Charging load prediction method for electric vehicle charging scenarios on chain highways

Abstract

This invention relates to a charging load prediction method for electric vehicle charging scenarios on chained highways, comprising: determining the time of entry of electric vehicles onto the highway and the state of charge at the starting point of entry based on daily data of electric vehicles entering the highway; for each service area on the highway, using an electric vehicle charging decision model constructed based on the state of charge at the starting point of entry, determining whether each electric vehicle should charge upon entering the service area; if charging is performed, calculating the charging power of the electric vehicle based on the time of entry onto the highway, and summing the charging power of all charging electric vehicles to obtain the charging load of electric vehicles in that service area. This invention achieves accurate prediction of the electric vehicle charging load in each service area of ​​a chained highway.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging load prediction technology, and in particular to a charging load prediction method for electric vehicle charging scenarios on chained highways. Background Technology

[0002] With the global energy transition and the rapid development of the electric vehicle (EV) industry, highways, as a key infrastructure for long-distance travel, are facing the challenge of rapidly growing charging demand. The widespread adoption of electric vehicles places higher demands on the energy supply of highway service areas, especially given the uncertainty of the temporal and spatial distribution of charging loads, which places higher demands on user-end load forecasting technology.

[0003] Electric vehicle (EV) charging load forecasting is fundamental to highway energy supply system planning. Unlike traditional gasoline vehicles, EV charging demand is influenced by various uncertainties, including traffic flow, highway entry time, state of charge (SOC), and charging behavior. Existing patent document CN119151159A discloses an EV charging load forecasting method and system that considers traffic flow. However, this scheme only considers traffic flow information and does not account for the stochastic characteristics of EV travel status and charging demand. Therefore, directly applying this scheme to a chain-like highway EV charging scenario would result in insufficient accuracy in charging load forecasting. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a charging load prediction method for electric vehicle charging scenarios on chain-type highways, which can improve the accuracy of charging load prediction.

[0005] The technical solution adopted by this invention to solve its technical problem is: to provide a charging load prediction method for electric vehicle charging scenarios on chain-type highways, including the following steps:

[0006] The time when electric vehicles enter the highway and their state of charge at the starting point of entry into the highway are determined based on the data of electric vehicles entering the highway during the day.

[0007] For each service area on the highway, an electric vehicle charging decision model based on the state of charge at the starting point of entering the highway is used to determine whether each electric vehicle should charge when entering the service area. If charging is performed, the charging power of the electric vehicle is calculated based on the time the electric vehicle enters the highway, and the charging power of all charging electric vehicles is summed to obtain the charging load of the electric vehicles in the service area.

[0008] The process of determining the time when an electric vehicle enters the highway based on intraday data on electric vehicles entering the highway specifically includes:

[0009] A time probability distribution model for electric vehicles entering highways is generated based on intraday traffic flow data of electric vehicles on highways.

[0010] Based on the time probability distribution model of electric vehicles entering highways, the Monte Carlo method is used to obtain the time of day when electric vehicles enter highways.

[0011] The method for generating a time probability distribution model of electric vehicles entering highways based on intraday traffic flow data of electric vehicles on highways specifically includes:

[0012] A traffic flow matrix is ​​constructed based on the number of electric vehicles entering the highway per hour;

[0013] Calculate the probability density matrix of electric vehicles based on the traffic flow matrix;

[0014] Based on the distribution characteristics of the probability density matrix of electric vehicles, a temporal probability distribution model of electric vehicles entering highways within a day is obtained.

[0015] The method based on the time probability distribution model of electric vehicles entering highways uses the Monte Carlo method to obtain the time of electric vehicles entering highways within a day. Specifically, it uses the Monte Carlo method to randomly sample based on the time probability distribution model of electric vehicles entering highways, generates random number samples that are uniformly distributed within a preset range, and performs an inverse transformation through the time probability distribution model of highways to convert the uniformly distributed random number samples into samples of the time probability distribution model of highways, thereby obtaining the time of electric vehicles entering highways within a day.

[0016] The method of determining the state of charge at the starting point of entering the highway based on the data of electric vehicles entering the highway within a day is specifically: using a uniform distribution model to determine the state of charge of electric vehicles entering the highway within a day.

[0017] The electric vehicle charging decision model is specifically as follows: ,in, For the first Electric vehicles reach number 1 The state of charge at each service area is determined by the state of charge of the electric vehicle at the starting point of the highway. For the first Electric vehicles reach number 1 The distance traveled when visiting each service area, when When it is the last service area, The total length of the highway. This represents the amount of electricity consumed by the nth electric vehicle per kilometer traveled. This represents the battery capacity of the nth electric vehicle. The charging coefficient is defined as the minimum state of charge that a user can accept when traveling from the current service area to the next service area; when the electric vehicle charging decision model is satisfied, it means that the electric vehicle needs to be charged when entering the service area.

[0018] The calculation of the charging power of electric vehicles and the summing of the charging power of all charging electric vehicles to obtain the charging load of electric vehicles in the service area specifically includes:

[0019] The charging start and end times for each electric vehicle that needs charging are calculated based on the time when the electric vehicle enters the highway.

[0020] A model for the relationship between charging power and time for each electric vehicle that needs charging is determined based on the charging start time and charging end time of each electric vehicle that needs charging.

[0021] Calculate the charging power of each electric vehicle that needs to be charged in each time period to obtain the charging load of the service area in each time period.

[0022] The method for calculating the charging start time of each electric vehicle that needs to be charged is as follows: The charging completion time for each electric vehicle requiring charging is calculated as follows: ,in, and The first The start and end times of charging for electric vehicles in Taiwan; For the first The time when Taiwanese electric vehicles enter highways. For the first Electric vehicles reach number 1 Distance traveled per service area For the first The speed of the electric car; For the first electric vehicles in the first The charging time for each service area is expressed as follows: , For the first Electric vehicles reach number 1 State of charge at each service area This represents the battery capacity of the nth electric vehicle. For the first The charging power of electric vehicles in Taiwan.

[0023] The technical solution adopted by this invention to solve its technical problem is: to provide a charging load prediction device for electric vehicle charging scenarios on chain-type highways, comprising:

[0024] The determination module is used to determine the time when electric vehicles enter the highway and the state of charge at the starting point of entry into the highway based on the data of electric vehicles entering the highway during the day.

[0025] The prediction module is used to determine whether each electric vehicle should charge when it enters the service area of ​​the highway, based on the electric vehicle charging decision model constructed from the state of charge at the starting point of entering the highway. If charging is performed, the charging power of the electric vehicle is calculated based on the time of entry into the highway, and the charging power of all charging electric vehicles is superimposed to obtain the charging load of electric vehicles in the service area.

[0026] The technical solution adopted by the present invention to solve its technical problem is: to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-mentioned charging load prediction method for electric vehicle charging scenarios on chain-type highways.

[0027] The technical solution adopted by the present invention to solve its technical problem is: to provide a computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the above-mentioned charging load prediction method for electric vehicle charging scenarios on chain-type highways are implemented.

[0028] Beneficial effects

[0029] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art: The present invention determines the time of electric vehicle entry into the highway and the state of charge at the starting point of entry into the highway based on the data of electric vehicles entering the highway during the day, fully considers the uncertainty characteristics of electric vehicle travel time and state of charge, and realizes accurate prediction of electric vehicle charging load in each service area of ​​the chain highway. Attached Figure Description

[0030] Figure 1 This is a flowchart of the charging load prediction method for electric vehicle charging scenarios on chain-type highways according to the first embodiment of the present invention.

[0031] Figure 2 This is a highway topology diagram according to the first embodiment of the present invention. Detailed Implementation

[0032] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined by the appended claims.

[0033] The first embodiment of the present invention relates to a charging load prediction method for electric vehicle charging scenarios on chain-linked highways, such as... Figure 1 As shown, it includes the following steps:

[0034] Step 1: Determine the time of entry and state of charge (SOC) of electric vehicles entering the highway based on intraday data. This step utilizes the randomness of charging load distribution on chained highways and employs the Monte Carlo method to simulate the temporal, spatial, and battery SOC characteristics of electric vehicles.

[0035] The time for electric vehicles to enter highways is determined in the following way:

[0036] A time probability distribution model for electric vehicles entering highways is generated based on intraday traffic flow data of electric vehicles on highways.

[0037] To determine the time when electric vehicles enter highways, this implementation method generates a probability distribution model of EV entry time based on intraday traffic flow data of electric vehicles on highways, as follows:

[0038] A traffic flow matrix is ​​constructed based on the number of electric vehicles entering the highway per hour. The details are as follows:

[0039] ;

[0040] in, Indicates the first The number of electric vehicles entering the highway within a specific time period. Based on a traffic flow matrix. This forms the probability density matrix of electric vehicles. It is represented as:

[0041] ;

[0042] in, Indicates that electric vehicles are in the first The probability of entering the highway within the given time period is equal to the probability of entering the highway within the given time period. Number of electric vehicles entering highways during a given time period Dividing by the total number of electric vehicles entering highways within a day, the calculation is as follows:

[0043] ;

[0044] The probability density matrix of electric vehicles By fitting the distribution characteristics, the time probability density function (i.e., the time probability distribution model) of electric vehicles entering highways within a day is obtained. Assuming that the distribution conforms to a Gaussian mixture distribution, the time probability density function is expressed as:

[0045] ;

[0046] This formula reflects the time axis of a single electric vehicle. The probability density at time t is .in, The number of components in the Gaussian mixture distribution represents the number of sub-models in the Gaussian mixture model. The number, and Let these represent the mean and variance of the sub-model, respectively. The mixing coefficient represents the weight of each sub-model.

[0047] Based on the time probability distribution model of electric vehicles entering highways, the Monte Carlo method is used to obtain the time of day when electric vehicles enter highways, specifically: based on the above probability density function. Monte Carlo sampling is used to generate random number samples uniformly distributed in [0, 24], which are then processed using a probability density function. Perform an inverse transformation to convert a uniformly distributed random number sample into a target distribution. The sample.

[0048] Assuming there is If Taiwanese electric vehicles enter the highway within a single day, a matrix will be generated. It is represented as:

[0049] ;

[0050] in, Representing the The time when Taiwanese EVs enter the highway.

[0051] In this step, the state of charge of the electric vehicle at the starting point of the highway is determined in the following way:

[0052] Electric vehicles can only travel in one direction on highways, and the route includes toll booths and service areas. Since electric vehicles only charge at service areas, the highway topology network leading to electric vehicle charging stations is described as a straight line, with various service areas providing power along the way. The topology network is as follows: Figure 2As shown.

[0053] Electric vehicle owners maintain a high state of charge (SOC) level in their vehicles before entering the highway. Therefore, assuming the SOC of the electric vehicle follows a uniform distribution of [0.6, 1] at the start of the highway, the SOC will remain relatively constant throughout the day. The initial SOC of an electric vehicle at the starting point of a highway can be achieved using a matrix. express:

[0054] ;

[0055] In the formula, Indicates the first The State of Charge (SOC) of an electric vehicle at the starting point of a highway.

[0056] Step 2: For each service area on the highway, an electric vehicle charging decision model based on the state of charge at the starting point of entering the highway is used to determine whether each electric vehicle should charge when entering the service area. If charging is performed, the charging power of the electric vehicle is calculated based on the time when the electric vehicle enters the highway, and the charging power of all charging electric vehicles is summed to obtain the charging load of the electric vehicles in the service area.

[0057] When an electric vehicle arrives at a service area, the user may not necessarily choose to charge. Charging will only occur when the vehicle's State of Charge (SOC) falls below a certain level. Furthermore, the user's decision to charge at the current service area considers not only the vehicle's current SOC but also whether they can reach the next service area. To determine the electric vehicle's charging behavior and the charging time, this implementation introduces an electric vehicle charging decision model. When the model's requirements are met, the electric vehicle begins charging; otherwise, it leaves the service area directly.

[0058] To determine whether an electric vehicle needs to be charged upon arrival at a service area, this implementation introduces a charging coefficient. This is defined as the minimum SOC (State of Charge) of an electric vehicle that a user can accept when traveling from the current service area to the next service area. Therefore, the electric vehicle charging decision model of this embodiment can be expressed as:

[0059] ;

[0060] In the formula, For the first Electric vehicles reach number 1 The state of charge at each service area is determined by the state of charge of the electric vehicle at the starting point of the highway. For the first Electric vehicles reach number 1 The distance traveled when visiting each service area, when When it is the last service area, The total length of the highway. This represents the amount of electricity consumed by the nth electric vehicle per kilometer traveled. This represents the battery capacity of the nth electric vehicle.

[0061] When the above electric vehicle charging decision model is met, the electric vehicle will perform a charging operation. electric vehicles in the first When a service area performs a charging operation, its charging start time can be expressed as:

[0062] ;

[0063] When the electric vehicles in the first When a service area finishes its charging operation, its charging end time can be expressed as:

[0064] ;

[0065] in, and The first The start and end times of charging for electric vehicles in Taiwan; For the first Electric vehicles reach number 1 Distance traveled per service area For the first The speed of the electric car For the first electric vehicles in the first Charging time at each service area.

[0066] In this embodiment, when the electric vehicle selects the first... When charging begins at each service area, the charging power is approximately constant, and each charge fully charges the battery, i.e., the State of Charge (SOC) is 1. Therefore, the [missing information - likely a specific charge level]... electric vehicles in the first Charging time at each service area The calculation formula can be expressed as:

[0067] ;

[0068] In the formula, Indicates the first The charging power of electric vehicles in Taiwan. Based on this formula, within a day... The charging time of electric vehicles in various service areas can be calculated using a matrix. express:

[0069] .

[0070] Determine the first electric vehicles in the first After the charging start and end times of each service area, for the first... The relationship between the charging power and time of an electric vehicle can be expressed as follows:

[0071] ;

[0072] In the formula, the charging power calculation cycle for electric vehicles is controlled within a 24-hour period per day. Therefore, It takes values ​​between 0 and 24.

[0073] The design calculates a time step of 1 hour, which divides a day into 24 time periods. The calculation of the time step for each electric vehicle within each time period is then performed. The charging power of each service area can be summarized to obtain the charging power of the [number]th service area. The charging load of a service area can be expressed as:

[0074] ;

[0075] Based on this formula, the first The distribution of charging load in each service area throughout the 24 hours of the day can form a matrix. It is represented as:

[0076] ;

[0077] When the traversal is complete, the electric vehicle charging load data for all service areas will be obtained, thus completing the charging load prediction.

[0078] This invention fully considers the uncertainty of the State of Charge (SOC) of electric vehicles entering highways using the Monte Carlo method and improves it by introducing an electric vehicle charging decision model, thus achieving accurate prediction of electric vehicle charging load at each service area of ​​a chain-like highway. Furthermore, this invention only requires inputting the total number of electric vehicles entering the highway during the day to obtain the distribution of electric vehicle charging load at different times of the day.

[0079] The second embodiment of the present invention relates to a charging load prediction device for electric vehicle charging scenarios on chain-link highways, comprising:

[0080] The determination module is used to determine the time when electric vehicles enter the highway and the state of charge at the starting point of entry into the highway based on the data of electric vehicles entering the highway during the day.

[0081] The prediction module is used to determine whether each electric vehicle should charge when it enters the service area of ​​the highway, based on the electric vehicle charging decision model constructed from the state of charge at the starting point of entering the highway. If charging is performed, the charging power of the electric vehicle is calculated based on the time of entry into the highway, and the charging power of all charging electric vehicles is superimposed to obtain the charging load of electric vehicles in the service area.

[0082] The determining module includes a time determining unit, which generates a time probability distribution model of electric vehicles entering the highway based on the traffic flow data of electric vehicles on the highway during the day; based on the time probability distribution model of electric vehicles entering the highway, the Monte Carlo method is used to obtain the time of electric vehicles entering the highway within a day.

[0083] When the time determination unit generates a time probability distribution model for electric vehicles entering the highway based on intraday traffic flow data of electric vehicles on highways, it specifically includes:

[0084] A traffic flow matrix is ​​constructed based on the number of electric vehicles entering the highway per hour;

[0085] Calculate the probability density matrix of electric vehicles based on the traffic flow matrix;

[0086] Based on the distribution characteristics of the probability density matrix of electric vehicles, a temporal probability distribution model of electric vehicles entering highways within a day is obtained.

[0087] The time determination unit uses the Monte Carlo method to obtain the time when electric vehicles enter the highway within a day, based on the time probability distribution model of electric vehicles entering the highway. Specifically, it uses the Monte Carlo method to perform random sampling based on the time probability distribution model of electric vehicles entering the highway, generates random number samples that are uniformly distributed within a preset range, and performs an inverse transformation through the time probability distribution model of the highway to convert the uniformly distributed random number samples into samples of the time probability distribution model of the highway, thereby obtaining the time when electric vehicles enter the highway within a day.

[0088] The determination module includes a state of charge determination unit, which uses a uniform distribution model to determine the state of charge of the electric vehicle at the starting point of the highway within a day.

[0089] The electric vehicle charging decision model is specifically as follows: ,in, For the first Electric vehicles reach number 1 The state of charge at each service area is determined by the state of charge of the electric vehicle at the starting point of the highway. For the first Electric vehicles reach number 1 The distance traveled when visiting each service area, when When it is the last service area, The total length of the highway. This represents the amount of electricity consumed by the nth electric vehicle per kilometer traveled. This represents the battery capacity of the nth electric vehicle. The charging coefficient is defined as the minimum state of charge that a user can accept when traveling from the current service area to the next service area; when the electric vehicle charging decision model is satisfied, it means that the electric vehicle needs to be charged when entering the service area.

[0090] The prediction module includes:

[0091] The time calculation unit is used to calculate the charging start time and charging end time of each electric vehicle that needs to be charged based on the time when the electric vehicle enters the highway.

[0092] The power-time determination unit determines the relationship model between the charging power and time of each electric vehicle that needs to be charged, based on the charging start time and charging end time of each electric vehicle.

[0093] The charging load calculation unit is used to calculate the charging power of each electric vehicle that needs to be charged in each time period, so as to obtain the charging load of the service area in each time period.

[0094] The time calculation unit via Calculate the charging start time for each electric vehicle that needs charging, by... Calculate the charging completion time for each electric vehicle that needs charging, where... and The first The start and end times of charging for electric vehicles in Taiwan; For the first The time when Taiwanese electric vehicles enter highways. For the first Electric vehicles reach number 1 Distance traveled per service area For the first The speed of the electric car; For the first electric vehicles in the first The charging time for each service area is expressed as follows: , For the first Electric vehicles reach number 1 State of charge at each service area This represents the battery capacity of the nth electric vehicle. For the first The charging power of electric vehicles in Taiwan.

[0095] The third embodiment of the present invention relates to an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the charging load prediction method for chain-linked highway electric vehicle charging scenarios of the first embodiment.

[0096] The fourth embodiment of the present invention relates to a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the charging load prediction method for electric vehicle charging scenarios on chained highways as described in the first embodiment.

[0097] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0098] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0099] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction methods implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0100] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0101] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A charging load prediction method for electric vehicle charging scenarios on chain-type highways, characterized in that, Includes the following steps: The time of entry of electric vehicles into the highway and the state of charge at the starting point of entry are determined based on the data of electric vehicles entering the highway during the day; wherein, determining the time of entry of electric vehicles into the highway based on the data of electric vehicles entering the highway during the day specifically includes: The model generates a temporal probability distribution model of electric vehicles entering highways based on daily traffic flow data of electric vehicles. Specifically, it involves: constructing a traffic flow matrix based on the number of electric vehicles entering the highway per hour; calculating the probability density matrix of electric vehicles based on the traffic flow matrix; and obtaining a temporal probability distribution model of electric vehicles entering highways within a day based on the distribution characteristics of the probability density matrix of electric vehicles. Based on the time probability distribution model of electric vehicles entering highways, the Monte Carlo method is used to obtain the time of electric vehicles entering highways within a day. Specifically, based on the time probability distribution model of electric vehicles entering highways, random sampling is performed using the Monte Carlo method to generate random number samples that are uniformly distributed within a preset range. Then, the time probability distribution model of highways is inversely transformed to convert the uniformly distributed random number samples into samples of the time probability distribution model of highways, thereby obtaining the time of electric vehicles entering highways within a day. The method of determining the state of charge at the starting point of entering the highway based on the data of electric vehicles entering the highway within a day is specifically: using a uniform distribution model to determine the state of charge of electric vehicles entering the highway within a day. For each service area on the highway, an electric vehicle charging decision model based on the state of charge at the highway entry point is used to determine whether each electric vehicle should charge upon entering the service area. If charging is performed, the charging power of the electric vehicle is calculated based on the time it entered the highway, and the charging power of all charging electric vehicles is summed to obtain the charging load of the electric vehicles in that service area. The electric vehicle charging decision model is as follows: in, Let n be the state of charge of the nth electric vehicle when it arrives at the jth service area. This state of charge is determined by the state of charge of the electric vehicle at the starting point of its entry into the highway. Let be the distance traveled by the nth electric vehicle when it reaches the jth service area. When j is the last service area... The total length of the highway. This represents the amount of electricity consumed by the nth electric vehicle per kilometer traveled. Let ω represent the battery capacity of the nth electric vehicle, and let ω be the charging coefficient, defined as the minimum state of charge that the user can accept when the electric vehicle travels from the current service area to the next service area. When the electric vehicle charging decision model is satisfied, it means that the electric vehicle needs to be charged when it enters the service area.

2. The charging load prediction method for electric vehicle charging scenarios on chain-type highways according to claim 1, characterized in that, The calculation of the charging power of electric vehicles and the summing of the charging power of all charging electric vehicles to obtain the charging load of electric vehicles in the service area specifically includes: The charging start and end times for each electric vehicle that needs charging are calculated based on the time when the electric vehicle enters the highway. A model for the relationship between charging power and time for each electric vehicle that needs charging is determined based on the charging start time and charging end time of each electric vehicle that needs charging. Calculate the charging power of each electric vehicle that needs to be charged in each time period to obtain the charging load of the service area in each time period.

3. The charging load prediction method for electric vehicle charging scenarios on chain-like highways according to claim 2, characterized in that, The method for calculating the charging start time of each electric vehicle that needs to be charged is as follows: The method for calculating the charging completion time of each electric vehicle that needs charging is as follows: in, and These are the start and end times of charging for the nth electric vehicle, respectively. Let be the time when the nth electric vehicle enters the highway. Let V be the distance traveled by the nth electric vehicle when it reaches the jth service area. n Let n be the speed of the nth electric car; The charging time for the nth electric vehicle in the jth service area is represented as: Let n be the state of charge of the nth electric vehicle when it arrives at the jth service area. This represents the battery capacity of the nth electric vehicle. The charging power of the nth electric vehicle.

4. A charging load prediction device for electric vehicle charging scenarios on chain-type highways, characterized in that, include: A determination module is used to determine the time of electric vehicle entry into the highway and the state of charge at the starting point of entry into the highway based on the daily data of electric vehicles entering the highway. The determination module includes a time determination unit and a state of charge determination unit. The time determination unit generates a probability distribution model of the time of electric vehicle entry into the highway based on the traffic flow data of electric vehicles on the highway during the day. Specifically, it includes: constructing a traffic flow matrix based on the number of electric vehicles entering the highway per hour; calculating the probability density matrix of electric vehicles based on the traffic flow matrix; and obtaining a probability distribution model of the time of electric vehicle entry into the highway within a day based on the distribution characteristics of the probability density matrix of electric vehicles. The time determination unit uses the Monte Carlo method to obtain the time of electric vehicle entry into the highway within a day based on the probability distribution model of electric vehicle entry into the highway. Specifically, it uses the Monte Carlo method to randomly sample and generate a random number sample uniformly distributed within a preset range based on the probability distribution model of electric vehicle entry into the highway. Then, it performs an inverse transformation on the time probability distribution model of the highway to convert the uniformly distributed random number sample into a sample of the time probability distribution model of the highway, thus obtaining the time of electric vehicle entry into the highway within a day. The state of charge determination unit uses a uniform distribution model to determine the state of charge of electric vehicles at the starting point of entry into the highway within a day. The prediction module is used to determine, for each service area on the highway, whether each electric vehicle should charge upon entering the service area, based on an electric vehicle charging decision model constructed from the state of charge at the starting point of entering the highway. If charging is performed, the charging power of the electric vehicle is calculated based on the time the electric vehicle entered the highway, and the charging power of all charging electric vehicles is summed to obtain the charging load of the electric vehicles in that service area. The electric vehicle charging decision model is specifically as follows: in, Let n be the state of charge of the nth electric vehicle when it arrives at the jth service area. This state of charge is determined by the state of charge of the electric vehicle at the starting point of its entry into the highway. Let be the distance traveled by the nth electric vehicle when it reaches the jth service area. When j is the last service area... The total length of the highway. This represents the amount of electricity consumed by the nth electric vehicle per kilometer traveled. Let ω represent the battery capacity of the nth electric vehicle, and let ω be the charging coefficient, defined as the minimum state of charge that the user can accept when the electric vehicle travels from the current service area to the next service area. When the electric vehicle charging decision model is satisfied, it means that the electric vehicle needs to be charged when it enters the service area.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the charging load prediction method for electric vehicle charging scenarios on chained highways as described in any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the charging load prediction method for electric vehicle charging scenarios on chained highways as described in any one of claims 1-3.

Images