Electric vehicle fast-charging demand guidance method and apparatus, device, and medium

Abstract

The present invention relates to the technical field of electric vehicle charging guidance, and in particular to an electric vehicle fast-charging demand guidance method and apparatus, a device, and a medium. The method comprises: establishing a dynamic traffic network capable of real-time updates; constructing a road traffic impedance model and an electric vehicle power consumption model; respectively constructing a private vehicle travel behavior model and a ride-hailing vehicle travel behavior model; constructing a user charging satisfaction quantification index; providing charging selection modes for different types of electric vehicles; and predicting the charging load of charging stations within each time period, and formulating a dynamic pricing strategy for the charging stations with the objective of minimizing load fluctuations at each charging station. For the travel models of different types of electric vehicles, including private vehicles and ride-hailing vehicles, the spatio-temporal distribution of fast-charging load is optimized, and by means of price regulation, the strategy can guide users to charge during low-load periods, thereby balancing the load of each charging station, reducing the power fluctuation pressure on a distribution network caused by fast charging, and ensuring stable operation of a power grid.

Description

Methods, devices, equipment and media for guiding demand for fast charging of electric vehicles Technical Field

[0001] This invention relates to the field of electric vehicle charging guidance technology, and in particular to a method, apparatus, equipment and medium for guiding fast charging demand of electric vehicles. Background Technology

[0002] Electric vehicle charging stations typically offer both fast and slow charging options. Fast charging, compared to slow charging, generates a massive power demand within a short period, which can significantly negatively impact the power distribution network. Therefore, guiding users to distribute their electric vehicles evenly across various charging stations for fast charging when their batteries are low, thereby altering the spatiotemporal distribution of fast charging load, is crucial for maintaining stable voltage in the power distribution network. Guiding electric vehicle charging primarily aims to reduce congestion at charging stations and improve the utilization rate of charging facilities.

[0003] However, existing electric vehicle charging guidance primarily influences users' charging decisions by adjusting electricity prices, typically using price reductions to attract users to charge during specific time periods. However, this approach has significant limitations in practice. Simple price adjustments cannot fully consider the specific travel needs and behavioral characteristics of electric vehicle users, making it difficult to accurately guide users to distribute their charging load. Therefore, existing charging guidance measures have limited effectiveness in improving the utilization rate of charging facilities and alleviating congestion. There is an urgent need for more detailed behavioral analysis and quantification of charging satisfaction for different user groups, combined with optimization using appropriate pricing strategies.

[0004] The information disclosed in this background section is intended only to enhance the understanding of the general background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and medium for guiding fast charging demand for electric vehicles, thereby effectively solving the problems in the background art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is: a method for guiding fast charging demand for electric vehicles, comprising the following steps:

[0007] S10: Obtain road, traffic and charging station information to establish a dynamic transportation network with real-time updates;

[0008] S20: Based on the dynamic traffic network, considering the road travel time and road speed of electric vehicles under different traffic conditions, construct a road traffic impedance model and an electric vehicle power consumption model;

[0009] S30: Based on the road traffic impedance model and the electric vehicle power consumption model, simulate the travel behavior of electric vehicles, classify electric vehicles into different types according to their different travel patterns, including private cars and ride-hailing vehicles, and construct private car travel behavior models and ride-hailing vehicle travel behavior models respectively.

[0010] S40: Based on the private car travel behavior model and the ride-hailing travel behavior model, and taking into account travel time, charging price and energy consumption, construct a quantitative indicator of user charging satisfaction.

[0011] S50: Based on the aforementioned quantitative indicators of user charging satisfaction and the queuing system of charging stations, a charging selection model for different types of electric vehicles is proposed.

[0012] S60: Based on the charging selection model and the queuing system of the charging station, predict the charging load of the charging station in each time period, and implement a dynamic pricing strategy for the charging station with the goal of minimizing the load fluctuation of each charging station.

[0013] Further, in step S20, the road traffic impedance model includes:

[0014] ;

[0015] In the formula, Rl represents the total travel time for road segment l; Tl represents the total travel time for road segment l. 0, l The travel time when road segment l is unobstructed; For road segment l, traffic flow is provided. L represents the actual traffic capacity of road segment l; l N is the length of road segment l; l Let τ be the number of roadside vehicles on road segment l; τ is the influence coefficient of roadside vehicles on the traffic flow of the road segment.

[0016] Further, in step S20, the electric vehicle power consumption model includes:

[0017] ;

[0018] In the formula, E lose ,l V represents the electricity consumption of an electric vehicle on road segment l. l L represents the average speed of an electric vehicle traveling on road segment l. Different road grades and road conditions correspond to different speeds. l Let l be the length of road segment l; a, b, and c are power consumption coefficients.

[0019] Furthermore, in step S30, based on the different travel patterns of electric vehicles, electric vehicle types are classified, including private cars and ride-hailing vehicles, and separate travel behavior models for private cars and ride-hailing vehicles are constructed, including:

[0020] S31: Determine the travel behavior of private cars, including using travel chains with residential areas as the starting and ending points to describe the travel behavior of private cars, and the first trip time and stay time of each type of travel chain follow a normal distribution.

[0021] S32: Determine the travel behavior of ride-hailing vehicles, including describing the travel behavior of ride-hailing vehicles using a travel state transition matrix. The first travel time and number of trips of ride-hailing vehicles follow a normal distribution.

[0022] S33: Based on the travel behavior of the private car and the ride-hailing vehicle, plan the routes for the private car and the ride-hailing vehicle respectively, including:

[0023] Private cars plan routes with the goal of finding the shortest travel time during their journeys;

[0024] When a ride-hailing service is carrying passengers, it plans routes with the goal of minimizing the distance traveled by electric vehicles. When a ride-hailing service is empty, it plans routes with the goal of minimizing the energy consumption of electric vehicles or the travel time on roads.

[0025] S34: Based on the route planning for private cars and ride-hailing vehicles, calculate the arrival time and remaining battery power of electric vehicles.

[0026] Further, in step S34, the arrival time and remaining battery power of the electric vehicle are calculated, and the model includes:

[0027] ;

[0028] ;

[0029] In the formula, The time when the h-th electric vehicle arrives at the activity location p; The time when the h-th electric vehicle leaves the activity location p-1; Ω represents the travel time from node i to node j. p -1, p This is the set of road segments along the path from activity location p-1 to activity location p. The remaining battery power of the h-th electric vehicle upon arrival at location p; The remaining battery power of the h-th electric vehicle when it leaves the activity location p-1; This represents the power consumption of the road segment from node i to node j.

[0030] Furthermore, in step S40, considering travel time, charging electricity price, and energy consumption, a quantitative indicator of user charging satisfaction is constructed, including:

[0031] ;

[0032] In the formula, f CSR ,k Overall charging satisfaction for electric vehicles at charging station k; f1 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; f2 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; f3 ,k Satisfaction with the charging price of electric vehicles reaching charging station k; α, γ and γ are the weighting coefficients of the user charging satisfaction index, and their sum is 1.

[0033] Further, in step S50, based on the user charging satisfaction quantification index and the charging station queuing system, a charging selection model for different types of electric vehicles is proposed, including:

[0034] S51: Determining the charging needs of private cars, including whether, before each trip, if the remaining battery power of an electric vehicle is insufficient to support reaching the next destination, the electric vehicle user will choose to detour to a charging station to charge; if fast charging is required during the trip between two stops, the private car will detour to a charging station to charge.

[0035] S52: Determining the charging needs of ride-hailing vehicles, including when a ride-hailing vehicle is in a state of no load and its battery charge is below a certain level, it will go to a charging station to charge before picking up passengers.

[0036] S53: Based on the judgment of the charging demand of the private car and the judgment of the charging demand of the ride-hailing vehicle, select the most suitable charging station based on the quantitative index of user charging satisfaction, and calculate the charging time and load demand based on the initial power and charging station conditions.

[0037] S54: Based on the charging time and load demand, the queuing system of the charging station determines the queuing and charging order of electric vehicles according to the first-come, first-served principle.

[0038] Further, in step S60, based on the charging selection model and the queuing system of the charging station, the charging load of the charging station is predicted for each time period, and a dynamic pricing strategy for the charging station with the goal of minimizing load fluctuations at each charging station is implemented, including:

[0039] S61: Construct a charging station load prediction model to obtain the predicted charging load of the charging station;

[0040] S62: Based on the maximum charging load capacity that different charging stations can accommodate, the predicted load of each charging station is reduced to the maximum capacity, and the average predicted load of the charging station is calculated.

[0041] S63: When the difference between the predicted charging load of each charging station and the average predicted load is less than or greater than the adjustment threshold, the electricity price of the charging station shall be adjusted.

[0042] S64: Adjust the charging station electricity price as described above, and optimize the charging electricity price adjustment step size based on the particle swarm optimization algorithm with compression factor.

[0043] Further, in step S62, the average predicted load of the charging station is calculated, and the model includes:

[0044] ;

[0045] ;

[0046] In the formula, Let t be the average forecasted load demand for the time period t; σ represents the predicted load demand of charging station k during time period t; k Let σ be the reduction factor for charging station k. When the charging load capacity of charging station k is equal to the maximum capacity among all charging stations, then σ... k =1; K is the total number of charging stations; q k Let k be the number of charging piles in charging station k.

[0047] Further, in step S63, when the difference between the predicted charging load demand of each charging station and the average predicted load is less than or greater than an adjustment threshold, the electricity price of the charging station is adjusted. The model includes:

[0048] ;

[0049] In the formula, C k , t Let Δc be the charging electricity price at charging station k during time period t; k The step size for adjusting the charging electricity price; ε is the dead zone coefficient; Let t be the average forecasted load demand for the time period t; σ represents the predicted load demand of charging station k during time period t; k Let σ be the reduction factor for charging station k. When the charging load capacity of charging station k is equal to the maximum capacity among all charging stations, then σ... k =1.

[0050] The present invention also includes a fast-charging demand guidance device for electric vehicle users' charging intentions, using the method described above, comprising:

[0051] The dynamic transportation network establishment unit is used to acquire road, traffic and charging station information to establish a dynamic transportation network that is updated in real time.

[0052] The impedance and power consumption model building unit is used to build a road traffic impedance model and an electric vehicle power consumption model based on the dynamic traffic network, considering the road travel time and road speed of electric vehicles under different traffic conditions.

[0053] The travel behavior model construction unit is used to simulate the travel behavior of electric vehicles based on the road traffic impedance model and the electric vehicle power consumption model. According to the different travel patterns of electric vehicles, electric vehicle types are divided, including private cars and ride-hailing vehicles, and travel behavior models for private cars and ride-hailing vehicles are constructed respectively.

[0054] The user satisfaction construction unit is used to construct a quantitative indicator of user charging satisfaction based on the private car travel behavior model and the ride-hailing travel behavior model, taking into account travel time, charging price and energy consumption.

[0055] The charging selection model construction unit is used to propose charging selection models for different types of electric vehicles based on the quantitative indicators of user charging satisfaction and the queuing system of charging stations.

[0056] The dynamic pricing strategy unit is used to predict the charging load of charging stations in each time period based on the charging selection model and the queuing system of the charging station, and to implement a dynamic pricing strategy for charging stations with the goal of minimizing the load fluctuation of each charging station.

[0057] The present invention also includes a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described above.

[0058] The present invention also includes a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described above.

[0059] The beneficial effects of this invention are as follows:

[0060] This invention accurately depicts the travel and charging behaviors of various electric vehicles by comprehensively considering real-time changes in traffic flow and the travel behavior patterns of different types of electric vehicles. Based on the actual needs of different users, it establishes a quantitative index for user charging satisfaction and, combined with appropriate charging pricing strategies, rationally guides electric vehicles towards fast charging. For different types of electric vehicles, such as private cars and ride-hailing vehicles, the system can address potential peak charging loads at specific times and locations, optimizing the spatiotemporal distribution of fast charging loads. In this way, it effectively reduces the pressure on the power distribution network during peak charging times and maintains the stability of the grid voltage. Furthermore, this invention lays an important technical foundation for further research into comprehensive charging guidance strategies that simultaneously consider both slow and fast charging of electric vehicles. Attached Figure Description

[0061] 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 recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 is a flowchart illustrating the method for guiding demand for fast charging of electric vehicles.

[0063] Figure 2 is a flowchart of the electric vehicle fast charging demand guidance method;

[0064] Figure 3 is a flowchart of private car charging demand forecasting;

[0065] Figure 4 is a flowchart of the ride-hailing vehicle charging demand forecasting process.

[0066] Figure 5 shows the dynamic pricing flowchart for charging stations;

[0067] Figure 6 is a schematic diagram of the fast charging demand guidance device for electric vehicle users' charging intentions.

[0068] Figure 7 is a schematic diagram of the structure of a computer device. Detailed Implementation

[0069] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0070] As shown in Figures 1 to 5: A method for guiding fast charging demand for electric vehicles includes the following steps:

[0071] S10: Obtain road, traffic and charging station information to establish a dynamic transportation network with real-time updates;

[0072] S20: Based on the dynamic traffic network, considering the road travel time and speed of electric vehicles under different traffic conditions, a road traffic impedance model and an electric vehicle power consumption model are constructed.

[0073] S30: Based on the road traffic impedance model and electric vehicle power consumption model, simulate the travel behavior of electric vehicles. According to the different travel patterns of electric vehicles, classify electric vehicles into types, including private cars and ride-hailing vehicles, and construct private car travel behavior models and ride-hailing vehicle travel behavior models respectively.

[0074] S40: Based on private car travel behavior models and ride-hailing travel behavior models, and taking into account travel time, charging price and energy consumption, a quantitative indicator of user charging satisfaction is constructed.

[0075] S50: Based on quantitative indicators of user charging satisfaction and the queuing system of charging stations, a charging selection model for different types of electric vehicles is proposed.

[0076] S60: Based on the charging selection model and the queuing system of charging stations, it predicts the charging load of charging stations in different time periods and implements a dynamic pricing strategy for charging stations with the goal of minimizing load fluctuations at each charging station.

[0077] This invention accurately depicts the travel and charging behaviors of various electric vehicles by comprehensively considering real-time changes in traffic flow and the travel behavior patterns of different types of electric vehicles. Based on the actual needs of different users, it establishes a quantitative index for user charging satisfaction and, combined with appropriate charging pricing strategies, rationally guides electric vehicles towards fast charging. For different types of electric vehicles, such as private cars and ride-hailing vehicles, the system can address potential peak charging loads at specific times and locations, optimizing the spatiotemporal distribution of fast charging loads. In this way, it effectively reduces the pressure on the power distribution network during peak charging times and maintains the stability of the grid voltage. Furthermore, this invention lays an important technical foundation for further research into comprehensive charging guidance strategies that simultaneously consider both slow and fast charging of electric vehicles.

[0078] By constructing a road traffic impedance model and an electric vehicle power consumption model, and considering the travel time and power consumption of electric vehicles under different traffic conditions, the charging guidance strategy can more accurately predict the remaining power and driving range of vehicles, thereby helping users to plan charging time and location more scientifically.

[0079] By classifying electric vehicles into different types, such as private cars and ride-hailing vehicles, and constructing separate travel behavior models, we can provide personalized guidance for the travel needs and charging behaviors of different types of electric vehicles. For different types of electric vehicle users, we can provide more personalized charging guidance strategies, ensuring that the guidance measures can adapt to the charging habits and travel needs of different users, thus making up for the shortcomings of existing methods that do not adequately consider the differentiated needs of users.

[0080] By constructing a quantitative indicator of user charging satisfaction, which comprehensively considers multiple factors such as travel time, charging price, and energy consumption, the overall charging experience of users can be significantly improved. Users no longer choose charging stations based on a single factor (such as price), but make intelligent decisions based on comprehensive satisfaction, thereby improving the comfort and satisfaction during the charging process.

[0081] Based on user charging satisfaction and the charging station queuing system, a dynamic charging station selection model is proposed to guide electric vehicle users to choose suitable charging stations according to their actual needs, avoid overcrowding at some charging stations, optimize the allocation of charging resources, reduce excessive congestion at charging stations during peak hours, optimize the utilization rate of charging facilities, and enable more users to complete charging more efficiently. This solves the problem of uneven resource allocation caused by user crowding at existing charging stations.

[0082] Based on the charging selection model and the queuing system of charging stations, and combined with the prediction of charging station load in different time periods, a dynamic pricing strategy is proposed with the goal of minimizing charging station load fluctuations. This strategy can guide users to charge when the load is low through price regulation, thereby balancing the load of each charging station, reducing the power fluctuation pressure on the distribution network caused by fast charging, and ensuring the stable operation of the power grid.

[0083] As a preferred embodiment of the above, in step S20, the road traffic impedance model includes:

[0084] ;

[0085] In the formula, Rl represents the total travel time for road segment l; Tl represents the total travel time for road segment l. 0, l The travel time when road segment l is unobstructed; The traffic load of road segment l; For road segment l, traffic flow is provided. L represents the actual traffic capacity of road segment l; l N is the length of road segment l; l Let τ be the number of roadside vehicles on road segment l; τ is the influence coefficient of roadside vehicles on the traffic flow of the road segment.

[0086] This model not only considers travel time under normal and smooth conditions, but also incorporates actual conditions such as traffic load and road length, enabling it to dynamically reflect road resistance under different traffic conditions. By using traffic load and the roadside vehicle influence coefficient τ, this scheme can well adapt to the travel needs of electric vehicles under different complex road conditions, especially on congested or narrow roads, providing a more realistic time estimate.

[0087] In this embodiment, the electric vehicle power consumption model in step S20 includes:

[0088] ;

[0089] In the formula, E lose ,l Electricity consumption of electric vehicles on road segment l; V l L represents the average speed of an electric vehicle traveling on road segment l. Different road grades and road conditions correspond to different speeds. l Let l be the length of road segment l; a, b, and c are power consumption coefficients.

[0090] The model takes into account the changes in driving speed caused by different road grades and road conditions, enabling it to flexibly adapt to various real-world road conditions and more closely reflect the energy consumption performance of electric vehicles in real-world environments. The accurate energy consumption calculation provides electric vehicle users with a more comprehensive energy consumption estimate when choosing different routes, helping users select the most energy-efficient driving route or charging station based on their current battery level.

[0091] As a preferred embodiment of the above, in step S30, electric vehicles are classified into different types based on their different travel patterns, including private cars and ride-hailing vehicles, and separate travel behavior models for private cars and ride-hailing vehicles are constructed, including:

[0092] S31: Determine the travel behavior of private cars, including using travel chains with residential areas as the starting and ending points to describe the travel behavior of private cars, and the first trip time and stay time of each type of travel chain follow a normal distribution.

[0093] S32: Determine the ride-hailing behavior, including describing the ride-hailing behavior using a ride state transition matrix. The first trip time and number of trips for ride-hailing services follow a normal distribution. The ride state transition matrix can be represented as:

[0094] ;

[0095] In the formula, p t p represents the state transition matrix of an electric vehicle for each time period within a 24-hour day. mn(m,n=1,2,3) represents the transition probability of electric vehicles between various functional areas; R, W and O represent other areas such as residential area, work area and commercial area, respectively.

[0096] S33: Based on the travel behavior of private cars and ride-hailing vehicles, plan the routes for private cars and ride-hailing vehicles respectively, including:

[0097] Private cars plan routes with the goal of finding the shortest travel time during their journeys;

[0098] When a ride-hailing service is carrying passengers, it plans routes with the goal of minimizing the distance traveled by electric vehicles. When a ride-hailing service is empty, it plans routes with the goal of minimizing the energy consumption of electric vehicles or the travel time on roads.

[0099] S34: Based on the route planning of private cars and ride-hailing vehicles, calculate the arrival time and remaining battery power of electric vehicles.

[0100] Private cars and ride-hailing services differ significantly in their travel patterns. By building separate models, their behavioral characteristics can be more accurately depicted. Private cars mainly follow fixed travel chains, while ride-hailing services involve more random factors. The state transition matrix can better simulate the complex operational patterns of ride-hailing services. Personalized behavioral modeling helps to provide more accurate charging guidance for different user groups, avoiding the neglect of user needs by a single model and improving the flexibility and accuracy of charging guidance.

[0101] In step S34, the arrival time and remaining battery power of the electric vehicle are calculated, and the model includes:

[0102] ;

[0103] ;

[0104] In the formula, The time when the h-th electric vehicle arrives at the activity location p; The time when the h-th electric vehicle leaves the activity location p-1; Ω represents the travel time from node i to node j. p -1, p This is the set of road segments along the path from activity location p-1 to activity location p. The remaining battery power of the h-th electric vehicle upon arrival at location p; The remaining battery power of the h-th electric vehicle when it leaves the activity location p-1; This represents the power consumption of the road segment from node i to node j.

[0105] This model combines electric vehicle route planning, travel time, and energy consumption to provide high-precision basic data for the charging guidance system. This enables the system to not only dynamically adjust charging recommendations based on the electric vehicle's real-time remaining battery power and travel time, but also to provide users with intelligent charging station selection and optimal charging timing. Through accurate arrival time prediction, the system can better guide users to adjust charging time, reducing wasted time on the road. Through precise energy consumption calculation, users can select the most suitable charging station and time based on the vehicle's actual energy consumption, avoiding premature charging or missing charging opportunities, thus improving charging efficiency.

[0106] In this embodiment, in step S40, considering travel time, charging price, and energy consumption, a quantitative indicator of user charging satisfaction is constructed, including:

[0107] S41: The following is a summary of electric vehicle users' satisfaction with charging travel time:

[0108] ;

[0109] In the formula, f1 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; T k T represents the travel time of the electric vehicle to charging station k. min The shortest travel time for an electric vehicle to reach all available charging stations; T max The longest journey time for an electric vehicle to reach all available charging stations; T wait, k The charging wait time for the electric vehicle to arrive at charging station k; T waitmax The maximum charging queue time that electric vehicle users can tolerate;

[0110] S42: The following is a summary of electric vehicle user satisfaction with electricity consumption during charging distances:

[0111] ;

[0112] In the formula, f2 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; P lose, k P represents the amount of electricity consumed by the electric vehicle when it reaches charging station k. losemin The minimum amount of electricity consumed by an electric vehicle when traveling to all available charging stations; P losemax The electric vehicle consumes the most electricity when traveling to all available charging stations;

[0113] S43: The following is a summary of electric vehicle user satisfaction with charging electricity prices:

[0114] ;

[0115] In the formula, f3 ,k Satisfaction with the charging price of electric vehicles reaching charging station k; C k The electricity price for an electric vehicle to reach charging station k; C min The lowest electricity price for electric vehicles to reach all available charging stations; C max The highest charging price for electric vehicles among all available charging stations;

[0116] S44: The following are the comprehensive charging satisfaction indicators for electric vehicle users:

[0117] ;

[0118] In the formula, f CSR ,k The overall charging satisfaction rate of electric vehicles at charging station k will be used as a quantitative indicator of user charging satisfaction; f1 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; f2 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; f3 ,k Satisfaction with the charging price of electric vehicles reaching charging station k; α, γ and γ are the weighting coefficients of the user charging satisfaction index, and their sum is 1.

[0119] By comprehensively considering three dimensions—travel time, power consumption, and electricity price—a more accurate quantitative model for user charging satisfaction was constructed. This model can be adjusted according to the preferences of different users, making charging guidance more personalized. By balancing the distribution of users across different charging stations, the resource utilization rate of charging stations is optimized, avoiding waste or unreasonable allocation of charging station resources. Electricity price satisfaction, as an important indicator for users to choose charging stations, can effectively guide users to charge during periods of lower electricity prices and lighter loads, thereby reducing the pressure on charging stations during peak hours, reducing load fluctuations at charging stations during peak periods, improving the stability and safety of the power grid and charging stations, balancing the load on charging stations, and optimizing the operation of the charging network.

[0120] As a preferred embodiment of the above, in step S50, based on the quantitative index of user charging satisfaction and the queuing system of the charging station, a charging selection model for different types of electric vehicles is proposed, including:

[0121] S51: Determining the charging needs of private cars, including whether, before each trip, if the remaining battery power of the electric vehicle is insufficient to reach the next destination, the electric vehicle user will choose to detour to a charging station to charge; if fast charging is required during the trip between two stops, the private car will detour to charging station k to charge; the charging needs determination is as follows:

[0122] ;

[0123] In the formula, The minimum amount of electricity required to reach the nearest charging station to destination p;

[0124] S52: Determining the charging needs of ride-hailing vehicles, including determining whether a ride-hailing vehicle will recharge at a charging station before picking up passengers if its battery level falls below a certain threshold and it is unloaded during a trip; the determination of ride-hailing vehicle charging needs is as follows:

[0125] ;

[0126] In the formula, δ is the energy coefficient used to determine whether the taxi needs to be charged; E 0, h The battery capacity of electric vehicle h;

[0127] S53: Based on the assessment of charging demand for private cars and ride-hailing vehicles, the most suitable charging station is selected based on the quantitative index of user charging satisfaction. The charging time and load demand are calculated based on the initial battery level and charging station conditions. The charging time for electric vehicles can be expressed as:

[0128] ;

[0129] In the formula, T C Charging time for electric vehicles; E O E represents the ideal state of charge for electric vehicles. t The initial state of charge (η) of the electric vehicle during charging. C For charging efficiency; P C This refers to the charging power.

[0130] The charging load of an electric vehicle can be expressed as:

[0131] ;

[0132] In the formula, P k , t P represents the charging load demand of charging station k during time period t. h , k ,t The charging load demand of electric vehicle h at charging station during time periods k and t; N is the total number of electric vehicles;

[0133] S54: Based on charging time and load demand, the queuing system of the charging station determines the queuing and charging order of electric vehicles according to the first-come, first-served principle.

[0134] Based on the relationship between the number of electric vehicles and the number of chargers in the station, there exist queuing queues and charging queues. This is represented by the set A = {tarrive h,k|hÎ[1,N...}. k ]} and D={tdeparture h,k|hÎ[1,N k Record the arrival and departure times of electric vehicle h at fast charging station k in chronological order, where N k Let k be the number of electric vehicles charging at charging station k; the number of vehicles charging at charging station k in each time period can be expressed as:

[0135] ;

[0136] In the formula, NEV(k,t) is the number of vehicles that need to be charged at charging station k during time period t; num(A,t) and num(D,t) are the cumulative number of electric vehicles that arrive and leave before time t.

[0137] When there are charging stations available, the charging queue time for electric vehicles is 0; otherwise, the charging queue time for electric vehicles is as follows:

[0138] ;

[0139] In the formula, t w The remaining charging time for the electric vehicle; Let k be the number of charging piles at charging station k.

[0140] By assessing the charging needs of private cars and ride-hailing vehicles separately, the system can provide personalized charging suggestions for different types of users. Private car owners prioritize driving safety and battery life, while ride-hailing vehicles prioritize charging time and operational efficiency. The system optimizes its charging guidance strategies accordingly. This personalized charging guidance effectively enhances the system's flexibility, meets the actual needs of different user groups, and reduces uncertainty in charging decisions.

[0141] Figure 3 shows the flowchart for forecasting private car charging demand: Specific steps include:

[0142] Initialize input raw data: When the system starts, the system first inputs raw data, including vehicle information, charging status, travel plans, etc. of private cars;

[0143] Set initial loop parameters: Initialize the loop variable h to 1, indicating that the data of the first private car will be processed.

[0144] Read vehicle battery capacity: Read the battery capacity of the h-th private car and obtain its current remaining power.

[0145] Extract trip chain type: Based on the vehicle's historical behavior data or planned trip, extract the trip chain type of the private car and record the first departure time, initial battery level, and initial departure node;

[0146] Extract the destination node from the trip chain: Extract the destination node for this trip from the trip chain;

[0147] Route planning: The system aims to minimize travel time by planning the shortest route for a private car from its current starting point to its destination; based on this route, it calculates the time and battery power consumed by the private car to reach the target node from its current starting point.

[0148] Check battery level: Determine the remaining battery power of the private car when it reaches the target location. Is it below the minimum power required to reach the next target node? ;

[0149] If yes, the system will plan a detour for the vehicle to the nearest charging station, selecting the charging station with the highest user charging satisfaction (considering factors such as charging time, electricity price, and waiting time); after charging is completed, the system will replan the shortest path to continue to the target node; if no, the system will directly follow the originally planned path to the target node without detouring to the charging station.

[0150] Check if the trip has ended: After the vehicle arrives at the target node, the system checks whether it has reached the starting node of the trip chain (indicating whether the current trip chain has ended).

[0151] If not, update the trip chain status and continue processing the next segment of the trip; return to the step of extracting the trip chain type, extract the destination of the next segment of the trip chain, and repeat the above steps. If yes, check if there is any other vehicle (h) data that needs to be processed.

[0152] Process the next private car's data: If more private car data needs to be processed, the system will increment h by 1, read the battery capacity of the next car, and repeat the above steps; if the trips of all vehicles have been processed, the process ends.

[0153] Figure 4 shows the flowchart for forecasting charging demand for ride-hailing vehicles; the specific steps include:

[0154] Input raw data: The system first inputs the raw data of the ride-hailing vehicle, including information such as the vehicle's battery capacity and travel records;

[0155] Set loop parameters: Initialize the loop variable h to 1, indicating that the data of the first ride-hailing vehicle will be processed;

[0156] Read the battery capacity of ride-hailing vehicles: The system reads the battery capacity of the h-th ride-hailing vehicle to obtain the current remaining power information;

[0157] Extracting trip count and initial status: The system extracts the number of trips, first departure time, initial battery state (SOC, State of Charge), and initial departure node of the ride-hailing vehicle; the system records the vehicle's current battery capacity and current location to prepare for subsequent planning;

[0158] Check if the remaining battery level is below the threshold: Determine the remaining battery level of the ride-hailing vehicle. Is the battery level below the threshold? (Battery capacity minimum value);

[0159] If the battery is low, the system will automatically enter charging mode, plan the vehicle to a suitable charging station, select the charging station with the highest user satisfaction, and optimize the charging strategy; otherwise, if the battery is sufficient, the system will continue to plan the next step of the journey.

[0160] Extracting the destination node based on the state transition matrix: Using the state transition matrix model, the system extracts the next target destination node of the ride-hailing vehicle. This step is based on dynamic programming of the ride-hailing vehicle's operating model and the state transition matrix.

[0161] Route planning and energy consumption calculation: The system performs route planning with the goal of minimizing energy consumption, determines the optimal driving route from the current node to the target node, and calculates the time required for the ride-hailing vehicle to reach the target node and the amount of electricity consumed.

[0162] Check if the number of trips has reached the predetermined value: The system determines whether the current number of trips for the ride-hailing vehicle is equal to the preset number of sampling trips;

[0163] If not, proceed to the next trip. The return step extracts the destination node based on the state transition matrix, continues to extract the next target node, and performs path planning and power consumption calculation; if yes, the current ride-hailing vehicle's charging demand prediction process ends.

[0164] Process the next ride-hailing vehicle's data: If more ride-hailing vehicle data needs to be processed, the system increments h by 1, reads the battery capacity of the next vehicle, and repeats the above steps; if all vehicle data has been processed, the process ends.

[0165] As a preferred embodiment of the above, in step S60, based on the charging selection model and the queuing system of the charging station, the charging load of the charging station is predicted for each time period, and a dynamic pricing strategy for the charging station with the goal of minimizing the load fluctuation of each charging station is implemented, including:

[0166] S61: Construct a charging station load prediction model to obtain the predicted charging load of the charging station; the model includes:

[0167] ;

[0168] In the formula, The predicted load demand of charging station k in time period t+1; The new load at charging station k during time period t; The charging load of charging station k during time period t; To determine the load that will be charged at charging station k during time period t; The charging load cancelled at charging station k during the t+1 period;

[0169] S62: Based on the maximum charging load capacity that different charging stations can accommodate, the predicted load of each charging station is reduced to the maximum capacity, and the average predicted load of the charging station is calculated.

[0170] S63: When the difference between the predicted charging load and the average predicted load of each charging station is less than or greater than the adjustment threshold, the electricity price of the charging station shall be adjusted.

[0171] S64: Based on the adjustment of the charging station electricity price, the step size Δc of the charging electricity price adjustment is determined using a particle swarm optimization algorithm with a compression factor. k Optimizations will be implemented to ensure that when there are significant differences in load at different charging stations, electricity price adjustments can effectively guide users to charging stations with lower loads, thereby reducing load fluctuations.

[0172] Through reasonable load forecasting and dynamic pricing control, the system can effectively avoid overcharging during peak periods, reduce the impact of peak charging periods on the distribution network, ensure the stable operation of the distribution network, reduce the grid burden during peak hours, avoid grid pressure caused by concentrated fast charging demand, and improve the overall stability and security of the grid. Through load forecasting and price adjustment, the system can rationally allocate charging station resources, reduce users' queuing and waiting time during peak hours, improve the efficiency of the overall charging process, reduce user waiting time, improve the charging experience, and at the same time improve the overall operating efficiency of the system, enabling charging stations to operate in a more efficient environment.

[0173] In step S62, the average predicted load of the charging station is calculated, and the model includes:

[0174] ;

[0175] ;

[0176] In the formula, Let t be the average forecasted load demand for the time period t; σ represents the predicted load demand of charging station k during time period t; k Let σ be the reduction factor for charging station k. When the charging load capacity of charging station k is equal to the maximum capacity among all charging stations, then σ... k =1; K is the total number of charging stations; q k Let k be the number of charging piles in charging station k.

[0177] By predicting the load of charging stations and calculating the average load, the system can identify which charging stations may exceed the safety threshold earlier, allowing for proactive adjustments. This not only optimizes the load distribution of charging stations but also avoids the pressure on the power distribution network caused by excessive load, ensuring the stable operation of the power distribution network. It reduces the load fluctuation pressure caused by fast charging of electric vehicles, protects the operation safety of the power grid, and improves the stability of the overall power supply system. Through load prediction and reasonable electricity price adjustments, users can more accurately select charging stations with lower loads, thereby reducing waiting time. The system can alleviate congestion at charging stations during peak hours by dynamically adjusting electricity prices and load distribution, improving user charging efficiency and overall experience. It also reduces the time users spend waiting to charge during peak hours, optimizes the charging experience, and improves the service quality of the charging system.

[0178] In this embodiment, in step S63, when the difference between the predicted charging load demand and the average predicted load of each charging station is less than or greater than the adjustment threshold, the electricity price of the charging station is adjusted. The model includes:

[0179] ;

[0180] In the formula, C k , t Let Δc be the charging electricity price at charging station k during time period t; k The step size for adjusting the charging electricity price; ε is the dead zone coefficient; Let t be the average forecasted load demand for the time period t; σ represents the predicted load demand of charging station k during time period t; k Let σ be the reduction factor for charging station k. When the charging load capacity of charging station k is equal to the maximum capacity among all charging stations, then σ... k =1.

[0181] Through dynamic electricity price adjustment, the system can effectively guide users to charge during periods of lighter load, reducing the pressure on the power grid during peak hours, ensuring grid stability, balancing electric vehicle charging demand with grid load fluctuations, making the charging process smoother and more efficient, reducing the impact of peak charging periods on the power grid, improving grid stability, and ensuring a dynamic balance between electric vehicle charging demand and grid load. Through a load forecast-based electricity price adjustment model, the system can provide users with real-time and accurate electricity price information, helping them make more rational charging choices. Users can select the most suitable charging station and time period based on dynamic changes in load and electricity prices, reducing charging costs. This enhances the intelligence level of users' charging decisions, helping them reduce charging costs, improve charging efficiency, and enhance user experience.

[0182] As shown in Figure 5, the dynamic pricing flowchart for charging stations of the present invention includes the following specific steps:

[0183] Input raw data: The system first inputs the raw data of the charging stations, including basic information such as the real-time load, historical data, and current electricity price of each charging station;

[0184] Determine the initial site selection results: Based on the input data, the system initially determines the initial state of each charging station and calculates the predicted load of each charging station in different time periods;

[0185] Obtain the predicted load of each charging station for each time period: Based on the initial station selection results, the system calculates the predicted load value of each charging station for each time period, and generates the load prediction for each time period by combining historical data and the current charging demand of electric vehicles.

[0186] Based on the predicted load for each time period, the average predicted load of the charging station is obtained: the system calculates the average predicted load of each charging station by generalizing the load for each time period; this step helps to standardize the load of charging stations with different capacities, so that subsequent electricity price adjustments can be based on a unified standard.

[0187] Based on the average predicted load of the charging station, the system determines whether to update the electricity price: It compares the current load of the charging station with the average predicted load to determine whether the current load exceeds or falls below the adjustment threshold. If the load fluctuates significantly, the electricity price for the charging station needs to be adjusted.

[0188] The system uses intelligent optimization algorithms (such as particle swarm optimization) to calculate and optimize the step size Δck of the charging price adjustment, so as to ensure that the price adjustment range is reasonable and avoid unreasonable user behavior caused by excessive or insufficient adjustments.

[0189] Update the electricity price of each charging station: Based on the optimization results, the system updates the electricity price of each charging station to match the real-time load level, so as to guide users to reasonably distribute their charging demand.

[0190] Loop Check: The system checks whether the current loop has exceeded the predetermined number of loops, or whether the difference between the two consecutive electricity price updates has become minimal; if so (e.g., the optimal electricity price has been reached or the electricity price change has stabilized), the loop ends; otherwise, it returns to the step of obtaining the predicted load of each charging station for each time period and continues to optimize the electricity price.

[0191] The optimal electricity price for each charging station is obtained: After multiple iterations of optimization, the system obtains the optimal electricity price for each charging station under different load conditions, ensuring load balance and optimizing resource utilization.

[0192] The present invention also includes a fast-charging demand guidance device for electric vehicle users' charging intentions, using the method described above, as shown in Figure 6, comprising:

[0193] The dynamic transportation network establishment unit is used to acquire road, traffic and charging station information to establish a dynamic transportation network that is updated in real time.

[0194] Impedance and power consumption model building unit is used to build a road traffic impedance model and an electric vehicle power consumption model based on a dynamic traffic network, considering the road travel time and road speed of electric vehicles under different traffic conditions.

[0195] The travel behavior model building unit is used to simulate the travel behavior of electric vehicles based on the road traffic impedance model and the electric vehicle power consumption model. According to the different travel patterns of electric vehicles, electric vehicles are classified into private cars and ride-hailing vehicles, and travel behavior models for private cars and ride-hailing vehicles are built respectively.

[0196] The user satisfaction construction unit is used to construct quantitative indicators of user charging satisfaction based on private car travel behavior models and ride-hailing travel behavior models, taking into account travel time, charging price and energy consumption.

[0197] The charging selection model building unit is used to propose charging selection models for different types of electric vehicles based on quantitative indicators of user charging satisfaction and the queuing system of charging stations.

[0198] The dynamic pricing strategy unit is used to predict the charging load of charging stations in different time periods based on the charging selection model and the queuing system of charging stations, and to implement a dynamic pricing strategy for charging stations with the goal of minimizing the load fluctuation of each charging station.

[0199] Please refer to Figure 7, which shows a schematic diagram of the structure of a computer device provided in an embodiment of this application. An embodiment of this application provides a computer device 400, including a processor 410 and a memory 420. The memory 420 stores a computer program executable by the processor 410. When the computer program is executed by the processor 410, it performs the method described above.

[0200] This application embodiment also provides a storage medium 430, on which a computer program is stored, and the computer program is executed by a processor 410 to perform the above method.

[0201] The storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0202] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. "A plurality of" means two or more, unless otherwise explicitly specified.

[0203] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0204] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0205] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0206] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered 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-included 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. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), 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). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0207] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in 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.

[0208] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0209] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for guiding fast charging demand for electric vehicles, characterized in that, Includes the following steps: S10: Obtain road, traffic and charging station information to establish a dynamic transportation network with real-time updates; S20: Based on the dynamic traffic network, considering the road travel time and road speed of electric vehicles under different traffic conditions, construct a road traffic impedance model and an electric vehicle power consumption model; S30: Based on the road traffic impedance model and the electric vehicle power consumption model, simulate the travel behavior of electric vehicles, classify electric vehicles into different types according to their different travel patterns, including private cars and ride-hailing vehicles, and construct private car travel behavior models and ride-hailing vehicle travel behavior models respectively. S40: Based on the private car travel behavior model and the ride-hailing travel behavior model, and taking into account travel time, charging price and energy consumption, construct a quantitative indicator of user charging satisfaction. S50: Based on the aforementioned quantitative indicators of user charging satisfaction and the queuing system of charging stations, a charging selection model for different types of electric vehicles is proposed. S60: Based on the charging selection model and the queuing system of the charging station, predict the charging load of the charging station in each time period, and implement a dynamic pricing strategy for the charging station with the goal of minimizing the load fluctuation of each charging station.

2. The method for guiding fast charging demand for electric vehicles according to claim 1, characterized in that, In step S20, the road traffic impedance model includes: ； In the formula, Rl represents the total travel time for road segment l; Tl represents the total travel time for road segment l. 0, l The travel time when road segment l is unobstructed; For road segment l, traffic flow is provided. L represents the actual traffic capacity of road segment l; l N is the length of road segment l; l Let τ be the number of roadside vehicles on road segment l; τ is the influence coefficient of roadside vehicles on the traffic flow of the road segment.

3. The method for guiding fast charging demand for electric vehicles according to claim 1, characterized in that, In step S20, the electric vehicle power consumption model includes: ； In the formula, E lose ,l V represents the electricity consumption of an electric vehicle on road segment l. l L represents the average speed of an electric vehicle traveling on road segment l. Different road grades and road conditions correspond to different speeds. l Let l be the length of road segment l; a, b, and c are power consumption coefficients.

4. The method for guiding fast charging demand for electric vehicles according to claim 1, characterized in that, In step S30, based on the different travel patterns of electric vehicles, electric vehicle types are classified, including private cars and ride-hailing vehicles. Private car travel behavior models and ride-hailing vehicle travel behavior models are then constructed, including: S31: Determine the travel behavior of private cars, including using travel chains with residential areas as the starting and ending points to describe the travel behavior of private cars, and the first trip time and stay time of each type of travel chain follow a normal distribution; S32: Determine the travel behavior of ride-hailing vehicles, including describing the travel behavior of ride-hailing vehicles using a travel state transition matrix. The first travel time and number of trips of ride-hailing vehicles follow a normal distribution. S33: Based on the travel behavior of the private car and the ride-hailing vehicle, plan the routes for the private car and the ride-hailing vehicle respectively, including: Private cars plan routes with the goal of finding the shortest travel time during their journeys; When a ride-hailing service is carrying passengers, it plans routes with the goal of minimizing the distance traveled by electric vehicles. When a ride-hailing service is empty, it plans routes with the goal of minimizing the energy consumption of electric vehicles or the travel time on roads. S34: Based on the route planning for private cars and ride-hailing vehicles, calculate the arrival time and remaining battery power of electric vehicles.

5. The method for guiding fast charging demand for electric vehicles according to claim 4, characterized in that, In step S34, the arrival time and remaining battery power of the electric vehicle are calculated, and the model includes: ； ； In the formula, The time when the h-th electric vehicle arrives at the activity location p; The time when the h-th electric vehicle leaves the activity location p-1; Ω represents the travel time of the segment from node i to node j; p -1, p This is the set of road segments along the path from activity location p-1 to activity location p. The remaining battery power of the h-th electric vehicle upon arrival at location p; The remaining battery power of the h-th electric vehicle when it leaves the activity location p-1; This represents the power consumption of the road segment from node i to node j.

6. The method for guiding fast charging demand for electric vehicles according to claim 1, characterized in that, In step S40, taking into account travel time, charging price, and energy consumption, a quantitative indicator of user charging satisfaction is constructed, including: ； In the formula, f CSR ,k Overall charging satisfaction for electric vehicles at charging station k; f1 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; f2 ,k Satisfaction with charging travel time for electric vehicles arriving at charging station k; f3 ,k Satisfaction with the charging price of electric vehicles reaching charging station k; α, γ and γ are the weighting coefficients of the user charging satisfaction index, and their sum is 1.

7. The method for guiding fast charging demand for electric vehicles according to claim 1, characterized in that, In step S50, based on the user charging satisfaction quantification index and the charging station queuing system, a charging selection model for different types of electric vehicles is proposed, including: S51: Determining the charging needs of private cars, including whether, before each trip, if the remaining battery power of an electric vehicle is insufficient to support reaching the next destination, the electric vehicle user will choose to detour to a charging station to charge; if fast charging is required during the trip between two stops, the private car will detour to a charging station to charge. S52: Determining the charging needs of ride-hailing vehicles, including when a ride-hailing vehicle is in a state of no load and its battery charge is below a certain level, it will go to a charging station to charge before picking up passengers. S53: Based on the judgment of the charging demand of the private car and the judgment of the charging demand of the ride-hailing vehicle, select the most suitable charging station based on the quantitative index of user charging satisfaction, and calculate the charging time and load demand based on the initial power and charging station conditions. S54: Based on the charging time and load demand, the queuing system of the charging station determines the queuing and charging order of electric vehicles according to the first-come, first-served principle.

8. The method for guiding fast charging demand for electric vehicles according to claim 1, characterized in that, In step S60, based on the charging selection model and the queuing system of the charging station, the charging load of the charging station is predicted for each time period, and a dynamic pricing strategy for the charging station with the goal of minimizing load fluctuations at each charging station is implemented, including: S61: Construct a charging station load prediction model to obtain the predicted charging load of the charging station; S62: Based on the maximum charging load capacity that different charging stations can accommodate, the predicted load of each charging station is reduced to the maximum capacity, and the average predicted load of the charging station is calculated. S63: When the difference between the predicted charging load of each charging station and the average predicted load is less than or greater than the adjustment threshold, the electricity price of the charging station shall be adjusted. S64: Adjust the charging station electricity price as described above, and optimize the charging electricity price adjustment step size based on the particle swarm optimization algorithm with compression factor.

9. The method for guiding fast charging demand for electric vehicles according to claim 8, characterized in that, In step S62, the average predicted load of the charging station is calculated, and the model includes: ； ； In the formula, Let t be the average forecasted load demand for the time period t; σ represents the predicted load demand of charging station k during time period t; k Let σ be the reduction factor for charging station k. When the charging load capacity of charging station k is equal to the maximum capacity among all charging stations, then σ... k =1; K is the total number of charging stations; q k Let k be the number of charging piles in charging station k.

10. The method for guiding fast charging demand for electric vehicles according to claim 8, characterized in that, In step S63, when the difference between the predicted charging load demand of each charging station and the average predicted load is less than or greater than the adjustment threshold, the electricity price of the charging station is adjusted. The model includes: ； In the formula, C k , t Let Δc be the charging electricity price at charging station k during time period t; k The step size for adjusting the charging electricity price; ε is the dead zone coefficient; Let t be the average forecasted load demand for the time period t; σ represents the predicted load demand of charging station k during time period t; k Let σ be the reduction factor for charging station k. When the charging load capacity of charging station k is equal to the maximum capacity among all charging stations, then σ... k =1.

11. A fast-charging demand guidance device for electric vehicles, characterized in that, Using the method as described in any one of claims 1 to 10, comprising: The dynamic transportation network establishment unit is used to acquire road, traffic and charging station information to establish a dynamic transportation network that is updated in real time. The impedance and power consumption model building unit is used to build a road traffic impedance model and an electric vehicle power consumption model based on the dynamic traffic network, considering the road travel time and road speed of electric vehicles under different traffic conditions. The travel behavior model construction unit is used to simulate the travel behavior of electric vehicles based on the road traffic impedance model and the electric vehicle power consumption model. According to the different travel patterns of electric vehicles, electric vehicle types are divided, including private cars and ride-hailing vehicles, and travel behavior models for private cars and ride-hailing vehicles are constructed respectively. The user satisfaction construction unit is used to construct a quantitative indicator of user charging satisfaction based on the private car travel behavior model and the ride-hailing travel behavior model, taking into account travel time, charging price and energy consumption. The charging selection model construction unit is used to propose charging selection models for different types of electric vehicles based on the quantitative indicators of user charging satisfaction and the queuing system of charging stations. The dynamic pricing strategy unit is used to predict the charging load of charging stations in each time period based on the charging selection model and the queuing system of the charging station, and to implement a dynamic pricing strategy for charging stations with the goal of minimizing the load fluctuation of each charging station.

12. A computer 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 method as described in any one of claims 1-10.

13. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-10.

Images