Electric vehicle charging load prediction method and device, equipment and storage medium
By acquiring and processing the charging time and residual power data of electric vehicles, and using the probability distribution function to predict the charging load of electric vehicles, the problem of distortion of prediction results in the prior art is solved, and the accuracy and applicability of prediction are improved.
Patent Information
- Application Number
- CN202411184005.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-22
AI Technical Summary
The existing electric vehicle charging load prediction methods lack the support for actual charging data of electric vehicles. The data processing method is simple, resulting in large distortion of the prediction results and actual charging load, and it cannot be applied to different urban areas, resulting in poor universality.
By obtaining the charging time data and the remaining power data of charging time of different types of electric vehicles in different urban areas, processing these data based on the preset probability distribution function, determining the optimal probability distribution function, establishing a set of charging probability distribution function for the predicted period, and combining it with The charging piles are online for predicting the charging load.
It improves the accuracy and universality of charging load prediction, and can conduct segmented predictions for specific time periods and types of vehicles to meet specific needs and improves the accuracy of prediction.
Smart Images

Figure CN119005525A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of power grid load prediction, and in particular relates to a method, device, equipment and storage medium for predicting charging load of an electric vehicle. Background Art
[0002] With the continuous development of electric vehicle technology, the popularity of electric vehicles has increased year by year, and they are widely used in people's travel, life and transportation.
[0003] At present, in order to facilitate the establishment of an appropriate number and location of electric vehicle charging piles in different areas of the city, and to plan the corresponding power grid facilities, it is necessary to study the charging load of electric vehicles in different areas of the city, so as to realize the prediction of the charging load of electric vehicles; an existing way to preset the charging load of electric vehicles is to collect people's travel demand information, existing charging pile distribution information and electricity price information, and consider the impact of this information on the user's charging behavior, so as to simulate the charging load of electric vehicles, thereby realizing the prediction of the charging load of electric vehicles.
[0004] However, the above method of predicting the charging load of electric vehicles lacks the support of the actual charging data of electric vehicles, and the data processing method is relatively simple, which leads to a large distortion of the charging load of the electric vehicle predicted in the end compared with the actual charging load.
[0005] Existing technologies for electric vehicle charging load forecasting include:
[0006] Chinese patent application number CN110929921A provides a method, device, computer equipment and storage medium for predicting the load of a charging station. The method analyzes the proportion of the number of electric vehicles arriving at the station for charging every day based on historical data, and then estimates the total number of electric vehicles arriving at the station for charging on that day. The number of electric vehicles arriving at the station for charging is predicted in detail based on the probability distribution function of the time when the electric vehicles arrive at the station. The remaining state of charge of each electric vehicle arriving at the station is estimated based on the probability distribution function of the daily mileage of the electric vehicles. Then, based on the above two sets of data, the charging load data of the charging station is predicted every hour. However, this method mainly involves predicting the charging load data of the charging station. Although it also involves the load of electric vehicles, it does not provide a detailed introduction on how to predict the charging load of electric vehicles.
[0007] Chinese patent application number CN109308541A provides a method for predicting charging load of electric vehicles based on scenario analysis. The steps of the method are as follows: first, according to the attributes of the travel day, the time variables such as the first travel time, driving time and parking time of the electric vehicle, as well as the spatial variables such as the destination transfer probability and the driving mileage, are analyzed, and the probability distribution function is constructed to fit the above variables, thereby obtaining the spatiotemporal distribution characteristics of the electric vehicle travel; then, according to the different charging behaviors of the electric vehicle, three scenarios are divided, including one charge per day, multiple charges per day and one charge per multiple days, and charging decision models are established for different scenarios respectively; finally, the travel demand and charging characteristics of the electric vehicle are comprehensively considered to predict the charging load under different scenarios. However, this method does not take into account that different urban areas will be divided in the city, such as living areas, commercial areas and production areas; the time variables and spatial variables of vehicles in different urban areas are different, which will result in the final predicted charging load being only applicable to a certain urban area, but not to multiple urban areas, resulting in the poor universality of the final predicted charging load in the city.
[0008] Chinese patent application number CN114734840A provides a method and system for predicting the demand response adjustable potential of electric vehicle load groups, wherein the method includes the following steps: Step 1, predicting the charging start time and charging duration of electric vehicles in different scenarios based on the charging habits of electric vehicle users, and obtaining the joint probability distribution function of electric vehicles in different scenarios respectively; Step 2, statistically analyzing the charging power of electric vehicles in the region at different times based on the joint probability distribution function; Step 3, sampling all electric vehicles in the region using the Monte Carlo method, and calculating the total demand of all electric vehicles in the sampled samples, as well as the regional regulation potential. However, the universality of the charging load of this method in cities is also poor, and it can only calculate the charging power of vehicles in a certain period of time, but cannot predict the charging load of a certain type of vehicle in a certain period of time. In addition, the patent uses a sampling method to finally determine the regional regulation potential. When the number of samples is insufficient or not representative, the result of the final determination of the regional regulation potential will be poorly determined. Summary of the invention
[0009] In order to solve the deficiencies in the prior art, the present invention provides a method, device, equipment and storage medium for predicting charging load of electric vehicles.
[0010] The present invention adopts the following technical solution.
[0011] A first aspect of the present invention provides a method for predicting charging load of an electric vehicle, the method specifically comprising the following steps:
[0012] Step 1, obtaining charging time data and remaining power data of different types of electric vehicles in different urban areas;
[0013] Step 2, processing the charging time data and the remaining power data at the charging time based on different types of probability distribution functions of different preset urban areas, respectively, to obtain quantified results, comparing the quantified results obtained according to different probability distribution functions with the probability distribution of the actual electric vehicle charging time and the remaining power at the charging time, and determining the optimal probability distribution function of the charging time data and the remaining power data at the charging time of each type of electric vehicle in each urban area;
[0014] Step 3, processing different urban areas and types of electric vehicles through the optimal probability distribution function, and obtaining charging time prediction data and remaining power prediction data corresponding to different types of electric vehicles in different urban areas;
[0015] Step 4: Based on the charging time prediction data, the remaining power prediction data at the charging time, and the acquired online status of the charging piles, a charging probability distribution function group for the prediction period is established;
[0016] Step 5: Based on the prediction period charging probability distribution function group and the obtained prediction period charging power, the charging load of electric vehicles of corresponding types in different urban areas corresponding to the prediction period is predicted.
[0017] Preferably, in step 1, the urban area includes at least living areas, commercial areas and production areas; the types of electric vehicles include at least private travel vehicles and work transport vehicles; the charging time data is the time recording data when the electric vehicle charging pile charges the electric vehicle, and the charging time remaining power data is the remaining power of the electric vehicle at the beginning of the charging time.
[0018] Preferably, in step 2, the preset different probability distribution functions include at least Fourier probability distribution function, normal distribution probability function and Gaussian probability distribution function; the probability distribution function includes charging moment data probability distribution function and charging moment remaining power data probability distribution function, the horizontal axis of the charging moment data probability distribution function is the charging moment data, and the vertical axis is the first probability; the horizontal axis of the charging moment remaining power data probability distribution function is the charging moment data, and the vertical axis is the second probability.
[0019] Preferably, in step 2, the processing of the charging time data and the remaining power data at the charging time based on different types of probability distribution functions preset in different urban areas specifically includes:
[0020] The charging time data and the remaining power data at the charging time are respectively input into different types of probability distribution functions to obtain the probability distribution results under the corresponding probability distribution functions; the fitting results corresponding to different probability distribution functions are obtained based on the preset fitting function type; based on the fitting results and the mean of the probability distribution results, the quantization results corresponding to different probability distribution functions are calculated through the preset quantization function, and the optimal probability distribution function is determined based on the quantization results.
[0021] Preferably, the quantization function is specifically:
[0022] Quantization function: divide the probability distribution function curve into integer points and take the value of each point.
[0023]
[0024] In the formula, λ represents the type of probability distribution function, λ={1,2,3}, which represent Fourier probability distribution function, normal distribution probability function, Gaussian probability distribution function respectively, y 0,i,λ represents the λth probability distribution result of the i-th point, is the mean of the λth probability distribution, y i,λ is the λth fitting result of the ith point, and n is the total number of data.
[0025] Preferably, in step 2, the scheme for determining the optimal probability distribution function specifically includes:
[0026] The quantified results of the fitting results of different probability distribution functions of different types of electric vehicles in different areas of the city are calculated, and the differences with the preset threshold values are calculated respectively. The probability distribution function corresponding to the quantified result with the smallest difference is recorded as the optimal probability distribution function.
[0027] Preferably, the specific steps of step 3 are: calculating the mean of the optimal probability distribution function of different types of electric vehicles in different urban areas as the charging time prediction data and the remaining power prediction data of different types of electric vehicles in different areas of the corresponding city.
[0028] Preferably, in step 4, the specific process of establishing the electric vehicle charging probability distribution function group for the prediction period is:
[0029] The communication connection status between a charging pile used during charging and the power grid server is obtained, represented by r. If the charging pile and the power grid server are communicating normally, r = 1, otherwise, r = 0; the distribution probability p of the predicted time is obtained from the best probability distribution function of different types of electric vehicle charging time prediction data in different urban areas. m,e,t , calculate the predicted charging time T required to fully charge the electric vehicle of the mth urban area and the eth type at the tth moment m,e,t ;
[0030] T m,e,t The calculation formula is:
[0031]
[0032] C f Indicates the battery capacity of the electric vehicle connected to the charging pile obtained through the power grid server.
[0033] C l,m,e is the remaining power prediction data of the electric vehicle of the e-th type in the m-th urban area at the charging time; P m,e,t represents the charging power of the charging pile used by the e-th type of electric vehicle in the m-th urban area at the t-th moment, P m,e,t It is equal to the historical charging power of the corresponding type of electric vehicles of the charging pile in each prediction period;
[0034] Calculate the following formula:
[0035]
[0036] Repeating the above steps for all types of electric vehicles in all regions can obtain the electric vehicle charging probability distribution function group for the forecast period.
[0037] Preferably, step 5 specifically includes:
[0038] Get the forecast period, input the forecast period, city area and electric vehicle type into the forecast period charging probability distribution function group, and output the forecast period charging probability f m,e,t ; Calculate the charging power P during the forecast period t The product of the charging probability during the forecast period f m,e,t , as the predicted charging load C of the corresponding type of electric vehicles in the corresponding prediction period in the corresponding urban area m,e,t .
[0039] Preferably, the method further comprises step 6: calculating the total load of electric vehicles in different urban areas corresponding to the forecast period, and determining whether it is credible;
[0040] Step 6.1, obtaining the number of different types of electric vehicles in the urban area, and obtaining the number of electric vehicles in the urban area;
[0041] Step 6.2, based on the information on the number of electric vehicles in the urban area and the charging loads of different types of electric vehicles, calculate the total load of electric vehicles in the urban area during the forecast period;
[0042] Step 6.3, statistically analyze the total load of electric vehicles in the city area during several forecast periods, and obtain the standard deviation N and the mathematical expectation S as statistical results;
[0043] Step 6.4, based on the statistical results, it is determined whether the total load of electric vehicles in the forecast period of the city area at different time periods converges. If so, it is considered that the total load of electric vehicles in the forecast period of the city area at different time periods is credible.
[0044] Preferably, the formula for calculating the total load of electric vehicles in a certain city area during the forecast period m in step 6.2 is:
[0045]
[0046] Among them, C m,E,t represents the total load of electric vehicles in the urban area during the forecast period, E represents the number of types of electric vehicles in the urban area, and n m,e represents the number of electric vehicles of the eth type in the mth area. 12. The method for predicting electric vehicle charging load according to claim 10, characterized in that:
[0047] The convergence equation used to determine convergence in step 6.4 is:
[0048]
[0049] Where k is the number of iterations, N is the standard deviation of the total load of electric vehicles in several forecast periods, and S is the mathematical expectation of the total load of electric vehicles in several forecast periods.
[0050] The second aspect of the present invention provides an electric vehicle charging load prediction device, using the method described in the first aspect of the present invention, characterized in that:
[0051] A data acquisition module, used to acquire charging time data and remaining power data of different types of electric vehicles in different preset urban areas; the urban areas at least include living areas, commercial areas and production areas; the types of electric vehicles at least include private travel vehicles and work transportation vehicles;
[0052] A function processing module, used to process the charging time data and the remaining power data at the charging time respectively based on different preset probability distribution functions to obtain processing results; judge the processing results to determine the best probability distribution function;
[0053] A data generation module, configured to process the input urban area and type of electric vehicle based on the optimal probability distribution function to obtain charging time prediction data and remaining power prediction data of the type of electric vehicle in the urban area;
[0054] A function group establishment module, used to establish a charging probability distribution function group for a prediction period based on the charging time prediction data, the remaining power prediction data at the charging time, and the acquired online status of the charging pile;
[0055] The load prediction module is used to predict the charging load of electric vehicles of corresponding types in corresponding prediction periods in different urban areas based on the charging probability distribution function group of the prediction period and the obtained charging power of the prediction period.
[0056] The third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method described in the first aspect of the present invention when executing the computer program.
[0057] The fourth aspect of the present invention proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods proposed in the first aspect of the present invention are implemented.
[0058] The beneficial effect of the present invention is that, compared with the prior art,
[0059] 1. In the process of calculating the final predicted charging load of a specific type of vehicle in a specific period of time, the influence of different urban areas on the calculation of the final predicted charging load, such as living areas, commercial areas and production areas, is fully considered; in this way, the universality of calculating the final predicted charging load of a specific type of vehicle in a specific period of time can be improved, thereby improving the accuracy of the predicted charging load.
[0060] 2. It can predict the charging load of a specific type of vehicle in a specific period of time; this helps to predict the load of a specific type of vehicle, thereby improving the further segmentation of vehicle load forecasting to meet specific needs.
[0061] 3. When predicting the charging load of a specific type of vehicle in a specific period of time, not only some data corresponding to the car when charging is considered, but also the remaining power data of the vehicle and the online status of the charging pile are considered. This makes it easy to fully consider the objects used to predict the charging load of a specific type of vehicle in a specific period of time, so as to improve the accuracy of the final predicted charging load of a specific type of vehicle in a specific period of time. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] Figure 1 This is an application environment diagram of an electric vehicle charging load prediction method in one embodiment of the present invention;
[0063] Figure 2 A flow chart of a method for predicting charging load of an electric vehicle provided in one embodiment of the present invention;
[0064] Figure 3 A schematic diagram of the structure of a device for predicting charging load of an electric vehicle provided in one embodiment of the present invention;
[0065] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present invention;
[0066] Figure 5 An internal structure diagram of a computer-readable storage medium provided in one embodiment of the present invention. DETAILED DESCRIPTION
[0067] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.
[0068] Embodiment 1 of the present invention provides a method for predicting charging load of an electric vehicle. Figure 2 As shown, the specific steps include:
[0069] Step 1: Obtain charging time data and remaining power data of different types of electric vehicles in different urban areas.
[0070] Preferably, in step 1, the urban area includes at least living areas, commercial areas and production areas; the types of electric vehicles include at least private travel vehicles and work transport vehicles. The charging time data refers to the time recording data when the electric vehicle charging pile charges the electric vehicle, and the charging time remaining power data refers to the remaining power of the electric vehicle at the beginning of the charging time. The electric vehicle charging pile can obtain the vehicle type of the electric vehicle and the remaining power of the electric vehicle at the beginning of the charging time with the consent of the electric vehicle owner, thereby obtaining the charging time remaining power data.
[0071] It should be noted that cities are generally divided into different functional areas. In the present embodiment, it is assumed that the functional areas divided into cities include at least living areas, commercial areas and production areas; the types of electric vehicles distributed in each functional area include at least private travel vehicles and work transport vehicles; the demands for different types of electric vehicles in different functional areas of the city are different. For example, the number of private travel vehicles distributed in living areas and commercial areas is significantly more than that of work transport vehicles; and the number of work transport vehicles distributed in production areas is significantly more than that of private travel vehicles.
[0072] In order to facilitate the provision of charging services for electric vehicles, electric vehicle charging piles are installed at specific locations in different urban areas, and the charging piles are electrically connected to the corresponding power grid and are communicatively connected to the server of the power grid; when the electric vehicle is charging at the charging pile, on the one hand, the charging pile records the time when the electric vehicle is charging, thereby obtaining the charging time data; on the other hand, the charging pile can obtain the vehicle type of the electric vehicle and the remaining power of the electric vehicle at the beginning of the charging time with the consent of the electric vehicle owner, thereby obtaining the remaining power data at the charging time; further, the obtained charging time data and the remaining power data at the charging time are sent to the power grid server; in this way, the power grid server can obtain the charging time data and the remaining power data at the charging time of the electric vehicle in different areas of the corresponding city at different time periods.
[0073] Step 2: Process the charging time data and the remaining power data at the charging time based on different types of probability distribution functions preset in different urban areas to obtain quantified results. Compare the quantified results obtained according to different probability distribution functions with the probability distribution of the actual electric vehicle charging time and the remaining power at the charging time to determine the optimal probability distribution function for each type of electric vehicle charging time data and the remaining power data at the charging time in each urban area.
[0074] It should be noted that in order to facilitate the subsequent prediction of the charging time prediction data and the remaining power prediction data at the charging time of electric vehicles of corresponding vehicle types in different areas of the corresponding city based on the acquired charging time data and the remaining power data at the charging time, and to make the charging time prediction data and the remaining power prediction data at the charging time as close as possible to the corresponding actual charging time data and the actual remaining power data at the charging time, the power grid server needs to select the best probability distribution function from its built-in several probability distribution functions to process the acquired charging time data and the remaining power data at the charging time.
[0075] After the power grid server obtains the charging time data and the remaining power data at the charging time through step 1, it further uses its built-in different probability distribution functions to process the obtained charging time data and the remaining power data at the charging time respectively, so as to obtain processing results corresponding to different probability distribution functions; further, the power grid server judges each processing result to determine which processing result is closer to the actual probability distribution of electric vehicle charging data, the charging data including the obtained charging time data and the remaining power data at the charging time, and takes the corresponding probability distribution function as the optimal probability distribution function.
[0076] Preferably, in step 2, the preset different probability distribution functions include at least Fourier probability distribution function, normal distribution probability function and Gaussian probability distribution function; the probability distribution function includes charging moment data probability distribution function and charging moment remaining power data probability distribution function, the horizontal axis of the charging moment data probability distribution function is the charging moment data, and the vertical axis is the first probability; the horizontal axis of the charging moment remaining power data probability distribution function is the charging moment data, and the vertical axis is the second probability.
[0077] Preferably, in step 2, the processing of the charging time data and the remaining power data at the charging time based on different types of probability distribution functions preset in different urban areas specifically includes:
[0078] The charging time data and the remaining power data at the charging time are respectively input into different types of probability distribution functions to obtain the probability distribution results under the corresponding probability distribution functions; the fitting results corresponding to different probability distribution functions are obtained based on the preset fitting function type; based on the fitting results and the mean of the probability distribution results, the quantization results corresponding to different probability distribution functions are calculated through the preset quantization function, and the optimal probability distribution function is determined based on the quantization results.
[0079] Preferably, the quantization function is specifically:
[0080] Quantization function: divide the probability distribution function curve into integer points and take the value of each point.
[0081]
[0082] In the formula, λ represents the type of probability distribution function, λ={1,2,3}, which represent Fourier probability distribution function, normal distribution probability function, Gaussian probability distribution function respectively, y 0,i,λ represents the λth probability distribution result of the i-th point, is the mean of the λth probability distribution, y i,λ is the λth fitting result of the ith point, and n is the total number of data.
[0083] Preferably, the quantified results of the fitting results of different probability distribution functions of different types of electric vehicles in different areas of the city are calculated, and the differences with the preset threshold values are calculated respectively. The probability distribution function corresponding to the quantified result with the smallest difference is recorded as the optimal probability distribution function.
[0084] Step 3, through the optimal probability distribution function, process different areas of different cities and types of electric vehicles to obtain charging time prediction data and remaining power prediction data of different types of electric vehicles in different areas of the corresponding city.
[0085] It should be noted that the input of the optimal probability distribution function is the urban area and the type of electric vehicle, and the output of the optimal probability distribution function is the charging time prediction data and the remaining power prediction data at the charging time for different types of electric vehicles in different areas of the corresponding city.
[0086] Preferably, the specific steps of step 3 are: calculating the mean of the optimal probability distribution function of different types of electric vehicles in different urban areas as the charging time prediction data and the remaining power prediction data of different types of electric vehicles in different areas of the corresponding city.
[0087] Step 4: Based on the charging time prediction data, the remaining power prediction data at the charging time, and the online status of the charging piles obtained through the power grid server, a group of electric vehicle charging probability distribution functions for the prediction period is established.
[0088] It should be noted that in order to facilitate the calculation of the final electric vehicle charging load forecast, it is necessary to understand the charging probability of electric vehicles in different urban areas at different time periods. For this purpose, it is necessary to establish a corresponding charging probability distribution function group for the forecast period.
[0089] Preferably, in step 4, the specific process of establishing the electric vehicle charging probability distribution function group for the prediction period is:
[0090] The communication connection status between a charging pile used during charging and the power grid server is obtained, represented by r. If the charging pile and the power grid server are communicating normally, r = 1, otherwise, r = 0; the distribution probability p of the predicted time is obtained from the best probability distribution function of different types of electric vehicle charging time prediction data in different urban areas. m,e,t , calculate the predicted charging time T required to fully charge the electric vehicle of the mth urban area and the eth type at the tth moment m,e,t ;
[0091] T m,e,t The calculation formula is:
[0092]
[0093] C f It represents the battery capacity of the electric vehicle connected to the charging pile obtained through the power grid server, C l,m,e is the remaining power prediction data of the electric vehicle of the e-th type in the m-th urban area at the charging time; P m,e,t represents the charging power of the charging pile used by the e-th type of electric vehicle in the m-th urban area at the t-th moment, P m,e,t It is equal to the historical charging power of the corresponding type of electric vehicles of the charging pile in each prediction period;
[0094] Calculate the following formula:
[0095]
[0096] Since different types of electric vehicles in different regions have different communication connection conditions between charging piles and power grid servers at different times, optimal probability distribution functions, battery capacities, charging times, and charging powers, ordinary technicians in this field can easily obtain a group of electric vehicle charging probability distribution functions for different regions in predicted time periods by repeating the above steps for all types of electric vehicles in all regions based on the optimal probability distribution function of the region, the communication connection status between the charging pile and the power grid server, battery capacity, and the charging power of the battery and charging pile.
[0097] It should be noted that, in order to facilitate the prediction of the charging load of electric vehicles by time period, in the implementation, several prediction time periods are preset in the power grid server; in this embodiment, in a day, starting from 0 o'clock, every half an hour is divided into a prediction time period, and a total of 48 time periods are set in a day;
[0098] Step 5: Obtain the charging power in the prediction period based on the charging probability distribution function group in the prediction period, and predict the charging load of electric vehicles of the corresponding type in the corresponding prediction period in different areas of the corresponding city.
[0099] It should be noted that the input of the prediction period charging probability distribution function group is a number of pre-set prediction periods corresponding to a certain vehicle type, and the output of the prediction period charging probability distribution function group is the prediction period charging probability of the corresponding type of electric vehicle corresponding to the prediction period.
[0100] Preferably, step 5 specifically includes:
[0101] Get the forecast period, input the forecast period, city area and electric vehicle type into the forecast period charging probability distribution function group, and output the forecast period charging probability f m,e,t ; Calculate the charging power P during the forecast period t The product of the charging probability during the forecast period f m,e,t , as the predicted charging load C of the corresponding type of electric vehicles in the corresponding prediction period in the corresponding urban area m,e,t .
[0102] Preferably, the method further comprises step 6: calculating the total load of electric vehicles in different urban areas corresponding to the forecast period, and determining whether it is credible;
[0103] Step 6.1, obtaining the number of different types of electric vehicles in the urban area, and obtaining information on the number of electric vehicles in the urban area.
[0104] Step 6.2, based on the information on the number of electric vehicles in the urban area and the charging loads of different types of electric vehicles, calculate the total load of electric vehicles in the urban area during the forecast period.
[0105] Preferably, the formula for calculating the total load of electric vehicles in a certain city area during the forecast period m in step 6.2 is:
[0106]
[0107] Among them, C m,E,t represents the total load of electric vehicles in the urban area during the forecast period, E represents the number of types of electric vehicles in the urban area, and n m,e represents the number of electric vehicles of the eth type in the mth area.
[0108] It should be noted that the power grid server can obtain the number of different types of electric vehicles in the urban area by mobilizing the data interface with the vehicle management department, thereby obtaining the number of electric vehicles of each type, which is recorded as the number of electric vehicles in the urban area.
[0109] Step 6.3, statistics are collected on the total load of electric vehicles in the urban area during several forecast periods, and the standard deviation N and the mathematical expectation S are obtained as statistical results.
[0110] Step 6.4, based on the statistical results, it is determined whether the total load of electric vehicles in the forecast period of the city area at different time periods converges. If so, it is considered that the total load of electric vehicles in the forecast period of the city area at different time periods is credible.
[0111] The convergence equation used to determine convergence in step 6.4 is:
[0112]
[0113] Where k is the number of iterations, N is the standard deviation of the total load of electric vehicles in several forecast periods, and S is the mathematical expectation of the total load of electric vehicles in several forecast periods.
[0114] It should be noted that the corresponding convergence threshold is preset in the power grid server. In this embodiment, the convergence threshold is preferably 0.0004. In implementation, after calculating the function value Q of the convergence function, it is further determined whether the function value Q is less than the convergence threshold. If so, it is determined that the total electric vehicle load in the urban area forecast period in different time periods is credible.
[0115] Embodiment 2 of the present invention provides an electric vehicle charging load prediction device, using the method described in Embodiment 1, specifically comprising:
[0116] A data acquisition module, used to acquire charging time data and remaining power data of different types of electric vehicles in different preset urban areas; the urban areas at least include living areas, commercial areas and production areas; the types of electric vehicles at least include private travel vehicles and work transportation vehicles;
[0117] A function processing module, used to process the charging time data and the remaining power data at the charging time respectively based on different preset probability distribution functions to obtain processing results; judge the processing results to determine the best probability distribution function;
[0118] A data generation module, configured to process the input urban area and type of electric vehicle based on the optimal probability distribution function to obtain charging time prediction data and remaining power prediction data of the type of electric vehicle in the urban area;
[0119] A function group establishment module, used to establish a charging probability distribution function group for a prediction period based on the charging time prediction data, the remaining power prediction data at the charging time, and the acquired online status of the charging pile;
[0120] The load prediction module is used to predict the charging load of electric vehicles of corresponding types in corresponding prediction periods in different urban areas based on the charging probability distribution function group of the prediction period and the obtained charging power of the prediction period.
[0121] Can be applied to Figure 2 In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server, or it can be placed on the cloud or other network servers. Among them, the terminal can be but not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server can be implemented as an independent server or a server cluster consisting of multiple servers.
[0122] It should be noted that each module in the above-mentioned electric vehicle charging load prediction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned different modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.
[0123] Embodiment 3 of the present invention provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the charging load of an electric vehicle is implemented.
[0124] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0125] Embodiment 4 of the present invention provides a computer-readable storage medium, such as Figure 5 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned different method embodiments are implemented.
[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by different parties.
[0127] It should be noted that the terms "first", "second", etc. in the specification and claims and drawings of this article are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0128] In this article, the term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship.
[0129] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.
[0130] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0131] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0132] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.
[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A method for predicting electric vehicle charging load, characterized in that: The specific steps include: Step 1, obtaining charging time data and remaining power data of different types of electric vehicles in different urban areas; Step 2, processing the charging time data and the remaining power data at the charging time based on different types of probability distribution functions of different preset urban areas, respectively, to obtain quantified results, comparing the quantified results obtained according to different probability distribution functions with the probability distribution of the actual electric vehicle charging time and the remaining power at the charging time, and determining the optimal probability distribution function of the charging time data and the remaining power data at the charging time of each type of electric vehicle in each urban area; Step 3, processing different urban areas and types of electric vehicles through the optimal probability distribution function, and obtaining charging time prediction data and remaining power prediction data corresponding to different types of electric vehicles in different urban areas; Step 4: Based on the charging time prediction data, the remaining power prediction data at the charging time, and the acquired online status of the charging piles, a charging probability distribution function group for the prediction period is established; Step 5: Based on the prediction period charging probability distribution function group and the obtained prediction period charging power, the charging load of electric vehicles of corresponding types in different urban areas corresponding to the prediction period is predicted.
2. The method for predicting charging load of an electric vehicle according to claim 1, characterized in that: In step 1, the urban area includes at least living areas, commercial areas and production areas; the types of electric vehicles include at least private travel vehicles and work transport vehicles; the charging time data is the time recording data when the electric vehicle charging pile charges the electric vehicle, and the charging time remaining power data is the remaining power of the electric vehicle at the beginning of the charging time.
3. The method for predicting charging load of an electric vehicle according to claim 1, characterized in that: In step 2, the preset different probability distribution functions include at least Fourier probability distribution function, normal distribution probability function and Gaussian probability distribution function; the probability distribution function includes charging time data probability distribution function and charging time remaining power data probability distribution function, the horizontal axis of the charging time data probability distribution function is the charging time data, and the vertical axis is the first probability; the horizontal axis of the charging time remaining power data probability distribution function is the charging time remaining power data, and the vertical axis is the second probability.
4. The method for predicting charging load of an electric vehicle according to claim 3, characterized in that: In step 2, the processing of the charging time data and the remaining power data at the charging time based on different types of probability distribution functions preset in different urban areas specifically includes: The charging time data and the remaining power data at the charging time are respectively input into different types of probability distribution functions to obtain the probability distribution results under the corresponding probability distribution functions; the fitting results corresponding to different probability distribution functions are obtained based on the preset fitting function type; based on the fitting results and the mean of the probability distribution results, the quantization results corresponding to different probability distribution functions are calculated through the preset quantization function, and the optimal probability distribution function is determined based on the quantization results.
5. The method for predicting charging load of an electric vehicle according to claim 4, characterized in that: The quantization function is specifically: Quantization function: take integer points on the probability distribution function curve and take the value of each point; In the formula, λ represents the type of probability distribution function, λ={1,2,3}, which represent Fourier probability distribution function, normal distribution probability function, Gaussian probability distribution function respectively, y 0,i,λ represents the λth probability distribution result of the i-th point, is the mean of the λth probability distribution, y i,λ is the λth fitting result of the ith point, and n is the total number of data.
6. The method for predicting charging load of an electric vehicle according to claim 4, characterized in that: In step 2, the scheme for determining the optimal probability distribution function specifically includes: The quantified results of the fitting results of different probability distribution functions of different types of electric vehicles in different areas of the city are calculated, and the differences with the preset threshold values are calculated respectively. The probability distribution function corresponding to the quantified result with the smallest difference is recorded as the optimal probability distribution function.
7. The method for predicting charging load of an electric vehicle according to claim 1, characterized in that: The specific steps of step 3 are: calculating the mean of the optimal probability distribution function of different types of electric vehicles in different urban areas as the charging time prediction data and the remaining power prediction data of different types of electric vehicles in different areas of the corresponding city.
8. The method for predicting charging load of an electric vehicle according to claim 1, characterized in that: In step 4, the specific process of establishing the charging probability distribution function group for the prediction period is: The communication connection status between the charging pile used during charging and the power grid server is obtained, represented by r. If the charging pile and the power grid server are communicating normally, r = 1, otherwise, r = 0; the distribution probability p of the predicted time is obtained from the best probability distribution function of the prediction data of different types of electric vehicle charging time in different urban areas. m,e,t , calculate the predicted charging time T required to fully charge the electric vehicle of the e-th type in the m-th urban area at the t-th moment m,e,t ; T m,e,t The calculation formula is: C f It represents the battery capacity of the electric vehicle connected to the charging pile obtained through the power grid server, C l,m,e is the remaining power prediction data of the electric vehicle of the mth urban area and the eth type at the charging time; P m,e,t represents the charging power of the charging pile used by the e-th type of electric vehicle in the m-th urban area at the t-th moment, P m,e,t It is equal to the historical charging power of the corresponding type of electric vehicles of the charging pile in each prediction period; Calculate the following formula: Repeating the above steps for all types of electric vehicles in all regions can obtain the electric vehicle charging probability distribution function group for the forecast period.
9. The method for predicting charging load of an electric vehicle according to claim 1, characterized in that: Step 5 specifically includes: Get the forecast period, input the forecast period, city area and electric vehicle type into the forecast period charging probability distribution function group, and output the forecast period charging probability f m,e,t ; Calculate the charging power P during the forecast period t The product of the charging probability during the forecast period f m,e,t , as the predicted charging load C of the corresponding type of electric vehicles in the corresponding prediction period in the corresponding urban area m,e,t .
10. The method for predicting charging load of an electric vehicle according to claim 1, characterized in that: The method further comprises step 6: calculating the total load of electric vehicles in the corresponding forecast period in different urban areas, and determining whether it is credible; Step 6.1, obtaining the number of different types of electric vehicles in the urban area, and obtaining the number of electric vehicles in the urban area; Step 6.2, based on the number of electric vehicles in the urban area and the charging loads of different types of electric vehicles, calculate the total load of electric vehicles in the urban area during the forecast period; Step 6.3, statistically analyze the total load of electric vehicles in the city area during several forecast periods, and obtain the standard deviation N and the mathematical expectation S as statistical results; Step 6.4, based on the statistical results, it is determined whether the total load of electric vehicles in the forecast period of the city area at different time periods converges. If so, it is considered that the total load of electric vehicles in the forecast period of the city area at different time periods is credible.
11. The method for predicting charging load of an electric vehicle according to claim 10, characterized in that: The formula for calculating the total electric vehicle load in a city area during forecast period m in step 6.2 is: Among them, C m,E,t represents the total load of electric vehicles in the urban area during the forecast period, E represents the number of types of electric vehicles in the urban area, and n m,e represents the number of electric vehicles of the eth type in the mth area.
12. The method for predicting charging load of an electric vehicle according to claim 10, characterized in that: The convergence equation used to determine convergence in step 6.4 is: Where k is the number of iterations, N is the standard deviation of the total load of electric vehicles in several forecast periods, and S is the mathematical expectation of the total load of electric vehicles in several forecast periods.
13. An electric vehicle charging load prediction device, using the method according to any one of claims 1 to 12, characterized in that: A data acquisition module, used to acquire charging time data and remaining power data of different types of electric vehicles in different preset urban areas; the urban areas at least include living areas, commercial areas and production areas; the types of electric vehicles at least include private travel vehicles and work transportation vehicles; A function processing module, used to process the charging time data and the remaining power data at the charging time respectively based on different preset probability distribution functions to obtain processing results; judge the processing results to determine the best probability distribution function; A data generation module, configured to process the input urban area and type of electric vehicle based on the optimal probability distribution function to obtain charging time prediction data and remaining power prediction data of the type of electric vehicle in the urban area; A function group establishment module, used to establish a charging probability distribution function group for a prediction period based on the charging time prediction data, the remaining power prediction data at the charging time, and the acquired online status of the charging pile; The load prediction module is used to predict the charging load of electric vehicles of corresponding types in corresponding prediction periods in different urban areas based on the charging probability distribution function group of the prediction period and the obtained charging power of the prediction period.
14. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.
15. 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 12 are implemented.
