Electric vehicle space load prediction method considering road traffic condition

Abstract

The invention discloses an electric vehicle space load prediction method considering road traffic conditions. Obtaining road information to construct a road traffic network matrix, and calculating the driving speed and passing time of the electric vehicle on the road; acquiring starting points and terminal points of all the electric vehicles, and simulating travel paths of the electric vehicles to obtain travel path information of the electric vehicles; the initial electric quantity and the parking time of each electric vehicle are randomly generated through a Monte Carlo method; charging station information is obtained, and charging stations selected to be charged by all the electric vehicles are determined in combination with the travel paths of all the electric vehicles; power constraint conditions of charging and discharging of the electric vehicles are constructed, and spatial-temporal distribution of charging loads of the electric vehicles is obtained by combining travel path information of the electric vehicles, the charging stations selected by the electric vehicles, the initial electric quantity of each electric vehicle and parking time processing. According to the method, the charging and discharging time model is constructed, and better effects are achieved in the aspects of energy utilization efficiency, energy distribution efficiency and driving path simulation accuracy.

Description

Technical Field

[0001] This invention relates to the field of power system spatial load planning technology, specifically to a method for predicting the spatial load of electric vehicles that takes into account road traffic conditions. Background Technology

[0002] With the trend of large-scale development, if a large number of electric vehicles are connected to the power grid in an uncontrolled manner, it may impact the grid and cause incalculable losses. At the same time, while electric vehicles act as loads, they also possess energy storage characteristics. When the grid load is too high, electric vehicles can discharge electricity to the grid, acting as a power source in the power system. Therefore, understanding the spatial load of electric vehicles is particularly important. Due to the complexity of urban traffic, road conditions vary from day to day and hour to hour. Road construction and closures also pose challenges to load forecasting. Therefore, there is an urgent need for a method for predicting the spatial load of electric vehicles that takes into account road traffic conditions.

[0003] Existing load forecasting methods are typically based on static data and lack adaptability to real-time traffic conditions. This means they cannot effectively cope with dynamic changes in urban traffic, such as traffic congestion and road closures, resulting in time-consuming and energy-inefficient route selection. Electric vehicle users often face range anxiety due to inaccurate route planning, which to some extent limits the adoption and efficiency of electric vehicles. Existing technologies also have significant limitations in the management of electric vehicle charging and discharging. Most systems do not fully consider the overall load distribution of the urban power grid and the actual service capacity of charging stations. This leads to low utilization efficiency of charging stations and the risk of overloading the power grid during peak hours. Furthermore, the management of electric vehicle charging and discharging time is often relatively simple, lacking in-depth analysis of individual vehicle characteristics and user behavior patterns. This limits the potential role of electric vehicles in the energy system, especially in demand-side management and peak-valley load regulation. Existing electric vehicle distribution management systems often fail to fully utilize advanced data analysis methods and algorithms. For example, the prediction of initial electric vehicle charge and parking time is often not accurate enough, affecting the formulation and execution of charging strategies. In this regard, the lack of effective statistical and forecasting tools, such as Monte Carlo sampling, makes it difficult for the system to optimize the energy utilization and route planning of electric vehicles. Summary of the Invention

[0004] To address the problems of low accuracy in driving path simulation, unrealistic load forecasting results, low energy efficiency, and low availability and economy of power grids in existing load forecasting methods, this invention proposes a spatial load forecasting method for electric vehicles that takes into account road traffic conditions.

[0005] The technical solution of this invention is: This invention includes the following steps: S1. Obtain road information to construct a road traffic network matrix, and then calculate the driving speed and travel time of electric vehicles on the road; S2. Obtain the starting point and ending point of all electric vehicles, and then combine the road traffic network matrix with the driving speed and travel time of electric vehicles on the road to simulate the travel path of electric vehicles and obtain the travel path information of electric vehicles. S3. Based on a preset probability distribution, the initial battery level and parking time of each electric vehicle are randomly generated using the Monte Carlo method. S4. Obtain charging station information to construct a service range model of charging stations, and then combine the travel paths of each electric vehicle to determine the charging stations that each electric vehicle should choose to charge. S5. Construct power constraints for electric vehicle charging and discharging, and then combine electric vehicle travel route information, charging stations selected by each electric vehicle, initial battery level of each electric vehicle, and parking time to obtain the spatiotemporal distribution of electric vehicle charging load.

[0006] The road information in step S1 includes road traffic conditions, road length, number of road nodes, road capacity, and road construction status. The electric vehicle travel route information in step S2 includes the travel route of each electric vehicle, the travel time of each electric vehicle on each road segment, and the departure and arrival times of each electric vehicle. The charging station information in step S4 includes the maximum power of the charging station, the location of the charging station, and the cost per unit of electricity of the charging station.

[0007] The driving speed and travel time of electric vehicles on the road are set according to the following formula: in, Represents the road segment at time t The vehicle's speed, Indicates road segment The maximum driving speed is specified. for Time and Section Traffic flow For road section Traffic capacity, To characterize the impact of road congestion, p represents the inherent adaptive coefficient characterizing the traffic characteristics of the road itself, and q represents the traffic flow sensitivity coefficient of the road.

[0008] Specifically, S2 is: S2.1 Obtain the starting and ending points of all electric vehicles, and then simulate the travel demand matrix of electric vehicles using the OD analysis method; S2.2 Based on the electric vehicle travel demand matrix, road traffic network matrix, and the speed and travel time of electric vehicles on the road, the Floyd algorithm is used to plan the electric vehicle travel route information.

[0009] In step S4, each electric vehicle selects a charging station according to the following formula: in, This represents the maximum power of the i-th charging station. This represents the preset weighting coefficient. This indicates the distance the electric vehicle travels to the charging station. This indicates the unit power consumption of an electric vehicle. This indicates the electricity price for charging electric vehicles. This represents the standardized attractiveness value of the i-th charging station. This represents the original attractiveness value of the i-th charging station. This represents the average original attractiveness of all charging stations. The standard deviation of the original attractiveness of all charging stations. This indicates the total number of charging stations.

[0010] The power constraint conditions for charging and discharging the electric vehicle in step S5 are set according to the following formula: in, , These represent the charging time and discharging time of the nth electric vehicle participating in energy storage, respectively. Let n be the expected charging capacity of the nth electric vehicle participating in energy storage. The energy ratio reserved for the trip of the nth electric vehicle Let be the available battery capacity of the nth electric vehicle. for The state of charge of the battery of the nth car at time n. , and , Let the charging and discharging power and charging and discharging efficiency of the nth electric vehicle be given. , Indicates the adjustment coefficient for charging power and discharging power. This indicates the total duration of parking. , This represents the maximum charging power and rated discharging power of the nth electric vehicle at time t. , This represents the charging and discharging periods of the nth vehicle.

[0011] The spatiotemporal distribution of electric vehicle charging load specifically refers to the charging and discharging power of electric vehicles at each charging station at each time point, as well as the total charging and discharging power of all electric vehicles at each time point.

[0012] The beneficial effects of this invention are: The electric vehicle spatial load prediction method considering road traffic conditions provided by this invention constructs a road traffic network matrix by collecting road information, achieving a detailed mapping of the urban road network. By analyzing road resistance and traffic flow, it outputs road travel speed and travel time, realizing dynamic assessment of traffic flow and improving the accuracy and efficiency of route planning. It uses OD and Floyd analysis to simulate the travel path of electric vehicles, and combines Monte Carlo sampling to optimize the estimation of initial battery power and parking time, enhancing the accuracy of route planning and the efficiency of battery power management, thereby improving energy utilization efficiency. It constructs a charging station service range model to improve the availability and economy of the charging network, and establishes a charging and discharging time model and determines power constraints to improve the energy utilization efficiency of electric vehicles and the operational reliability of vehicles. This invention achieves better results in terms of energy utilization efficiency, energy allocation efficiency, and accuracy of travel path simulation. Attached Figure Description

[0013] Figure 1 The first embodiment of the present invention provides an overall flowchart of a method for predicting the spatial load of electric vehicles that takes into account road traffic conditions.

[0014] Figure 2 This is a schematic diagram of a traffic network structure for a method of predicting the spatial load of electric vehicles that takes into account road traffic conditions, provided in the first embodiment of the present invention.

[0015] Figure 3 The following is an overall flowchart of a load balancing system for a computing platform based on a particle swarm genetic algorithm, provided as a third embodiment of the present invention. Detailed Implementation

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of protection of this invention.

[0018] like Figure 1 and Figure 3 As shown, this embodiment includes the following steps: S1. Obtain road information to construct a road traffic network matrix, and then calculate the driving speed and travel time of electric vehicles on the road based on the road information and the road traffic network matrix; Specifically, the first step is to collect road data based on the urban road network model and establish the urban road network model. Since urban traffic flow changes over time, an hour is chosen as a time period for modeling.

[0019] Subsequently, based on road resistance and traffic flow in the transportation network, road speed and travel time are output. According to the transportation network matrix, what drivers are most concerned about is the travel time on each road. Vehicle speed is closely related to factors such as road capacity and traffic flow at different times, and is a dynamic variable that changes over time.

[0020] S2. Obtain the starting point and ending point of all electric vehicles, and then combine the road traffic network matrix with the driving speed and travel time of electric vehicles on the road to simulate the travel path of electric vehicles and obtain the travel path information of electric vehicles. S3. Based on a preset probability distribution, the initial battery level and parking time of each electric vehicle are randomly generated using the Monte Carlo method. S4. Obtain charging station information to construct a service range model of charging stations, and then combine the travel paths of each electric vehicle to determine the charging stations that each electric vehicle should choose to charge. S5. Construct power constraints for electric vehicle charging and discharging, and then combine electric vehicle travel route information, charging stations selected by each electric vehicle, initial battery level of each electric vehicle, and parking time to obtain the spatiotemporal distribution of electric vehicle charging load.

[0021] The road information in step S1 includes road traffic conditions, road length, number of road nodes, road capacity, and road construction status; The road traffic network matrix is ​​set according to the following formula: in, For transportation network integration, The set of all nodes in the transportation network has a total of indivual, A collection of road segments in a transportation network. For the set of time periods, , For the weight set of road segments, The first in the transportation network 1 node To connect the first The node and the first Road sections at each transportation network node for Road sections during the time period The weights; Transportation network integration The connection relationships between nodes are represented by an adjacency matrix. To represent, matrix elements The representation is: in, for Road sections during the time period The weights; The traffic network matrix for each hour is output as follows: Where W represents the 24-hour transportation network matrix, consisting of 24 sub-matrices. , This indicates the road conditions for each hour of the 24-hour period.

[0022] The electric vehicle travel route information in step S2 includes the travel route of each electric vehicle, the travel time of each electric vehicle on each road segment, and the departure and arrival times of each electric vehicle. The charging station information in step S4 includes the charging station's maximum power, location, and cost per unit of electricity.

[0023] Road speed refers to the average speed of vehicles on this road segment; travel time refers to the time required for vehicles to pass through this road segment.

[0024] The speed and travel time of electric vehicles on the road are set according to the following formula: in, Represents the road segment at time t The vehicle speed (i.e., the speed of the road from node i to node j). Indicates road segment The maximum driving speed is specified. for Time and Section Traffic flow For road section Traffic capacity, and The ratio is Saturation level of road segments at any given time. To characterize the impact of road congestion, p represents the inherent adaptive coefficient characterizing the traffic characteristics of the road itself, and q represents the traffic flow sensitivity coefficient of the road.

[0025] Road traffic speed output is represented as: in, Let represent the vehicle speed from node i to node j at time t. If a node is not connected to a road, it is represented by 0. n represents the total number of nodes in the transportation network. V represents the total matrix of the vehicle speeds of each road for each hour of the 24-hour period. The travel time of a road is output by combining the road matrix and the road's travel speed, expressed as: Where T represents the travel time of vehicles on each road in each time period.

[0026] S2 specifically refers to: S2.1 Obtain the starting and ending points of all electric vehicles, and then simulate the travel demand matrix of electric vehicles using the OD analysis method; Specifically, step S2 simulates the driving path of the electric vehicle. Odescent (OD) analysis is used to analyze the starting and ending points of the electric vehicle. The OD matrix represents the traffic volume between road nodes, expressed as: in, This represents the number of vehicles that depart from node o and travel to node d at time t.

[0027] It should be noted that the starting point and destination of each electric vehicle can be determined by using the OD matrix combined with Monte Carlo sampling. Based on real-world driving habits, assuming that each electric vehicle owner chooses the shortest route, the Floyd algorithm is used to plan the travel routes of the electric vehicles, selecting the shortest route for each vehicle and recording the corresponding distance.

[0028] S2.2 Based on the electric vehicle travel demand matrix, road traffic network matrix, and the speed and travel time of electric vehicles on the road, the Floyd algorithm is used to plan the electric vehicle travel route information.

[0029] Specifically, the Floyd-Warshall algorithm is used to plan the travel routes of electric vehicles. The path with the shortest travel time for each vehicle is selected, the travel distance is recorded, and the shortest time to directly reach node j from node i is determined, denoted as . Determine the shortest time from node i to node j, allowing the journey to node j via one other node. Compare them, and record the shorter one as... Continue until all nodes within the planning area are traversed, and output the shortest distance. ; Subsequently, a basic model of electric vehicles is constructed, first determining the initial travel time. The travel time of electric vehicles is determined by working hours and travel habits. By collecting and analyzing the data of the electric vehicles under study, the probability distribution of electric vehicle travel times can be obtained: in, , , , , , ; The parking time and initial battery level of electric vehicles are largely influenced by the owner's driving habits and the vehicle's intended use, thus exhibiting a degree of randomness. We can assume that the distribution of electric vehicles follows a normal distribution, and obtain the probability density function accordingly as follows: in, For parking time of electric vehicles, The mean, The standard deviation is denoted as .

[0030] Depending on the actual usage habits of electric vehicles, different parameter values ​​can be selected to match the corresponding distribution.

[0031] When needing to charge, electric vehicle owners typically choose the charging station closest to their vehicle. The larger the charging station's capacity, the shorter the waiting time for users, as it offers stronger service capabilities and is more attractive to users. Besides capacity and distance, other influencing factors may exist. Therefore, a weighting coefficient is introduced to reflect the impact of other relevant factors on the service range. Based on the above theory and other factors related to the service range of charging stations, a model is proposed that can determine the service range of a charging station based on its capacity and location. This model can better plan the layout and service delivery of charging stations.

[0032] The service range model of a charging station is constructed based on its location and electricity price. This includes determining the service range of the charging station based on its capacity and location. When multiple charging stations exist, the total power of each station differs from the distance between electric vehicles. To address this, Z-Score normalization is introduced for standardization. In step S4, each electric vehicle selects a charging station according to the following formula: in, This represents the maximum power of the i-th charging station. This represents the preset weighting coefficient. This indicates the distance the electric vehicle travels to the charging station. This indicates the unit power consumption of an electric vehicle. This indicates the electricity price for charging electric vehicles. This represents the standardized attractiveness value of the i-th charging station. This represents the original attractiveness value of the i-th charging station. This represents the average original attractiveness of all charging stations. The standard deviation of the original attractiveness of all charging stations is represented by N, where N represents the total number of charging stations.

[0033] The more attractive a charging station is to car owners, the more likely electric vehicles are to choose that station. By standardizing the service areas of each charging station, a combined set of service areas can be obtained. Based on the charging needs and driving routes of electric vehicles, the location of the charging station that electric vehicle owners will choose can be determined.

[0034] The power constraints for charging and discharging electric vehicles in step S5 are set according to the following formula: First, the time that an electric vehicle can participate in the charging and discharging process is calculated. Since the parking time of an electric vehicle may not exactly equal the time it takes to fully charge, the electric vehicle, as a spatial load, can simultaneously act as a charging load (charging state) or a discharging power source (fully charged state). The sustainable service time of a single electric vehicle is: During parking, a portion of the time is permitted for the electric vehicle to be in a state where it is neither charging nor discharging. The total parking time constraint is expressed as: Electric vehicle constraints are expressed as: in, , These represent the charging time and discharging time of the nth electric vehicle participating in energy storage, respectively. Let n be the expected charging capacity of the nth electric vehicle participating in energy storage. The energy ratio reserved for the trip of the nth electric vehicle Let be the available battery capacity of the nth electric vehicle. for The state of charge of the battery of the nth car at time n. , and , Let the charging and discharging power and charging and discharging efficiency of the nth electric vehicle be given. , Indicates the adjustment coefficient for charging power and discharging power. This indicates the total duration of parking. , This represents the maximum charging power and rated discharging power of the nth electric vehicle at time t. , This represents the charging and discharging periods of the nth vehicle.

[0035] The spatiotemporal distribution of electric vehicle charging load specifically refers to the charging and discharging power of electric vehicles at each charging station at each time point, as well as the total charging and discharging power of all electric vehicles at each time point.

[0036] The spatial load distribution of electric vehicles includes the spatiotemporal distribution of electric vehicle charging load based on the selection of charging stations by electric vehicles and the constraints of charging and discharging, expressed as: in, , for The charging and discharging power of electric vehicles at the k-th charging station at any given time. , for The total charging and discharging power of all electric vehicles at any given time.

[0037] like Figure 3 As shown, the present invention uses a load forecasting method system for data processing. The system includes an initialization module, a traffic network matrix construction module, a travel route simulation module, a charging station service range model construction module, a charging and discharging time model construction module, a charging and discharging power constraint module, and an electric vehicle spatial load distribution output module. The initialization module is used to collect road information data; The traffic network matrix construction module is used to output road travel speed and travel time; The travel route simulation module is used to determine the initial battery level and parking time of electric vehicles; The charging station service range model is used to determine the location of the charging station selected by the owner of the electric vehicle. The charge / discharge time model building module is used to output the time that an electric vehicle can participate in the charge / discharge process; The charging and discharging power constraint module is used to constrain the charging and discharging power of electric vehicles. The electric vehicle spatial load distribution output module is used to take into account the selection of charging stations and the constraints of charging and discharging, and output the spatiotemporal distribution of electric vehicle charging load.

[0038] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0039] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0040] like Figure 2 As shown, this embodiment selects a medium-sized urban area and collects information on key roads using GPS and Geographic Information System (GIS) data. This data includes road type, length, width, and speed limits. A detailed road traffic network matrix is ​​constructed using this data to simulate the urban traffic network. Road congestion and traffic flow data are collected using a real-time traffic monitoring system. By analyzing this data, the average speed and estimated travel time for each road are calculated. The travel path of electric vehicles is simulated using OD (origin-destination) analysis and the Floyd algorithm. Multiple possible routes are simulated with different start points and destinations. Monte Carlo sampling is used to estimate the initial battery level and estimated parking time of electric vehicles at different start points. The geographical location and electricity price information of all charging stations in the city are analyzed to construct a charging station service range model to help electric vehicle users find the nearest charging station. Using the electric vehicle's driving and charging data, an electric vehicle charging and discharging time model is constructed, and power constraints during charging and discharging are determined. Based on the electric vehicle's own parameters, selected route, and parking duration, the spatial load distribution of the electric vehicle is calculated.

[0041] The experimental group was set up using the present invention, while the control group used existing methods.

[0042] Table 1 Experimental Results Regarding energy efficiency, it was observed that the implementation group generally had higher travel speeds than the control group. The travel speeds on routes A and C increased from 40 km / h to 43 km / h and from 45 km / h to 48 km / h, respectively. This indicates that after implementation, the invention can more effectively reduce road resistance and improve travel efficiency, thereby enhancing energy efficiency.

[0043] Regarding energy allocation efficiency, the initial charge levels in the experimental groups were generally higher than those in the control group, indicating that the invention can better predict and plan the energy needs of electric vehicles. The initial charge level for Route B increased from 70% to 75%, and for Route D from 65% to 70%. This means that electric vehicles can be charged more efficiently, reducing unnecessary energy waste.

[0044] In terms of the accuracy of driving route simulation, the optimization of parking time is also a significant indicator. In the experimental group, parking time was generally lower than that in the control group, with Route A decreasing from 30 minutes to 28 minutes and Route B decreasing from 25 minutes to 22 minutes. This indicates that after the invention is implemented, it can more accurately simulate the actual driving conditions of electric vehicles and effectively reduce parking time.

[0045] In summary, the present invention is a preferred solution in terms of energy utilization efficiency, energy distribution efficiency, and driving path simulation accuracy.

[0046] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0047] The specific embodiments described above illustrate the technical solution and beneficial effects of the present invention in detail. It should be understood that the above description is only the most preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, additions, and equivalent substitutions made within the scope of the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting space load of an electric vehicle, taking into account road traffic conditions, characterized in that, The method comprises the following steps: S1, acquiring road information to construct a road traffic network matrix, and then calculating the driving speed and passing time of the electric vehicle on the road; S2, acquiring the starting point and the ending point of all electric vehicles, and then combining the road traffic network matrix and the driving speed and passing time of the electric vehicle on the road to simulate the electric vehicle travel path to obtain electric vehicle travel path information; S3, generating the initial electric quantity and parking time of each electric vehicle randomly according to a preset probability distribution through a Monte Carlo method; S4, acquiring charging station information to construct a service range model of the charging station, and then determining the charging station selected by each electric vehicle in combination with the electric vehicle travel path; S5, constructing a power constraint condition of the charging and discharging of the electric vehicle, and then processing to obtain the space-time distribution of the electric vehicle charging load in combination with the electric vehicle travel path information, the charging station selected by each electric vehicle, the initial electric quantity and parking time of each electric vehicle. 2.The method of claim 1, wherein: The road information in the step S1 comprises the passing condition, road length, road node quantity, road capacity and road construction condition of the road; The electric vehicle travel path information in the step S2 comprises the travel path of each electric vehicle, the passing time of each electric vehicle on each road, and the departure time and arrival time of each electric vehicle; The charging station information in the step S4 comprises the maximum power of the charging station, the location of the charging station and the cost parameter of the unit electric power of the charging station. 3.The method of claim 1, wherein: The driving speed and passing time of the electric vehicle on the road are set according to the following formula: wherein, denotes the vehicle travel speed on the road segment at time t, denotes the maximum travel speed prescribed for the road segment at time t, is the traffic volume on the road segment at time t, is the traffic capacity of the road segment at time t, is the influence shadow representing the impact of road congestion, p represents an inherent adaptive coefficient representing the traffic characteristics of the road itself, and q represents the flow sensitivity coefficient of the road. 4.The method of claim 1, wherein: The S2 is specifically: S2.1, acquiring the starting point and the ending point of all electric vehicles, and then simulating to obtain the travel demand matrix of the electric vehicle through an OD analysis method; S2.2, according to the travel demand matrix of the electric vehicle, the road traffic network matrix and the driving speed and passing time of the electric vehicle on the road, the electric vehicle travel path information is planned by using a Floyd algorithm. 5.The method of claim 1, wherein: Each electric vehicle selects the charging station for charging according to the following formula in the step S4: wherein, represents the maximum power of the i-th charging station, represents a preset weight coefficient, represents the distance from the electric vehicle to the charging station, represents the unit power consumption of the electric vehicle, represents the charging price of the electric vehicle, represents the normalized attractiveness value of the i-th charging station, represents the original attractiveness value of the i-th charging station, represents the average of the original attractiveness of all charging stations, represents the standard deviation of the original attractiveness of all charging stations, represents the total number of charging stations. 6.The method of claim 1, wherein: The power constraint condition of the charging and discharging of the electric vehicle in the step S5 is set according to the following formula: in, , These represent the charging time and discharging time of the nth electric vehicle participating in energy storage, respectively. Let n be the expected charging capacity of the nth electric vehicle participating in energy storage. The energy ratio reserved for the trip of the nth electric vehicle Let be the available battery capacity of the nth electric vehicle. for The state of charge of the battery of the nth car at time n. , and , Let the charging and discharging power and charging and discharging efficiency of the nth electric vehicle be given. , Indicates the adjustment coefficient for charging power and discharging power. This indicates the total duration of parking. , This represents the maximum charging power and rated discharging power of the nth electric vehicle at time t. , This represents the charging and discharging periods of the nth vehicle. 7.The method of claim 1, wherein: The space-time distribution of the electric vehicle charging load is specifically the charging and discharging power of each electric vehicle at each charging station at each time point, and the total charging and discharging power of all electric vehicles at each time point.

8. An electronic device comprising: One or more processors; A memory having one or more programs stored thereon, when the one or more programs are executed by the one or more processors, the one or more processors implement the electric vehicle space load prediction method in any one of claims 1 to 7.

9. A computer readable medium characterized by The computer program is stored on the computer readable medium, and when the computer program is run, the electric vehicle space load prediction method in any one of claims 1 to 7 is executed.

Images