price K2;

[0010] Step 4: Use the relevant parameter data collected in step 1 to predict the load of the charging station with tiered electricity prices and determine the K3 coefficient value of the flat electricity price;

[0011] Step 5: Based on steps 1 to 4, predict the load of the charging station with tiered electricity prices, determine the average score of peak, valley, and flat electricity prices, and determine the coefficient values ​​of K1 to K3 through the average score combined with the score coefficient table to complete the charging station power load prediction.

[0012] Step 6: Optimize and improve the above predictions to determine the best prediction for the power load of the charging station.

[0013] Further, a preferred implementation is provided, in which the method for determining the coefficient value of the peak electricity price K1 in step 2 is:

[0014] P peak=K1*An*(A+B+C / A*K1+B*K2+C*K3)

[0015] In the formula, K1 is the overall charging load adjustment coefficient of the peak electricity price section in one day, K2 is the overall charging load adjustment coefficient of the valley electricity price section in one day, K3 is the overall charging load adjustment coefficient of the flat electricity price section in one day, A is the proportion of the overall charging load in the peak electricity price section in one day; B is the proportion of the overall charging load in the valley electricity price section in one day; C is the proportion of the overall charging load in the flat electricity price section in one day, and An is the peak charging load of similar stations.

[0016] Further, a preferred implementation is provided, in which the method for determining the coefficient value of the valley electricity price K2 in step 3 is:

[0017] P valley=K2*Bn*(A+B+C / A*K1+B*K2+C*K3)

[0018] Where Bn is the valley charging load at similar stations.

[0019] Further, a preferred implementation manner is provided, in which the method for determining the average score of the electricity price in the normal period in step 4 is:

[0020] P level=K3*Cn*(A+B+C / A*K1+B*K2+C*K3)

[0021] Where Cn is the charging load at a similar station at normal electricity prices.

[0022] Furthermore, a preferred implementation is provided, in which the method for determining the optimal charging station power load forecast in step 5 is obtained by analogy with a benchmark data analysis method.

[0023] Solution 2: A charging station power load prediction system, the system comprising:

[0024] A data collection module is used to collect and analyze the existing daily charging service order volume, the order volume and the parameters related to the site area, service vehicle type, and road traffic flow, and to construct a power load prediction method based on the above existing charging station;

[0025] The prediction method comprises the following steps:

[0026] Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic volume;

[0027] The peak electricity price K1 determination module is used to predict the load of the charging station in the construction area through the relevant parameter data collected by the data collection module, and determine the coefficient value of the peak electricity price K1;

[0028] The valley electricity price K2 determination module is used to predict the station construction conditions and the charging station load within the planned station construction scale through the relevant parameter data collected by the data collection module, and determine the coefficient value of the valley electricity price K2;

[0029] The K3 determination module of the average stage electricity price is used to predict the load of the charging station with the ladder electricity price through the relevant parameter data collected by the data collection module, and determine the K3 coefficient value of the flat stage electricity price;

[0030] The charging station power load prediction module is used to predict the charging station load of the tiered electricity price based on the K3 determination module of the data collection module to the flat stage electricity price, determine the average score of the peak, valley and flat stage electricity prices, and determine the K1 to K3 coefficient values ​​through the average score combined with the score coefficient table to complete the charging station power load prediction.

[0031] The optimal charging station power load forecasting module is used to optimize and improve the above-mentioned various forecasts and determine the optimal charging station power load forecast.

[0032] Solution three: A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes any one of the methods described in Solution one.

[0033] Solution 4: A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of Solution 1.

[0034] The present invention is beneficial in that:

[0035] The method for predicting the power load of a charging station described in the present invention obtains the 24-hour basic energy consumption data of a newly built station site through an analog benchmark data derivation method. The relatively accurate load energy consumption data is combined with the expected photovoltaic power generation to relatively accurately predict the photovoltaic system absorption rate. Combined with the energy management system, the photovoltaic surplus power is predicted in advance, the energy storage power purchase cost is reduced, and the storage of photovoltaic surplus power is predicted in advance.

[0036] The charging station power load prediction method described in the present invention accurately predicts energy consumption data, which promotes the optimal operation of the microgrid system. Through analogy analysis, condition evaluation reasonably determines the fluctuation curve of the benchmark energy consumption data, and provides strong support for the scale of photovoltaic and energy storage systems.

[0037] The charging station power load prediction method described in the present invention and reasonable energy consumption prediction can solve the irrationality of the scale of setting the number of charging guns in the station construction stage, carry out the basic construction of charging facilities more scientifically, improve the utilization rate of charging guns, and increase the rate of return.

[0038] The method described in the present invention can reasonably determine the 24-hour energy consumption through more accurate charging load energy consumption prediction, improve the correlation of photovoltaic energy storage systems through various load energy consumption predictions at charging stations, reduce electricity purchase costs, and avoid the waste of abandoned light resources.

[0039] The present invention is also applicable to the field of new energy consumption prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of analyzing the peak electricity price K1 coefficient value through regional evaluation as described in the ninth implementation mode.

[0041] Figure 2 This is a schematic diagram of the coefficient values ​​of K1 to K3 for evaluating and analyzing the vehicle composition at a passing station as described in the ninth embodiment.

[0042] Figure 3 This is a schematic diagram of analyzing the peak, valley and flat K1 to K3 coefficient values ​​through the tiered electricity price evaluation as described in the ninth implementation mode.

[0043] Figure 4 This is a schematic diagram of the K2 coefficient value of the valley electricity price for evaluating the site construction conditions described in Implementation Mode 9.

[0044] Figure 5 This is a schematic diagram of the valley electricity price K2 coefficient value for evaluating the functional scale conditions of the proposed station as described in Implementation Method Nine.

[0045] Figure 6 This is a schematic diagram of the average score of the peak electricity price coefficient K1 described in Implementation Method Nine.

[0046] Figure 7 This is a schematic diagram of the average score of the valley electricity price coefficient K2 described in Implementation Method Nine.

[0047] Figure 8 This is a schematic diagram of the average score of the flat-range electricity price coefficient K2 described in Implementation Mode 9.

[0048] Fig. 9 This is a schematic diagram of the benchmark percentage of charging capacity in each period of 24 hours for similar stations described in Implementation Mode 9.

[0049] Fig.10 This is a schematic diagram of the 24-hour energy consumption analysis nodes of the charging service described in Implementation Mode 9.

[0050] Fig.11 Schematic diagram of the change in power consumption in each time period after the energy storage system described in Implementation Mode 9 is operated. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the implementation methods of the present application clearer, the technical solutions in the implementation methods of the present application will be clearly and completely described below in conjunction with the drawings in the implementation methods of the present application. Obviously, the described implementation methods are only part of the implementation methods of the present application, not all of the implementation methods.

[0052] Embodiment 1: This embodiment provides a method for predicting the power load of a charging station, the method comprising:

[0053] By collecting and analyzing the existing daily charging service order volume, order volume and parameters related to the site area, service model, and road traffic flow, a method for predicting the power load of the existing charging stations is constructed;

[0054] The prediction method comprises the following steps:

[0055] Step 1: Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic flow;

[0056] Step 2: Use the relevant parameter data collected in step 1 to predict the load of the charging station in the construction area and determine the coefficient value of the peak electricity price K1;

[0057] Step 3: Based on the relevant parameter data collected in step 1, the station construction conditions and the charging station load within the planned station construction scale are predicted to determine the coefficient value of the valley electricity price K2;

[0058] Step 4: Use the relevant parameter data collected in step 1 to predict the load of the charging station with tiered electricity prices and determine the K3 coefficient value of the flat electricity price;

[0059] Step 5: Based on steps 1 to 4, predict the load of the charging station with tiered electricity prices, determine the average score of peak, valley, and flat electricity prices, and determine the coefficient values ​​of K1 to K3 through the average score combined with the score coefficient table to complete the charging station power load prediction.

[0060] Step 6: Optimize and improve the above predictions to determine the best prediction for the power load of the charging station.

[0061] Implementation method 2: This implementation method further limits the charging station power load prediction method described in implementation method 1. The method for determining the coefficient value of the peak power price K1 in step 2 is:

[0062] P peak=K1*An*(A+B+C / A*K1+B*K2+C*K3)

[0063] Wherein, K1 is the overall charging load adjustment coefficient of the peak electricity price period in one day, A is the proportion of the overall charging load in the peak electricity price period in one day; B is the proportion of the overall charging load in the valley electricity price period in one day; C is the proportion of the overall charging load in the flat electricity price period in one day, and An is the peak charging load of similar stations.

[0064] Implementation method 3: This implementation method further limits the charging station power load prediction method described in implementation method 1. The method for determining the coefficient value of the valley electricity price K2 in step 3 is:

[0065] P valley=K2*Bn*(A+B+C / A*K1+B*K2+C*K3)

[0066] Where K2 is the overall charging load adjustment coefficient for the valley section of electricity prices within a day; Bn is the valley charging load for similar stations.

[0067] Implementation method 4: This implementation method further limits the charging station power load prediction method described in implementation method 1. The method for determining the average score of the electricity price in normal period in step 4 is:

[0068] P level=K3*Cn*(A+B+C / A*K1+B*K2+C*K3)

[0069] Where K3 is the overall charging load adjustment coefficient during the flat electricity price period of a day, and Cn is the charging load at the normal electricity price of a similar station.

[0070] Implementation method five: This implementation method further limits the charging station power load prediction method described in implementation method one. In step five, the optimal charging station power load prediction method is determined by analogy with the benchmark data analysis method.

[0071] Embodiment 6: This embodiment proposes a charging station power load prediction system, the system comprising:

[0072] A data collection module is used to collect and analyze the existing daily charging service order volume, the order volume and the parameters related to the site area, service vehicle type, and road traffic flow, and to construct a power load prediction method based on the above existing charging station;

[0073] The prediction method comprises the following steps:

[0074] Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic volume;

[0075] The peak electricity price K1 determination module is used to predict the load of the charging station in the construction area through the relevant parameter data collected by the data collection module, and determine the coefficient value of the peak electricity price K1;

[0076] The valley electricity price K2 determination module is used to predict the station construction conditions and the charging station load within the planned station construction scale through the relevant parameter data collected by the data collection module, and determine the coefficient value of the valley electricity price K2;

[0077] The K3 determination module of the average stage electricity price is used to predict the load of the charging station with the ladder electricity price through the relevant parameter data collected by the data collection module, and determine the K3 coefficient value of the flat stage electricity price;

[0078] The charging station power load prediction module is used to predict the charging station load of the tiered electricity price based on the K3 determination module of the data collection module to the flat stage electricity price, determine the average score of the peak, valley and flat stage electricity prices, and determine the K1 to K3 coefficient values ​​through the average score combined with the score coefficient table to complete the charging station power load prediction.

[0079] The optimal charging station power load forecasting module is used to optimize and improve the above-mentioned various forecasts and determine the optimal charging station power load forecast.

[0080] Embodiment 7: This embodiment proposes a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the method described in any one of embodiments 1 to 5.

[0081] Embodiment 8: This embodiment proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in any one of embodiments 1 to 5 are implemented.

[0082] Embodiment 9: This embodiment provides an example, which is used to explain the above embodiments 1 to 8. The specific example is as follows:

[0083] See also Figures 1 to 11 To illustrate this embodiment, the method described in this embodiment includes the following steps:

[0084] The charging station described in this embodiment mainly consumes electricity for charging piles. The electricity consumption of charging piles depends on the number of charging service orders per day. The number of orders is closely related to the construction area, service vehicle type, and road traffic volume. With the help of the AutoNavi data platform, the station site electric vehicle entry rate is predicted. Based on the background data of the built stations in various cities, the analogy analysis method is used, and the electricity consumption data of similar charging stations is used as the basis. The K1, K2, and K3 values ​​are determined through regional evaluation, station entry vehicle composition evaluation, tiered electricity price evaluation, station construction condition evaluation, and the functional scale of the planned station. The calculation process is as follows:

[0085] By collecting and analyzing the existing daily charging service order volume, order volume and parameters related to the site area, service model, and road traffic flow, a method for predicting the power load of the existing charging stations is constructed;

[0086] The prediction method comprises the following steps:

[0087] Step 1: Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic flow;

[0088] Step 2: Use the parameter data collected in step 1 to predict the load of the charging station in the construction area and determine the coefficient value of the peak electricity price K1;

[0089] Step 3: Based on the parameter data collected in step 1, the load of the charging station within the proposed station construction scale is predicted to determine the coefficient value of the valley electricity price K2;

[0090] Step 4: Use the parameter data collected in step 1 to predict the load of the charging station with tiered electricity prices and determine the K3 coefficient value of the flat electricity price;

[0091] Step 5: Based on steps 1 to 4, predict the load of the charging station with tiered electricity prices, determine the average score of peak, valley, and flat electricity prices, and determine the coefficient values ​​of K1 to K3 through the average score combined with the score coefficient table to complete the charging station power load prediction.

[0092] Step 6: Optimize and improve the above predictions to determine the best prediction for the power load of the charging station.

[0093] Comprehensively considering the above construction conditions, professionals manually selected according to the site conditions, and obtained the scores of the above five conditions respectively, and then obtained the average scores of peak, valley and flat electricity prices respectively. Figures 6 to 9 As shown, the coefficient values ​​of K1 to K3 are determined by averaging the scores and combining them with the score coefficient table.

[0094] Based on the basic data of similar stations, calculate the accurate values ​​of peak, valley and normal periods:

[0095] P peak=K1*An*(A+B+C / A*K1+B*K2+C*K3)

[0096] P valley=K2*Bn*(A+B+C / A*K1+B*K2+C*K3)

[0097] P level=K3*Cn*(A+B+C / A*K1+B*K2+C*K3)

[0098] Where: A is the proportion of total charging load during the peak electricity price period in a day;

[0099] B is the proportion of total charging load in the valley period of electricity price in a day;

[0100] C is the proportion of total charging load in the flat electricity price period of the day;

[0101] An~Cn are the peak-valley-flat basic charging loads at similar stations;

[0102] K1 is the overall charging load adjustment coefficient during the peak electricity price period of a day;

[0103] K2 is the overall charging load adjustment coefficient during the electricity price valley period of the day;

[0104] K3 is the overall charging load adjustment coefficient in the flat electricity price period of the day;

[0105] That is, a 24-hour energy consumption data curve of the charging service is obtained.

[0106] Through the analogy benchmark data derivation method, the 24-hour basic energy consumption data of the newly built site is obtained. Through relatively accurate load energy consumption data, combined with the expected photovoltaic power generation, the photovoltaic system absorption rate is relatively accurately predicted. Combined with the energy management system, photovoltaic surplus power can be predicted in advance, the cost of energy storage electricity purchase can be reduced, and photovoltaic surplus power can be predicted and stored in advance.

[0107] Figure 1Any process or method description in the flowchart described in or otherwise described herein can be understood as representing a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a custom logic function or process, and the scope of the preferred embodiment of the present invention includes other implementations, in which the functions may be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by a person skilled in the art of the present invention. The logic and / or steps represented in the flowchart or otherwise described herein illustrate the possible implementation architecture, functions and operations of the apparatus and methods according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logic function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It is also noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions. For example, what may be considered as an ordered list of executable instructions for implementing a logical function may be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions in an instruction execution system, apparatus, or device).

[0108] Those skilled in the art will appreciate that the above are only preferred embodiments of the present invention, and the various embodiments of the present disclosure and / or the features described in the claims may be combined or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. It is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or perform equivalent substitutions on some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

[0109] Although preferred embodiments of the present invention have been described, additional changes and modifications may be made to these embodiments by those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for predicting power load of a charging station, characterized in that: The method comprises: By collecting and analyzing the existing daily charging service order volume, order volume and parameters related to the site area, service model, and road traffic flow, a method for predicting the power load of the existing charging stations is constructed; The prediction method comprises the following steps: Step 1: Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic flow; Step 2: Use the relevant parameter data collected in step 1 to predict the load of the charging station in the construction area and determine the coefficient value of the peak electricity price K1; Step 3: Based on the relevant parameter data collected in step 1, the station construction conditions and the charging station load within the planned station construction scale are predicted to determine the coefficient value of the valley electricity price K2; Step 4: Use the relevant parameter data collected in step 1 to predict the load of the charging station with tiered electricity prices and determine the K3 coefficient value of the flat electricity price; Step 5: Based on steps 1 to 4, predict the load of the charging station with tiered electricity prices, determine the average score of peak, valley, and flat electricity prices, and determine the coefficient values ​​of K1 to K3 through the average score combined with the score coefficient table to complete the charging station power load prediction. Step 6: Optimize and improve the above predictions to determine the best prediction for the power load of the charging station.

2. The charging station power load prediction method according to claim 1, characterized in that: The method for determining the coefficient value of the peak electricity price K1 in step 2 is: P peak=K1*An*(A+B+C / A*K1+B*K2+C*K3) In the formula, K1 is the overall charging load adjustment coefficient of the peak electricity price section in one day, K2 is the overall charging load adjustment coefficient of the valley electricity price section in one day, K3 is the overall charging load adjustment coefficient of the flat electricity price section in one day, A is the proportion of the overall charging load in the peak electricity price section in one day; B is the proportion of the overall charging load in the valley electricity price section in one day; C is the proportion of the overall charging load in the flat electricity price section in one day, and An is the peak charging load of similar stations.

3. The charging station power load prediction method according to claim 1, characterized in that: The method for determining the coefficient value of the valley electricity price K2 in step 3 is: P valley=K2*Bn*(A+B+C / A*K1+B*K2+C*K3) Where Bn is the valley charging load at similar stations.

4. The charging station power load prediction method according to claim 1, characterized in that: The method for determining the average score of the electricity price in the normal period in step 4 is: P level=K3*Cn*(A+B+C / A*K1+B*K2+C*K3) Where Cn is the charging load at a similar station at normal electricity prices.

5. The method for predicting the power load of a charging station according to claim 1, characterized in that: The method for determining the optimal power load forecast for charging stations in step 5 is obtained by analogy with the benchmark data analysis method.

6. A charging station power load prediction system, characterized in that: The system comprises: A data collection module is used to collect and analyze the existing daily charging service order volume, the order volume and the parameters related to the site area, service vehicle type, and road traffic flow, and to construct a power load prediction method based on the above existing charging station; The prediction method comprises the following steps: Collect the existing daily charging service order volume, and the parameter data related to the order volume, location, service model, and road traffic volume; The peak electricity price K1 determination module is used to predict the load of the charging station in the construction area through the relevant parameter data collected by the data collection module, and determine the coefficient value of the peak electricity price K1; The valley electricity price K2 determination module is used to predict the station construction conditions and the charging station load within the planned station construction scale through the relevant parameter data collected by the data collection module, and determine the coefficient value of the valley electricity price K2; The K3 determination module of the average stage electricity price is used to predict the load of the charging station with the ladder electricity price through the relevant parameter data collected by the data collection module, and determine the K3 coefficient value of the flat stage electricity price; The charging station power load prediction module is used to predict the charging station load of the tiered electricity price based on the K3 determination module of the data collection module to the flat stage electricity price, determine the average score of the peak, valley and flat stage electricity prices, and determine the K1 to K3 coefficient values ​​through the average score combined with the score coefficient table to complete the charging station power load prediction. The optimal charging station power load forecasting module is used to optimize and improve the above-mentioned various forecasts and determine the optimal charging station power load forecast.

7. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the steps of the method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images