Electric vehicle charging load prediction method and device based on Monte Carlo method

By establishing a probability model of charging and discharging behavior of electric vehicles and using Monte Carlo simulation method to calculate and superimpose the charging load curves of different types of electric vehicles, the problem of not considering the charging characteristics of different types of electric vehicles in the existing technology is solved, and the electric vehicles are improved Accuracy and physical significance of charging load prediction.

CN119029849APending Publication Date: 2024-11-26SHENZHEN POWER SUPPLY BUREAU
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411094298.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing charging load prediction method for electric vehicles based on Monte Carlo simulation method lacks the charging characteristics of different types of electric vehicles, resulting in unclear physical significance of the prediction results.

Method used

By obtaining the charging power, battery capacity and charging and discharging behavior probability models of various types of electric vehicles, the starting charging time and SOC were extracted using the Monte Carlo simulation method, the charging load curves of various types of electric vehicles were calculated, and the charging load curves of each type of electric vehicle were averaged and superimposed. To obtain the total charging load prediction curve for the preset area.

Benefits of technology

The accuracy of electric vehicle charging load prediction is improved, the overall trend of electric vehicle charging load in the region can be characterized, and the problem of not considering the charging characteristics of different types of electric vehicles in the prior art.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119029849A_ABST
    Figure CN119029849A_ABST
Patent Text Reader

Abstract

The invention provides an electric vehicle charging load prediction method and device based on a Monte Carlo method. Comprising the following steps: S1, acquiring a vehicle charging power, a battery capacity and a charging and discharging behavior probability model in an area; s2, setting a simulation frequency threshold value and initializing simulation frequency; s3, setting the total number of vehicles and the proportion of each vehicle; s4, acquiring a charging load curve of each vehicle according to the initial SOC obtained by sampling, the charging power of the electric vehicle and the charging duration, and according to the initial charging moment, the charging power and the charging duration; s5, determining that a simulation frequency threshold value is reached, executing S6, and executing S4 when the simulation frequency threshold value is not reached; and S6, averaging each charging load curve to obtain a daily charging load curve, and superposing a plurality of daily charging load curves to obtain a total charging load prediction curve in the region. The problem that charging characteristics of different types of electric vehicles are not considered in an electric vehicle charging load prediction method in the prior art is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicle charging load prediction based on the Monte Carlo method, and in particular, to a method and device for predicting electric vehicle charging load based on the Monte Carlo method. Background Art

[0002] Against the background of rapid development of electric vehicles, large-scale charging of electric vehicles will have a certain impact on the power grid. Electric vehicle charging load forecasting technology is conducive to planning the future development trend of electric vehicles and improving the security of the power grid.

[0003] At present, the prediction of electric vehicle charging load mostly adopts deep machine learning, fuzzy theory, artificial bee colony, Monte Carlo and other methods. The scheme closest to this scheme is the electric vehicle charging load prediction method based on Monte Carlo simulation method. The number of simulations is set to determine the vehicle charging behavior, and the charging load curve is accumulated to obtain the overall charging load. It is judged whether the number of simulations currently is greater than the set number of simulations; it is judged whether the overall charging load as the simulation result converges; if it converges, the simulation result is output; if not, it returns to reset the number of simulations.

[0004] The electric vehicle charging load prediction method based on the Monte Carlo simulation method lacks consideration of the charging characteristics of different types of electric vehicles, and the actual physical meaning of the resulting charging load prediction curve is unclear. Summary of the invention

[0005] The main purpose of the present application is to provide a method and device for predicting the charging load of electric vehicles based on the Monte Carlo method, so as to at least solve the problem that the electric vehicle charging load prediction method based on the Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for predicting charging load of electric vehicles based on Monte Carlo method is provided, comprising: step S1: obtaining charging power, battery capacity and charging and discharging behavior probability models of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; step S2: setting a simulation number threshold and initializing the simulation number to 1; step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles; step S4: extracting the starting charging time and starting SOC of each type of the electric vehicle by using Monte Carlo simulation method, and then calculating the starting charging time and starting SOC of the electric vehicle according to the sampling obtained starting SOC. C, and the corresponding charging power and charging demand of the electric vehicle to obtain the required charging time, so as to obtain the charging load curve of each type of the electric vehicle according to the starting charging time, the charging power and the required charging time; step S5: determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if not, return to execute step S4, and the number of simulations after executing step S4 once is increased by 1; step S6: average the charging load curves of each type of the electric vehicle to obtain the daily charging load curves of each type of the electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area.

[0007] Optionally, step S4 includes: performing the following steps for each type of the electric vehicle until the charging load curves of all types of the electric vehicles are obtained, step S41: obtaining the total number of the electric vehicles of the target type; step S42: initializing k=0; step S43: executing k=k+1; step S44: extracting the starting charging time and starting SOC of the electric vehicle of a target type, and obtaining the charging time required for the electric vehicle of the target type, so as to obtain the charging load curve of the electric vehicle of the target type; step S45: judging whether k>N holds, wherein N represents the total number of the electric vehicles of the target type; step S46: if k>N holds, switching to determining the charging load curve of another type of the electric vehicle, if k>N does not hold, returning to step S43.

[0008] Optionally, the probability model of the starting charging time is: Wherein, fs(tin) is the probability density function of the starting charging time tin; μ s is the expected time of starting charging; s is the standard deviation of the starting charging time; the starting SOC probability model is: Where: f s (SOC(t in )) is the probability density function of the initial SOC; μs is the expected initial SOC; s is the standard deviation of the initial SOC, μ s and σ s Varies with vehicle type.

[0009] Optionally, the charging and discharging behavior probability model further includes a probability model of the electric vehicle's exit time, and the probability model of the electric vehicle's exit time conforms to the following normal distribution: Where: fs(tout) is the probability density function of the termination time tout, μ s is the expected time to terminate charging, σ s is the standard deviation of the charging termination time, μ s and σ s Varies with vehicle type.

[0010] Optionally, the method also includes: obtaining relevant regional parameters, including at least one of the following: the total number of people in the area, the volume and number of consumption places in the area, climate factors, traffic factors, per capita income level, and the number of registered electric vehicles; and dividing the area according to the relevant regional parameters.

[0011] Optionally, after averaging the charging load curves for each type of the electric vehicle to obtain the daily charging load curves for each type of the electric vehicle, and superimposing multiple daily charging load curves to obtain the total charging load prediction curve for the preset area, the method further includes: obtaining the total number of charging piles in the preset area; determining whether additional charging piles are needed based on the total charging load prediction curve for the preset area and the total number of charging piles, and if additional charging piles are needed, issuing a prompt message, the prompt message including at least one of the following: adding charging piles to charging and swapping stations, adding charging piles to bus parking lots, and adding charging piles to special parking lots.

[0012] Optionally, whether additional charging piles need to be added is determined based on the total charging load prediction curve of the preset area and the total number of the charging piles, including: when the total number of charging piles is difficult to meet the charging load represented by the total charging load prediction curve of the preset area, determining the need to add charging piles, wherein whether the need is met takes into account charging pile failure factors.

[0013] According to another aspect of the present application, there is provided an electric vehicle charging load prediction device based on the Monte Carlo method, comprising: an acquisition unit, configured to execute step S1: acquiring the charging power, battery capacity and charging and discharging behavior probability model of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model comprises a starting charging time probability model and a starting SOC probability model; a first setting unit, configured to execute step S2: setting a simulation number threshold and initializing the simulation number to 1; a second setting unit, configured to execute step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles; a processing unit, configured to execute step S4: extracting the starting charging time and starting SOC of each type of the electric vehicle by using the Monte Carlo simulation method, and then obtaining the starting charging time and starting SOC of the electric vehicle according to the sampling; The starting SOC, and the corresponding charging power and charging demand of the electric vehicle are used to obtain the required charging time, so as to obtain the charging load curve of each type of the electric vehicle according to the starting charging time, the charging power and the required charging time; a determination unit is used to execute step S5: determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if not, return to execute step S4, and the number of simulations after executing step S4 once is increased by 1; a prediction unit is used to execute step S6: average the charging load curves of each type of the electric vehicle to obtain the daily charging load curves of each type of the electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the electric vehicle charging load prediction methods based on the Monte Carlo method.

[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the electric vehicle charging load prediction methods based on the Monte Carlo method.

[0016] Applying the technical solution of the present application, step S1: obtaining the charging power, battery capacity and charging and discharging behavior probability model of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; step S2: setting a simulation number threshold and initializing the simulation number to 1; step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles; step S4: using the Monte Carlo simulation method to extract the starting charging time and starting SOC of each type of electric vehicle, and then obtaining the required charging time according to the sampled starting SOC, and the corresponding charging power and charging demand of the electric vehicle, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, charging power and charging time; step S5: determining whether the number of simulations reaches the simulation number threshold, if yes, executing step S6, if not, returning to executing step S4, and executing step S4 once The number of simulations is increased by 1; step S6: averaging the charging load curves of each type of electric vehicle to obtain the daily charging load curves of each type of electric vehicle, and superimposing multiple daily charging load curves to obtain the total charging load prediction curve of the preset area. By establishing a probability model of electric vehicle charging and discharging behavior, the accuracy of electric vehicle charging load prediction is effectively improved, and electric vehicles are classified and processed, and the charging characteristics of different types of electric vehicles are summarized. The obtained electric vehicle charging load curve can characterize the overall trend of electric vehicle charging load in the region, and solve the problem that the electric vehicle charging load prediction method based on Monte Carlo simulation method in the existing technology lacks consideration of the charging characteristics of different types of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing an electric vehicle charging load prediction method based on a Monte Carlo method provided in an embodiment of the present application is shown;

[0019] Figure 2 A flow chart of a method for predicting charging load of electric vehicles based on the Monte Carlo method according to an embodiment of the present application is shown;

[0020] Figure 3 A schematic diagram of a daily charging load curve of a private electric vehicle provided according to an embodiment of the present application is shown;

[0021] Figure 4 A schematic diagram of a daily charging load curve of a rental electric vehicle provided according to an embodiment of the present application is shown;

[0022] Figure 5 A schematic diagram of a daily charging load curve of an electric bus provided according to an embodiment of the present application is shown;

[0023] Figure 6 A schematic diagram of a daily charging load curve of a public electric vehicle provided according to an embodiment of the present application is shown;

[0024] Figure 7 A schematic diagram of a charging load curve of 1,200 electric vehicles in a certain area on a weekday is shown according to an embodiment of the present application;

[0025] Figure 8 A flow chart of calculating daily charging loads of various types of electric vehicles based on Monte Carlo simulation according to an embodiment of the present application is shown;

[0026] Fig. 9 A structural block diagram of an electric vehicle charging load prediction device based on the Monte Carlo method provided according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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 devices.

[0030] As introduced in the background technology, the electric vehicle charging load prediction method based on the Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles. In order to solve the problem that the electric vehicle charging load prediction method based on the Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles, the embodiments of the present application provide an electric vehicle charging load prediction method and device based on the Monte Carlo method.

[0031] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0032] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal of an electric vehicle charging load prediction method based on the Monte Carlo method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU (Microcontroller Unit) or a programmable logic device FPGA (Field-Programmable Gate Array, programmable logic device)) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0033] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the electric vehicle charging load prediction method based on the Monte Carlo method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] In this embodiment, a method for predicting charging load of electric vehicles based on the Monte Carlo method is provided, which runs on a mobile terminal, a computer terminal or a similar computing device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] Figure 2 FIG. 1 is a flow chart of a method for predicting charging load of an electric vehicle based on the Monte Carlo method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0037] Step S1: obtaining charging power, battery capacity and charging and discharging behavior probability models of various types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC (State of Charge, the charge state of the battery, usually expressed as a percentage of the remaining charge of the battery, used to display the current usage of the battery and help users understand the remaining capacity of the battery) probability model;

[0038] Among them, the various types of electric vehicles include private electric vehicles, rental electric vehicles, bus electric vehicles, and official electric vehicles.

[0039] Step S2: setting the simulation times threshold and initializing the simulation times to 1;

[0040] The simulation times threshold can be set to 100, 150, 200, etc.

[0041] Step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles;

[0042] For example, the total number of electric vehicles can be set to 1,200, with private electric vehicles accounting for 84%, rental electric vehicles accounting for 3%, public transportation electric vehicles accounting for 1%, and official electric vehicles accounting for 12%.

[0043] Step S4: using the Monte Carlo simulation method to extract the starting charging time and starting SOC of each type of electric vehicle, and then obtaining the required charging time according to the sampled starting SOC, the corresponding charging power and charging demand of the electric vehicle, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, charging power and charging time;

[0044] Among them, the charging power, starting charging time and starting SOC of different types of vehicles are independent of each other;

[0045] This step determines the charging load curves of different types of vehicles according to the charging power, starting charging time and starting SOC of different types of vehicles.

[0046] Step S5: Determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if no, return to execute step S4, and after executing step S4 once, the number of simulations increases by 1;

[0047] Specifically, when the number of simulations does not reach the simulation threshold, step S4 is continued to be executed, and the number of simulations is increased by 1, until the number of simulations reaches the simulation threshold, and then step S6 is executed.

[0048] Step S6: averaging the charging load curves of each type of electric vehicle to obtain the daily charging load curves of each type of electric vehicle, and superimposing multiple daily charging load curves to obtain a total charging load prediction curve for a preset area.

[0049] Among them, the daily charging load curves of various types of electric vehicles are as follows: Figure 3 , Figure 4 , Figure 5 and Figure 6 As shown, Figure 3 This is a schematic diagram of the daily charging load curve of private electric vehicles. Figure 4 This is a schematic diagram of the daily charging load curve of rental electric vehicles. Figure 5 This is a schematic diagram of the daily charging load curve of electric buses. Figure 6 Schematic diagram of the daily charging load curve for official electric vehicles.

[0050] This method superimposes multiple daily charging load curves of various types of vehicles to obtain a total charging load prediction curve for a preset area, such as Figure 7 As shown, Figure 7 This is a schematic diagram of the charging load curve of 1,200 electric vehicles in a certain area on weekdays.

[0051] Through this embodiment, step S1: obtain the charging power, battery capacity and charging and discharging behavior probability model of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; step S2: set a simulation number threshold and initialize the simulation number to 1; step S3: set the total number of electric vehicles and the proportion of each type of electric vehicles; step S4: use the Monte Carlo simulation method to extract the starting charging time and starting SOC of each type of electric vehicle, and then obtain the required charging time according to the sampled starting SOC, and the corresponding charging power and charging demand of the electric vehicle, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, charging power and charging time; step S5: determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if not, return to execute step S4, and execute step S4 once, the number of simulations is increased by 1; step S6: average the charging load curves of each type of electric vehicle to obtain the daily charging load curves of each type of electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area. By establishing a probability model of electric vehicle charging and discharging behavior, the accuracy of electric vehicle charging load prediction is effectively improved, and electric vehicles are classified and processed, and the charging characteristics of different types of electric vehicles are summarized. The obtained electric vehicle charging load curve can characterize the overall trend of electric vehicle charging load in the region, and solve the problem that the electric vehicle charging load prediction method based on Monte Carlo simulation method in the existing technology lacks consideration of the charging characteristics of different types of electric vehicles.

[0052] In the specific implementation process, step S4 includes: executing the following steps for each type of electric vehicle until the charging load curves of all types of electric vehicles are obtained, step S41: obtaining the total number of electric vehicles of the target type; step S42: initializing k=0; step S43: executing k=k+1; step S44: extracting the starting charging time and starting SOC of an electric vehicle of a target type, and obtaining the charging time required for the electric vehicle of the target type, so as to obtain the charging load curve of the electric vehicle of the target type; step S45: judging whether k>N is established, wherein N represents the total number of electric vehicles of the target type; step S46: if k>N is established, switching to determine the charging load curve of another type of electric vehicle, if k>N is not established, returning to step S43.

[0053] The method first determines the total number of first type electric vehicles, and then performs a simulation operation, first initializing the number of simulations to 0, extracting the starting charging time and starting SOC of the first type electric vehicle, and obtaining the time required for charging the first type electric vehicle, determining the charging load curve of the electric vehicle based on the starting charging time and starting SOC of the first type electric vehicle, and the time required for charging, and then determining whether the number of simulations is greater than the total number of first type electric vehicles. If it is determined that the number of simulations is less than or equal to the total number of first type electric vehicles, continue to execute simulation step S43 until it is determined that the number of simulations is greater than the total number of first type electric vehicles, and continue to simulate the second type electric vehicle until all types of electric vehicles have completed the simulation and then obtain the charging load curves of all types of electric vehicles.

[0054] Specifically, the probability model of the starting charging time is: Among them, f s (t in ) is the starting charging time t in The probability density function, μ s is the expected time of starting charging, σ s is the standard deviation of the starting charging time; the starting SOC probability model is: Where: fs(SOC(tin)) is the probability density function of the initial SOC, μ s is the expected initial SOC, σ s is the standard deviation of the initial SOC, μ s and σ s Varies with vehicle type.

[0055] Among them, since the starting charging time of different electric vehicles is random, there is a probability that the user will charge the electric vehicle when the electric vehicle is low in power or at the end of a journey. According to a large number of independent random variables, they tend to be normally distributed after appropriate standardization. Therefore, as the scale of electric vehicles expands, their charging behavior and charging load will also have certain regularity. The normal distribution can be used to fit the probability model of the starting charging time;

[0056] Among them, the state of charge of the electric vehicle when it is connected is closely related to the daily mileage of the electric vehicle. The initial SOC also obeys the normal distribution, and the normal distribution can also be used to fit the initial SOC probability model. Due to the differences in driving characteristics of different types of vehicles, μ s and σ s Varies with vehicle type.

[0057] More specifically, the probability model of charging and discharging behavior also includes a probability model of the time when the electric vehicle leaves the station, and the probability model of the time when the electric vehicle leaves the station conforms to the following normal distribution: Where: fs(tout) is the probability density function of the termination time tout, μ s is the expected time to terminate charging, σ s is the standard deviation of the termination time of charging, μ s and σ s Varies with vehicle type.

[0058] This method uses a probability model of the time when the electric vehicle leaves the station to simulate the probability distribution of the time when the vehicle stops charging, so as to simulate the charging behavior of different electric vehicles.

[0059] Among them, the probability model of the electric vehicle's departure time is related to the battery capacity of different types of electric vehicles. The expectation of the termination time of charging also conforms to the normal distribution. The normal distribution is used to fit the probability model of the electric vehicle's departure time.

[0060] Furthermore, the method further includes: obtaining relevant regional parameters, including at least one of the following: the total number of people in the area, the volume and number of consumption places in the area, climate factors, traffic factors, per capita income level, and the number of registered electric vehicles; and dividing the area according to the relevant regional parameters. The method divides the area by obtaining regional relevant parameters, which can make the regional division more reasonable.

[0061] Furthermore, after averaging the charging load curves for each type of electric vehicle to obtain the daily charging load curves for each type of electric vehicle, and superimposing multiple daily charging load curves to obtain the total charging load prediction curve for the preset area, the method also includes: obtaining the total number of charging piles in the preset area; determining whether additional charging piles are needed based on the total charging load prediction curve for the preset area and the total number of charging piles, and if additional charging piles are needed, issuing a prompt message, the prompt message including at least one of the following: adding charging piles to charging and swapping stations, adding charging piles to bus parking lots, and adding charging piles to special parking lots.

[0062] Among them, the charging piles in the dedicated parking lot can be the charging piles in the community parking lot, the charging piles in the workplace parking lot, and the charging piles in the shopping mall parking lot; the method determines whether additional charging piles are needed based on the relationship between the number of charging piles in the preset area and the total charging load prediction curve.

[0063] Specifically, based on the total charging load prediction curve of the preset area and the total number of charging piles, determine whether additional charging piles are needed, including: when the total number of charging piles is difficult to meet the charging load represented by the total charging load prediction curve of the preset area, determine the need to add charging piles, wherein whether the need is met takes into account the failure factor of the charging piles.

[0064] For example, if there are 10 charging piles with fault factors, one or two of them may not be used in different time periods.

[0065] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the electric vehicle charging load prediction method based on the Monte Carlo method of the present application will be described in detail below in combination with specific embodiments.

[0066] This embodiment relates to a specific method for predicting charging load of electric vehicles based on the Monte Carlo method. Figure 8 As shown, it specifically includes the following contents:

[0067] Among them, the Monte Carlo method is a numerical calculation method that uses random numbers and probability statistics to solve problems. It approximates the solution to the problem by random sampling, and is usually used to solve complex mathematical problems or simulate actual systems. The core idea of ​​the Monte Carlo method is to approximate the solution to the problem through a large number of random samplings, thereby obtaining more accurate results.

[0068] First, the charging power, battery capacity and charging and discharging behavior probability models of various types of electric vehicles in a preset area are obtained, where the various types of electric vehicles include private electric vehicles, public transportation electric vehicles, rental electric vehicles, and official electric vehicles. The charging and discharging behavior probability models include the probability model of the starting charging time, the probability model of the starting SOC and the probability model of the electric vehicle exit time;

[0069] Among them, the charging load of electric vehicles is determined by multiple factors such as the starting charging time, charging time, departure time, starting power, expected power, battery capacity, charging power, etc. The Monte Carlo simulation method is used to determine the parameters of multiple electric vehicles.

[0070] Construct a probability model for the start charging time, the start charging time t inIt is random. There is a certain probability of charging at the end of each trip of the user. Since a large number of independent random variables tend to be normally distributed after appropriate standardization, as the scale of electric vehicles expands, their charging behavior and charging load will also have certain regularity. The normal distribution can be used to fit the probability distribution model of the starting charging time; since electric private cars are mainly used to meet the daily travel needs of electric vehicle users for work and entertainment, the travel and charging time of electric vehicle users have typical regularities. During the working day, the charging period of private cars can be divided into daytime charging period and nighttime charging period. Among them, the daytime charging process is mainly completed on commercial charging piles, and the charging locations are concentrated in public charging stations in workplaces and commercial parking lots; nighttime charging is generally the period of charging at the end of the last trip of the day, and the charging locations are generally community charging piles and private charging piles. The average daily mileage of private cars generally does not exceed the range of electric vehicles. Therefore, assuming that charging once a day can basically meet the daily use needs of car owners, the user's starting charging time t in It can be considered as the time when the user arrives at the charging station. Based on the relevant statistical data, preprocessing is performed to obtain the travel-related characteristic parameters of electric vehicle users. By fitting the data of travel and charging behavior, t in The probability distribution of the starting charging time probability model is as follows: Among them, f s (t in ) is the starting charging time t in The probability density function, μ s is the expected starting charging time, σ s is the standard deviation of the starting charging time;

[0071] Construct a probability model for the time when electric vehicles leave the station, the time when electric vehicles travel, that is, the time when charging is terminated t out , also obeys the normal distribution, and the probability model of the electric vehicle's departure time conforms to the following normal distribution:

[0072] Where: f s (t out ) is the probability density function of the charging termination time tout, μ s is the expected time to terminate charging, σ s is the standard deviation of the termination time of charging, μ s and σ s Varies with vehicle type.

[0073] Construct the starting SOC probability model of electric vehicles. The state of charge of electric vehicles when they are connected is closely related to the daily mileage of electric vehicles. The starting SOC probability model is: Where: fs(SOC(tin)) is the probability density function of the initial SOC, μ s is the expected initial SOC, σ s is the standard deviation of the initial SOC, μ s and σ s Varies with vehicle type.

[0074] Different types of electric vehicles have different on-board power battery capacities, so the number of daily charging times and charging methods are different. For example, official electric vehicles only need to be charged once a day. A comparison of the charging characteristics of various types of electric vehicles is shown in Table 1.

[0075] Table 1

[0076]

[0077]

[0078] After creating the probability model of the starting charging time, the probability model of the starting SOC and the probability model of the electric vehicle exit time, the simulation is started, the number of simulations is initialized to 1, and the simulation threshold is set, wherein the simulation threshold corresponds to the number of electric vehicles of each type, the total number of electric vehicles and the proportion of electric vehicles of each type are set, wherein the proportion of the number of electric vehicles that can participate in V2G (Vehicle-to-Grid, abbreviated as Vehicle-to-Grid, is a technology that allows electric vehicles to be connected to the grid and release the electric energy stored in the batteries of electric vehicles to the grid, thereby realizing a two-way flow of energy. This technology can help balance the load of the grid, improve energy efficiency, and provide an additional source of income for electric vehicle users) in a certain area occupied by private cars, taxis, buses, and official cars is set to 0.84, 0.03, 0.01, and 0.12 respectively;

[0079] The Monte Carlo simulation method is used to extract the starting charging time and starting SOC of each type of electric vehicle, and then the charging time required for the electric vehicle is obtained according to the sampled starting SOC, the corresponding charging power and the charging demand of the electric vehicle, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, the charging power and the charging time required. The specific steps for obtaining the charging load curve of the electric vehicle are as follows:

[0080] Step S41: Obtain the total number of electric vehicles of the target type;

[0081] Step S42: Initialize k=0;

[0082] Step S43: execute k=k+1;

[0083] Step S44: extracting a starting charging time and a starting SOC of an electric vehicle of a target type, and obtaining a charging time required for the electric vehicle of the target type, so as to obtain a charging load curve of the electric vehicle of the target type;

[0084] Step S45: determining whether k>N holds, where N represents the total number of electric vehicles of the target type;

[0085] Step S46: If k>N holds, the process proceeds to determine a charging load curve for another type of electric vehicle; if k>N does not hold, the process returns to step S43.

[0086] Perform the above steps for each type of electric vehicle until the charging load curves of all types of electric vehicles are obtained;

[0087] After obtaining the charging load curves of all types of electric vehicles, the average values ​​of the charging load curves of all types of electric vehicles are taken to obtain the daily charging load curves of each type of electric vehicle. The load curves of each type are then superimposed to obtain the total charging load prediction curve of the preset area.

[0088] In addition, there are many factors that affect the charging power of electric vehicles. Therefore, before calculating the charging load, some realistic assumptions and related parameter settings need to be made based on the current development status of electric vehicles:

[0089] For example:

[0090] 1) Parameters such as the daily charging times, approximate charging periods, charging probabilities in each period, starting SOC distribution, starting charging time distribution, and charging methods of four types of electric vehicles;

[0091] 2) The rated capacity of the on-board battery used in taxis and buses is 200kW·h, the rated capacity of the on-board battery used in official cars is 100kW·h, and the rated capacity of the on-board battery used in private cars is 80kW·h;

[0092] 3) The conventional and fast charging powers of private cars are 7kW and 45kW respectively, the conventional and fast charging powers of taxis are 14kW and 90kW respectively, the conventional and fast charging powers of buses are 21kW and 135kW respectively, and the conventional and fast charging powers of official cars are 7kW and 45kW respectively;

[0093] 4) The proportion of private cars, taxis, buses, and official cars to the number of electric vehicles that can participate in V2G in a certain area is set to 0.84, 0.03, 0.01, and 0.12 respectively.

[0094] 5) The charging power, starting charging time and starting SOC of different types of vehicles are independent of each other;

[0095] 6) The charging time of different types of vehicles is long enough and each charging reaches full power;

[0096] 7) All vehicles are charged using conventional or fast charging methods, ignoring charging efficiency;

[0097] 8) The charging power of each type of electric vehicle is regarded as a constant power model, without the two stages of constant voltage and constant current charging.

[0098] Based on the parameters and related assumptions that have been set, the electric vehicle charging load is calculated every hour, so there are 24 time nodes in a day. The number of Monte Carlo simulations is set to 100. Figure 8 The calculation flow chart of daily charging load of various types of electric vehicles based on Monte Carlo simulation is shown in FIG. The charging load of different types of electric vehicles in the preset area is predicted, and the daily charging load prediction curves of 4 types of electric vehicles in the preset area on weekdays are obtained. Figure 3 , Figure 4 , Figure 5 , Figure 6 As shown, then Figure 3 , Figure 4 , Figure 5 , Figure 6 The charging load curve of 1,200 electric vehicles in the preset area on weekdays is obtained by superposition. The superimposed curve is as follows Figure 7 shown.

[0099] The embodiments of the present application 1. establish a probability model of electric vehicle charging and discharging behavior, including a probability model of the electric vehicle starting charging time, a probability model of the electric vehicle exiting time, and a probability model of the electric vehicle starting SOC, summarize and analyze the charging characteristics of different types of electric vehicles, and provide theoretical support for the prediction of electric vehicle charging load; adopt a Monte Carlo simulation method to calculate the daily charging load curve of different types of electric vehicles in a preset area according to the charging behavior and charging characteristics of the electric vehicles, and average the charging loads of different types of electric vehicles, so as to obtain the total charging load curve of electric vehicles in the area, which has the advantages of clear algorithm, small calculation amount, strong rationality, etc.

[0100] The embodiment of the present application also provides an electric vehicle charging load prediction device based on the Monte Carlo method. It should be noted that the electric vehicle charging load prediction device based on the Monte Carlo method in the embodiment of the present application can be used to execute the electric vehicle charging load prediction method based on the Monte Carlo method provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0101] The following is an introduction to the electric vehicle charging load prediction device based on the Monte Carlo method provided in an embodiment of the present application.

[0102] Fig. 9 Schematic diagram of an electric vehicle charging load prediction device based on the Monte Carlo method according to an embodiment of the present application. Fig. 9 As shown, the device comprises:

[0103] The first acquisition unit 91 is used to execute step S1: acquiring the charging power, battery capacity and charging and discharging behavior probability model of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model;

[0104] Among them, the various types of electric vehicles include private electric vehicles, rental electric vehicles, bus electric vehicles, and official electric vehicles.

[0105] The first setting unit 92 is used to execute step S2: setting a simulation times threshold and initializing the simulation times to 1;

[0106] The simulation times threshold can be set to 100, 150, 200, etc.

[0107] The second setting unit 93 is used to execute step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles;

[0108] For example, the total number of electric vehicles can be set to 1,200, with private electric vehicles accounting for 84%, rental electric vehicles accounting for 3%, public transportation electric vehicles accounting for 1%, and official electric vehicles accounting for 12%.

[0109] The processing unit 94 is used to execute step S4: extract the starting charging time and starting SOC of each type of electric vehicle by using the Monte Carlo simulation method, and then obtain the required charging time according to the sampled starting SOC, the charging power and the charging demand of the corresponding electric vehicle, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, the charging power and the charging time;

[0110] Among them, the charging power, starting charging time and starting SOC of different types of vehicles are independent of each other;

[0111] Specifically, the charging load curves of the different types of vehicles are determined according to the charging power, the starting charging time and the starting SOC of the different types of vehicles.

[0112] The determination unit 95 is used to execute step S5: determine whether the number of simulations reaches the simulation number threshold, and if yes, execute step S6; if no, return to execute step S4, and after executing step S4 once, the number of simulations is increased by 1;

[0113] Specifically, when the number of simulations does not reach the simulation threshold, step S4 is continued to be executed, and the number of simulations is increased by 1, until the number of simulations reaches the simulation threshold, and then step S6 is executed.

[0114] The prediction unit 96 is used to execute step S6: average the charging load curves of each type of electric vehicle to obtain the daily charging load curves of each type of electric vehicle, and superimpose multiple daily charging load curves to obtain a total charging load prediction curve for a preset area.

[0115] Specifically, multiple daily charging load curves of various types of vehicles are superimposed to obtain a total charging load prediction curve for a preset area.

[0116] In this embodiment, the first acquisition unit is used to execute step S1: obtain the charging power, battery capacity and charging and discharging behavior probability model of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; the first setting unit is used to execute step S2: set the simulation number threshold and initialize the simulation number to 1; the second setting unit is used to execute step S3: set the total number of electric vehicles and the proportion of each type of electric vehicles; the processing unit is used to execute step S4: use the Monte Carlo simulation method to extract the starting charging time and starting SOC of each type of electric vehicle, and then according to the sampled starting SOC, and the charging power and charging demand of the corresponding electric vehicle to obtain the time required for charging, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, charging power and charging time required; a determination unit is used to execute step S5: determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if not, return to execute step S4, and the number of simulations after executing step S4 once is increased by 1; a prediction unit is used to execute step S6: average the charging load curves of each type of electric vehicle to obtain the daily charging load curves of each type of electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area. By establishing a probability model of electric vehicle charging and discharging behavior, the accuracy of electric vehicle charging load prediction is effectively improved, and electric vehicles are classified and processed, and the charging characteristics of different types of electric vehicles are summarized. The obtained electric vehicle charging load curve can characterize the overall trend of electric vehicle charging load in the region, and solve the problem that the electric vehicle charging load prediction method based on Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles.

[0117] As an optional scheme, the processing unit includes an acquisition module, an initialization module, an execution module, an extraction module, a judgment module, and a first determination module; the acquisition module is used to execute step S41: obtain the total number of electric vehicles of the target type; the initialization module is used for step S42: initialize k=0; the execution module is used to execute step S43: execute k=k+1; the extraction module is used to execute step S44: extract the starting charging time and starting SOC of an electric vehicle of a target type, and obtain the charging time required for the target type of electric vehicle to obtain the charging load curve of the target type of electric vehicle; the judgment module is used to execute step S45: judge whether k>N is established, where N represents the total number of electric vehicles of the target type; the first determination module is used to execute step S46: if k>N is established, switch to determining the charging load curve of another type of electric vehicle, if k>N is not established, return to step S43.

[0118] Specifically, the total number of first type electric vehicles is first determined, and then a simulation operation is performed. The number of simulations is first initialized to 0, and the starting charging time and starting SOC of the first type electric vehicle are extracted, as well as the time required for charging the first type electric vehicle. The charging load curve of the electric vehicle is determined based on the starting charging time and starting SOC of the first type electric vehicle, and the time required for charging. Then, it is determined whether the number of simulations is greater than the total number of first type electric vehicles. When it is determined that the number of simulations is less than or equal to the total number of first type electric vehicles, the simulation step S43 is continued until it is determined that the number of simulations is greater than the total number of first type electric vehicles. The second type electric vehicle is continued to be simulated until all types of electric vehicles have completed the simulation and the charging load curves of all types of electric vehicles are obtained.

[0119] An optional solution is that the probability model of the starting charging time is: Where, fs(tin) is the probability density function of the starting charging time tin; μ s is the expected time of starting charging; s is the standard deviation of the starting charging time; the starting SOC probability model is: Where: f s (SOC(t in )) is the probability density function of the initial SOC; μ s is the expected initial SOC; s is the standard deviation of the initial SOC, μ s and σ s Varies with vehicle type.

[0120] Among them, since the starting charging time of different electric vehicles is random, there is a probability that the user will charge the electric vehicle when the electric vehicle is low in power or at the end of a journey. According to a large number of independent random variables, they tend to be normally distributed after appropriate standardization. Therefore, as the scale of electric vehicles expands, their charging behavior and charging load will also have certain regularity. The normal distribution can be used to fit the probability model of the starting charging time;

[0121] Among them, the state of charge of the electric vehicle when it is connected is closely related to the daily mileage of the electric vehicle. The initial SOC also obeys the normal distribution, and the normal distribution can also be used to fit the initial SOC probability model. Due to the differences in driving characteristics of different types of vehicles, μ s and σ s Varies with vehicle type.

[0122] In an optional solution, the probability model of charging and discharging behavior also includes a probability model of the time when the electric vehicle leaves the station, and the probability model of the time when the electric vehicle leaves the station conforms to the following normal distribution: Where: fs(tout) is the probability density function of the termination time tout, μ s is the expected time to terminate charging, σ s is the standard deviation of the charging termination time, μ s and σ s Varies with vehicle type.

[0123] Among them, the probability model of the electric vehicle's departure time is related to the battery capacity of different types of electric vehicles. The expectation of the termination time of charging also conforms to the normal distribution. The normal distribution is used to fit the probability model of the electric vehicle's departure time.

[0124] In an optional solution, the device further includes a second acquisition unit and a division unit; the second acquisition unit is used to acquire relevant regional parameters, including at least one of the following: the total number of people in the area, the volume and number of consumption places in the area, climate factors, traffic factors, per capita income level, and the number of registered electric vehicles; the division unit is used to divide the area according to the relevant regional parameters. By obtaining the relevant regional parameters to divide the area, the regional division can be made more reasonable.

[0125] An optional solution, the device also includes a third acquisition unit and a prompt unit; the third acquisition unit is used to find the average value of the charging load curve for each type of electric vehicle to obtain the daily charging load curve for each type of electric vehicle, and after superimposing multiple daily charging load curves to obtain the total charging load prediction curve of the preset area, obtain the total number of charging piles in the preset area; the prompt unit is used to determine whether additional charging piles are needed based on the total charging load prediction curve of the preset area and the total number of charging piles, and if additional charging piles are needed, issue a prompt message, the prompt message including at least one of the following: adding charging piles to charging and swapping stations, adding charging piles to bus parking lots, and adding charging piles to special parking lots.

[0126] Among them, the charging piles in the dedicated parking lot can be the charging piles in the community parking lot, the charging piles in the workplace parking lot, and the charging piles in the shopping mall parking lot; whether additional charging piles are needed is determined based on the relationship between the number of charging piles in the preset area and the total charging load prediction curve.

[0127] In an optional solution, the prompt unit includes a second determination module, which is used to determine the need to add charging piles when the total number of charging piles is difficult to meet the charging load represented by the total charging load prediction curve of the preset area, wherein whether the need is met takes into account the failure factor of the charging piles.

[0128] For example, if there are 10 charging piles with fault factors, one or two of them may not be used in different time periods.

[0129] The electric vehicle charging load prediction device based on the Monte Carlo method includes a processor and a memory, and the above units are stored in the memory as program units, and the processor executes the above program units stored in the memory to implement corresponding functions. The above modules are all located in the same processor; or, the above modules are located in different processors in any combination.

[0130] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the problem that the electric vehicle charging load prediction method based on the Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles is solved by adjusting the kernel parameters.

[0131] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0132] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the electric vehicle charging load prediction method based on the Monte Carlo method.

[0133] An embodiment of the present invention provides a processor, which is used to run a program, wherein the electric vehicle charging load prediction method based on the Monte Carlo method is executed when the program is running.

[0134] An embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the electric vehicle charging load prediction method based on the Monte Carlo method is implemented.

[0135] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0136] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes at least the steps of the electric vehicle charging load prediction method based on the Monte Carlo method.

[0137] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0138] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0139] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0140] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0141] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0142] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0143] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0144] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape and disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0145] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0146] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0147] 1) A method for predicting charging load of electric vehicles based on the Monte Carlo method of the present application comprises: step S1: obtaining charging power, battery capacity and charging and discharging behavior probability models of various types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model comprises a starting charging time probability model and a starting SOC probability model; step S2: setting a simulation number threshold and initializing the simulation number to 1; step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles; step S4: extracting the starting charging time and starting SOC of each type of electric vehicle by using the Monte Carlo simulation method, and then calculating the starting SOC according to the sampling obtained. C, and the charging power and charging demand of the corresponding electric vehicle to obtain the time required for charging, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, charging power and charging time required; Step S5: Determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if not, return to execute step S4, and the number of simulations after executing step S4 once is increased by 1; Step S6: Calculate the average value of the charging load curve of each type of electric vehicle to obtain the daily charging load curve of each type of electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area. By establishing a probability model of electric vehicle charging and discharging behavior, the accuracy of electric vehicle charging load prediction is effectively improved, and electric vehicles are classified and processed, and the charging characteristics of different types of electric vehicles are summarized. The obtained electric vehicle charging load curve can characterize the overall trend of electric vehicle charging load in the region, and solve the problem that the electric vehicle charging load prediction method based on Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles.

[0148] 2) The present application discloses an electric vehicle charging load prediction device based on the Monte Carlo method, comprising: an acquisition unit, used to execute step S1: obtain the charging power, battery capacity and charging and discharging behavior probability model of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; a first setting unit, used to execute step S2: set a simulation number threshold and initialize the simulation number to 1; a second setting unit, used to execute step S3: set the total number of electric vehicles and the proportion of each type of electric vehicles; a processing unit, used to execute step S4: use the Monte Carlo simulation method to extract the starting charging time and starting SOC of each type of electric vehicle, and then According to the sampling starting SOC, the charging power and charging demand of the corresponding electric vehicle, the charging time required for the electric vehicle is obtained, so as to obtain the charging load curve of each type of electric vehicle according to the starting charging time, the charging power and the charging time required; the determination unit is used to execute step S5: determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if not, return to execute step S4, and the number of simulations after executing step S4 once is increased by 1; the prediction unit is used to execute step S6: average the charging load curves of each type of electric vehicle, obtain the daily charging load curves of each type of electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area. By establishing a probability model of electric vehicle charging and discharging behavior, the accuracy of electric vehicle charging load prediction is effectively improved, and electric vehicles are classified and processed, and the charging characteristics of different types of electric vehicles are summarized. The obtained electric vehicle charging load curve can characterize the overall trend of electric vehicle charging load in the region, and solve the problem that the electric vehicle charging load prediction method based on Monte Carlo simulation method in the prior art lacks consideration of the charging characteristics of different types of electric vehicles.

[0149] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for predicting charging load of electric vehicles based on Monte Carlo method, characterized in that: include: Step S1: obtaining charging power, battery capacity and charging and discharging behavior probability models of various types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; Step S2: setting the simulation times threshold and initializing the simulation times to 1; Step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles; Step S4: using the Monte Carlo simulation method to extract the starting charging time and starting SOC of each type of the electric vehicle, and then obtaining the required charging time according to the sampled starting SOC, and the corresponding charging power and charging demand of the electric vehicle, so as to obtain the charging load curve of each type of the electric vehicle according to the starting charging time, the charging power and the required charging time; Step S5: Determine whether the number of simulations reaches the simulation number threshold, if yes, execute step S6, if no, return to execute step S4, and after executing step S4 once, the number of simulations is increased by 1; Step S6: averaging the charging load curves of each type of the electric vehicle to obtain a daily charging load curve for each type of the electric vehicle, and superimposing a plurality of the daily charging load curves to obtain a total charging load prediction curve for the preset area.

2. The method according to claim 1, characterized in that Step S4 includes: The following steps are performed for each type of the electric vehicle until the charging load curves of all types of the electric vehicles are obtained. Step S41: Obtain the total number of electric vehicles of the target type; Step S42: Initialize k=0; Step S43: execute k=k+1; Step S44: extracting a starting charging time and a starting SOC of the electric vehicle of a target type, and obtaining a charging time required for the electric vehicle of the target type, so as to obtain a charging load curve of the electric vehicle of the target type; Step S45: determining whether k>N holds, wherein N represents the total number of electric vehicles of the target type; Step S46: If k>N holds, the process proceeds to determine a charging load curve of another type of the electric vehicle; if k>N does not hold, the process returns to step S43.

3. The method according to claim 1, characterized in that The probability model of the starting charging time is: Among them, f s (t in ) is the starting charging time t in The probability density function, μ s is the expected starting charging time, σ s is the standard deviation of the starting charging time; The initial SOC probability model is: in: fs(SOC(tin)) is the probability density function of the initial SOC, μ s is the expected initial SOC, σ s is the standard deviation of the initial SOC, μ s and σ s Varies with vehicle type.

4. The method according to claim 1, characterized in that The charging and discharging behavior probability model also includes a probability model of the time when the electric vehicle leaves the station, and the probability model of the time when the electric vehicle leaves the station conforms to the following normal distribution: Where: f s (t out ) is the probability density function of the charging termination time tout, μ s is the expected time to terminate charging, σ s is the standard deviation of the termination time of charging, μ s and σ s Varies with vehicle type.

5. The method according to claim 1, characterized in that The method further comprises: Obtain relevant regional parameters, including at least one of the following: the total number of people in the region, the volume and number of consumption venues in the region, climate factors, traffic factors, per capita income level, and the number of registered electric vehicles; The regions are divided according to the relevant region parameters.

6. The method according to claim 1, characterized in that After averaging the charging load curves of each type of the electric vehicles to obtain a daily charging load curve for each type of the electric vehicles, and superimposing a plurality of the daily charging load curves to obtain a total charging load prediction curve for the preset area, the method further includes: Obtaining the total number of charging piles in the preset area; Based on the total charging load prediction curve of the preset area and the total number of the charging piles, determine whether additional charging piles are needed. If additional charging piles are needed, a prompt message is issued, and the prompt message includes at least one of the following: adding charging piles to charging and swapping stations, adding charging piles to bus parking lots, and adding charging piles to special parking lots.

7. The method according to claim 6, characterized in that Determining whether additional charging piles are needed according to the total charging load prediction curve of the preset area and the total number of the charging piles includes: When the total number of the charging piles is difficult to meet the charging load represented by the total charging load prediction curve of the preset area, it is determined that additional charging piles need to be added, wherein whether the need is met takes into account charging pile failure factors.

8. An electric vehicle charging load prediction device based on the Monte Carlo method, characterized in that: include: An acquisition unit is used to execute step S1: acquiring charging power, battery capacity and charging and discharging behavior probability models of multiple types of electric vehicles in a preset area, wherein the charging and discharging behavior probability model includes a starting charging time probability model and a starting SOC probability model; The first setting unit is used to execute step S2: setting a simulation number threshold and initializing the simulation number to 1; The second setting unit is used to execute step S3: setting the total number of electric vehicles and the proportion of each type of electric vehicles; The processing unit is used to execute step S4: extract the starting charging time and the starting SOC of each type of the electric vehicle by using the Monte Carlo simulation method, and then obtain the required charging time according to the sampled starting SOC and the corresponding charging power and charging demand of the electric vehicle, so as to obtain the charging load curve of each type of the electric vehicle according to the starting charging time, the charging power and the required charging time; A determination unit, configured to execute step S5: determine whether the number of simulations reaches the simulation number threshold, and if so, execute step S6; if not, return to execute step S4, and after executing step S4 once, the number of simulations increases by 1; The prediction unit is used to execute step S6: average the charging load curves of each type of the electric vehicle to obtain the daily charging load curves of each type of the electric vehicle, and superimpose multiple daily charging load curves to obtain the total charging load prediction curve of the preset area.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the electric vehicle charging load prediction method based on the Monte Carlo method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the electric vehicle charging load prediction method based on the Monte Carlo method as described in any one of claims 1 to 7.

Citation Information

Cited By

  • Power supply control method and device of photovoltaic energy storage charging pile, medium, equipment and product

    CN120056797A

  • Electric vehicle load multi-target double-layer optimization method considering peak load shifting

    CN120933933A