Electric vehicle ordered charging power prediction method and related device

Abstract

The invention belongs to the technical field of electric vehicle charging regulation and control, and discloses an electric vehicle ordered charging power prediction method and a related device. The electric vehicle ordered charging power prediction method comprises the following steps: based on a selected to-be-predicted area, obtaining position information and type information of each hub point, path information between hub points, historical load data of the hub points, total number information of vehicles, types of each vehicle and endurance mileage information; based on the acquired data information, acquiring a charging power prediction value of each vehicle at each hub point; and then, for each hub point, summing each vehicle charging power prediction value to obtain a charging power prediction result of each hub point in the to-be-predicted area. According to the technical scheme disclosed by the invention, a prediction result with relatively high reliability can be obtained, and the technical problem that an existing single prediction evaluation method is relatively low in accuracy and reliability is solved.

Description

Technical Field

[0001] This invention belongs to the field of electric vehicle charging regulation technology, and specifically relates to a method and related device for predicting the orderly charging power of electric vehicles. Background Technology

[0002] Electric vehicles are among the most promising clean transportation tools, and the proposed "dual carbon" target is of great significance to the development of the electric vehicle industry, as this initiative will change the energy structure. However, the uncertainty of electric vehicle charging and discharging presents challenges such as grid connection economics, the rationality of charging station layout, and the reliability of electricity pricing.

[0003] The number of electric vehicles is growing rapidly, and the impact of electric vehicle charging behavior on power grid operation is gradually increasing. Among these factors, the randomness of electric vehicle owners' charging behavior, the diversity of electric vehicle charging stations, and the complexity of electric vehicle travel behavior all greatly increase the difficulty of predicting the orderly charging and discharging power of electric vehicles.

[0004] Currently, existing electric vehicle charging prediction methods mainly focus on the spatial distribution of electric vehicle charging stations or make predictions based on statistical data of electric vehicle charging and discharging at different time periods. However, both of these existing methods only consider some of the conditions affecting electric vehicle charging and discharging, without taking into account the impact of charging and discharging probabilities of different types of electric vehicles. This results in poor reliability of the prediction results and cannot adequately support the formulation of charging control strategies. Summary of the Invention

[0005] The purpose of this invention is to provide a method and related apparatus for predicting the orderly charging power of electric vehicles, in order to solve one or more of the aforementioned technical problems. Specifically, the technical solution disclosed in this invention is an orderly charging power prediction scheme that considers the fine classification and driving trajectory of electric vehicles. This scheme can obtain highly reliable prediction results and provides a better reference for solving problems related to grid connection economy, rational layout of charging stations, and reliability of electricity pricing faced by electric vehicles during charging and discharging. It overcomes the technical problems of low accuracy and reliability inherent in existing single prediction and evaluation methods.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for predicting the orderly charging power of electric vehicles, comprising the following steps: Based on the selected area to be predicted, obtain the location and type information of each hub point, the path information between hub points, the historical load data of hub points, as well as the total number of electric vehicles, the vehicle type and driving range information. Based on the acquired data, the predicted charging power of each vehicle at each hub point is obtained; then, for each hub point, the predicted charging power of each vehicle is accumulated and summed to obtain the predicted charging power of each hub point in the area to be predicted. The specific steps for obtaining the predicted charging power of each vehicle at each hub point include: selecting vehicles one by one and obtaining the predicted charging power of the selected vehicles at each hub point until all vehicles are selected; the process of obtaining the predicted charging power of the selected vehicles at each hub point involves calculating the travel probability of each driving path based on the historical load data of the hub point where the selected vehicle is located, combined with the path information between hub points, and calculating the probability of each other hub point in the area to be predicted as the destination based on the travel probability of each driving path; for each hub point with a certain probability of being the destination, the shortest path from the vehicle to the destination is obtained by using a path search algorithm based on the vehicle type of the selected vehicle; based on the shortest path and the range information of the selected vehicle, the charging probability and charging time of the selected vehicle are calculated, and the predicted charging power of the selected vehicle at the destination hub point is obtained based on the charging probability and charging time.

[0007] A further improvement of the technical solution of the present invention is that the type information of each hub point is a residential area, a commercial area or an office area; and the type information of each vehicle is a private car, a taxi or a bus.

[0008] A further improvement to the technical solution of this invention lies in the step of calculating the travel probability of each driving path based on the historical load data of the hub point where the selected vehicle is located, combined with the path information between hub points, and calculating the probability of each other hub point in the area to be predicted as the destination based on the travel probability of each driving path. Among the remaining hub points within the area to be predicted, when the hub point's type information is residential area or office area, the expression for the probability of it being a destination is: ; In the formula, z des Indicates the destination. P { z des = i} represents the pivot point i The probability of it being a destination; P load,i hub point i The average daily load; N wp The total number of hub points. R This is a set of hub points of type residential area. W A set of hub points of type office area; Among the remaining hub points within the area to be predicted, when the hub point's type information is a commercial area, the expression for the probability of it being a destination is: ; ; ; In the formula, a i Indicates the first i vehicle; L pre Indicates destination; Cp i Indicates the first i The area where the vehicle is located; v ( π i )express π ( a i | L pre The probability of ). d ( L pre |Cp i ) indicates from L pre To Cp i The shortest distance; d (Cp i | L pre ) indicates from Cp i arrive L next The shortest distance; σ 1. σ 2 represents the uniformity coefficient; P t (Cp i ) represents Cp i exist t Active power at any given moment; π t ( a i | L pre () indicates time t At that time L pre implement a i ; n Indicates the number of commercial areas.

[0009] A further improvement to the technical solution of this invention lies in the step of obtaining the shortest path from the selected vehicle to the destination using a path search algorithm for each hub point that has a certain probability of being the destination. Based on the travel chain of the selected vehicle, the distance calculation matrix of adjacent hub points is obtained, and then the path search algorithm is used to obtain the shortest path; When the selected vehicle is a private car, its travel route is: residential area - commercial area - office area - residential area; when the selected vehicle is a taxi, its travel route is: residential area - office area - residential area; when the selected vehicle is a bus, its travel route is: residential area - office area - commercial area - residential area. The distance calculation matrix for adjacent pivot points uses a Euclidean matrix. D ij express: ; In the formula, D ij This represents the distance matrix between adjacent pivot points. d ij Indicates from the hub point i To the hub j The distance between them; If two hub points are not adjacent and can only be reached through an intermediate hub point, then the hub point... i and hub points j The distance between them can be expressed as: ; In the formula, d ij Indicates from the hub point i To the hub j The distance between them x i and y i Representing hub points i The horizontal and vertical coordinates on the map.

[0010] A further improvement to the technical solution of the present invention lies in the step of calculating the charging probability and charging time of the selected vehicle based on the shortest path and the selected vehicle's range information, and obtaining the predicted charging power value of the selected vehicle at the destination hub based on the charging probability and charging time. Assuming the initial charge of an electric vehicle is random, its probability density function is: ; In the formula, f ( SOC st ) represents the probability density function of the initial charge of the electric vehicle; SOC st This indicates the initial charge level of the electric vehicle; SOC st,max This indicates the initial maximum charge level of the electric vehicle; SOCst,min This indicates the initial minimum charge level of the electric vehicle; The electric vehicle's remaining charge after reaching its destination will be: ; In the formula, SOC ar This indicates the battery level of the electric vehicle after it reaches its destination. D E Indicates the distance traveled by the electric vehicle. E km This indicates the electricity consumption per kilometer an electric vehicle travels. B c Indicates the volatility coefficient; If the probability of an electric vehicle leaving a certain location follows a normal distribution, then the probability density of its departure time is: ; In the formula, f ( t le () represents the probability density function at the departure time. t le Indicates the time of departure. μ le This represents the average value at departure times. σ le The standard deviation represents the departure time; like q k This represents the probability of switching from non-charging mode to charging mode. p k This represents the probability of switching from charging mode to non-charging mode. δ k This represents the probability of stopping. T 1. T 2 and T 3 represents the charging time, driving time, and parking time of an electric vehicle, respectively. Then: Discrete state space of electric vehicle charging S dis for: ; ; In the formula, S dis Represents the discrete state space of electric vehicle charging; c k and d k These represent the charging mode and non-charging mode of the electric vehicle, respectively; c k}and{ dk} represent the sets of electric vehicle charging modes and non-charging modes, respectively; k Indicates the percentage of battery charge in an electric vehicle; round Indicates rounding; SOC indicates the current battery level of the electric vehicle; Therefore, the probabilities of an electric vehicle being in charging mode and not charging mode are respectively: ; ; In the formula, P s () represents the probability of being in a certain state; p k-1 This indicates that the electric vehicle transitioned from a charging state to a non-charging state at the previous moment. c k-1 This indicates that the electric vehicle was in a charging state at the previous moment; d k This indicates that the electric vehicle is currently not charging. N bat This indicates the maximum percentage of battery charge in an electric vehicle. δ k Indicates the amount of electricity. k Stop at the designated time; subscript N This indicates that the electric vehicle's battery level is... N ; p 0=0, q 0=1, p 100 =1, q 100 =0; By combining the probabilities of the electric vehicle being in charging mode and not charging mode, we can obtain the probability of the electric vehicle being in not charging mode without including variables for the next time step: ; therefore, c k From this moment on, the battery capacity of electric vehicles will increase. k The probability of 1 is expressed as: ; In the formula, P s ( c k,k1 This indicates an increase in the electric vehicle's battery level. k The probability of 1; p k+k1 express k + k The probability that an electric vehicle will switch from charging to non-charging state at time 1. The charging time, driving time, and parking time of an electric vehicle are expressed as follows: ; ; ; In the formula, η c Indicates the power transmission efficiency of the charging pile; P c Indicates the rated charging power of electric vehicles; t le Indicates the departure time; t ar Indicates the time of arrival; k 2 indicates from d k The amount of electricity consumed by the electric vehicle from that moment on; E km This indicates the amount of electricity consumed by an electric vehicle per unit distance. v Indicates average speed; Therefore, the charging power of electric vehicles P cha exist t ar and t le Between P c The remaining time values ​​are 0; predicted charging power for electric vehicles. P cha.e Electric vehicle charging power P cha Electric vehicle charging probability P s ( c k ) of accumulation.

[0011] A further improvement to the technical solution of the present invention lies in the step of calculating the probability function of the total charging power of all electric vehicles in the selected area based on the predicted charging power of each electric vehicle. The probability function for the total charging power of all electric vehicles is: ; In the formula, P cha.sum This represents the total charging power of all electric vehicles; P cha.e Indicates the first e The charging power of an electric vehicle; N ev This represents the total number of electric vehicles at that moment.

[0012] A second aspect of the present invention provides an orderly charging power prediction system for electric vehicles, comprising: The data acquisition module is used to acquire location and type information of each hub point, path information between hub points, historical load data of hub points, and information on the total number of electric vehicles, vehicle types, and driving range based on the selected area to be predicted. The prediction module is used to obtain the predicted charging power of each vehicle at each hub point based on the acquired data information; then, for each hub point, the predicted charging power of each vehicle is accumulated and summed to obtain the predicted charging power of each hub point in the area to be predicted. The specific steps for obtaining the predicted charging power of each vehicle at each hub point include: selecting vehicles one by one and obtaining the predicted charging power of the selected vehicles at each hub point until all vehicles are selected; the process of obtaining the predicted charging power of the selected vehicles at each hub point involves calculating the travel probability of each driving path based on the historical load data of the hub point where the selected vehicle is located, combined with the path information between hub points, and calculating the probability of each other hub point in the area to be predicted as the destination based on the travel probability of each driving path; for each hub point with a certain probability of being the destination, the shortest path from the vehicle to the destination is obtained by using a path search algorithm based on the vehicle type of the selected vehicle; based on the shortest path and the range information of the selected vehicle, the charging probability and charging time of the selected vehicle are calculated, and the predicted charging power of the selected vehicle at the destination hub point is obtained based on the charging probability and charging time.

[0013] In a third aspect, the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the electric vehicle orderly charging power prediction method as described in any one of the first aspects of the present invention.

[0014] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the electric vehicle orderly charging power prediction method as described in any one of the first aspects of the present invention.

[0015] In a fifth aspect, the present invention provides a computer program product comprising a computer program or instructions which, when executed by a communication device, cause the electric vehicle orderly charging power prediction method described in any one of the first aspects of the present invention to be executed.

[0016] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a method for predicting the orderly charging power of electric vehicles, specifically a method that considers the fine classification and driving trajectory of electric vehicles. It analyzes the impact of different types of electric vehicles' possible travel paths on their charging behavior, and incorporates factors such as the complexity of user travel habits, the randomness of electric vehicle battery levels, the ambiguity of charging duration, and the diversity of charging station locations to predict electric vehicle charging and discharging. This method can improve the grid connection economy of charging stations (i.e., the rationality of charging station layout) by modifying charging station site selection before construction, and provides a reference for setting regional electricity prices based on charging station utilization rates to improve the utilization rate of charging stations in different regions. This overcomes the problem of low accuracy in traditional single-prediction and evaluation methods. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this 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 some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating an ordered charging power prediction method that considers the fine classification and driving trajectory of electric vehicles in an embodiment of the present invention. Figure 2 This is a schematic diagram of regional traffic and power transmission in an embodiment of the present invention; Figure 3 This is a schematic block diagram of the total power demand prediction process for electric vehicle charging in an embodiment of the present invention. Figure 4 This is a flowchart illustrating the path search algorithm in an embodiment of the present invention; Figure 5 This is a schematic diagram of the electric vehicle charging power prediction result of method D1 in an embodiment of the present invention; Figure 6 This is a schematic diagram of the electric vehicle charging power prediction result of method D2 in an embodiment of the present invention; Figure 7 This is a schematic diagram illustrating the prediction results of the daily total charging power at different time points using different prediction methods in an embodiment of the present invention. Figure 8 This is a schematic diagram of the predicted daily total charging power of hub points using different prediction methods in an embodiment of the present invention. Figure 9 This is a schematic diagram of an ordered charging power prediction system that considers the fine classification and driving trajectory of electric vehicles in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, 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.

[0020] Based on the technical solutions disclosed in the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0021] Please see Figure 1 This invention provides a method for predicting the ordered charging power of electric vehicles, specifically a method that considers the fine classification and driving trajectory of electric vehicles, including the following steps: Step 1: Based on the selected area to be predicted, obtain the location and type information of hub points, the route information between hub points, the historical load data of hub points, as well as the total number of vehicles, vehicle type and driving range information. Step 2: Based on the data obtained in Step 1, obtain the predicted charging power of each vehicle at each hub point; for each hub point, sum the predicted charging power of each vehicle to obtain the predicted charging power of each hub point in the area to be predicted. The step of obtaining the predicted charging power of each vehicle at each hub point based on the data information obtained in step 1 specifically includes: The process involves selecting vehicles one by one and obtaining the predicted charging power of each selected vehicle at each hub point until all vehicles are selected. The steps for obtaining the predicted charging power of each selected vehicle at each hub point include: calculating the probability of each travel path based on the vehicle type of the selected vehicle and the historical load data of the hub point, combined with the path information between hub points; calculating the probability of each other hub point within the prediction area being the destination based on the travel probability of each travel path; for each hub point with a certain probability of being reached, using a path search algorithm to obtain the shortest path from the vehicle to the destination; and calculating the charging probability and charging time of the selected vehicle based on the shortest path and the range information of the selected vehicle, and obtaining the predicted charging power based on the charging probability and charging time.

[0022] Please see Figures 2 to 4, An orderly charging power prediction method considering the fine classification and driving trajectory of electric vehicles provided by an embodiment of the present invention specifically includes the following steps: Step S1, define the process variable a = 0, and extract the total number of vehicles A to be analyzed based on the selected area to be predicted; calculate the probability of the hub point i as the destination according to the travel probability of each driving path; obtain the distance calculation matrix between adjacent hub points according to the travel chains of different electric vehicle types, and use the path search algorithm to obtain the shortest path, that is, the commuting distance; randomly extract the electric vehicle type, and thereby determine the number of paths N in its travel chain, and define the process variable n = 0; judge whether the destination is a commercial area. If so, calculate the probability of selecting each commercial area; otherwise, use the path search algorithm to obtain the shortest path, and calculate the time and power to reach the destination; calculate the charging probability and charging duration of the electric vehicle, and let n = n + 1; Step S2: Make a logical judgment on the numerical relationship between n and N; if n < N, return to execute the judgment in step S1 whether the destination is a commercial area; otherwise, execute the next step; calculate the charging demand of the electric vehicle, and sum up the charging demands of all electric vehicles in the previous steps, and let a = a + 1; make a logical judgment on the numerical relationship between a and A. If a < A, end; otherwise, return to execute the probability of the hub point i as the destination in S1.

[0023] Figure 2 The regional traffic and power transmission diagram of the orderly charging power prediction method considering the fine classification and driving trajectory of electric vehicles is shown.

[0024] In the exemplary technical solution of the embodiment of the present invention, calculating the probability of the hub point i as the destination according to the travel probability of each driving path includes: The charging load of electric vehicles in living areas is generally closely related to the number of permanent residents and the electric vehicle ownership rate. The charging load of electric vehicles in commercial areas is generally positively correlated with the pedestrian flow. Therefore, it can be known that the charging load of electric vehicles at the hub point is related to the number distribution of electric vehicles. Express this relationship in a mathematical relationship as: (1) In the formula, i represents that the destination sequence number is the i th; z des represents the destination; P { z des = i} represents the probability that the hub point i is the destination; P load,ihub point i The average daily load; N wp For the number of hub points, R As a hub for residents, W It serves as a hub for the office area.

[0025] For an electric vehicle owner, their living and working areas are generally fixed, but their business areas are uncertain. The probability of choosing each business area varies depending on factors such as distance and size. The remaining battery power of the electric vehicle after arriving at each business area also affects the probability of charging. Therefore, determining the destination is one of the keys to clarifying the charging needs of an electric vehicle.

[0026] The value of the next trip can be expressed as: (2) (3) In the formula, a Indicates the first a Measuring the vehicle; L pre Indicates destination; Cp i Indicates the area where the vehicle is located; v ( π i )express π ( a i | L pre The probability of ). d ( L pre |Cp i ) indicates from L pre To Cp i The shortest distance; d (Cp i | L pre ) indicates from Cp i arrive L next The shortest distance; σ 1. σ 2 represents the uniformity coefficient; P t (Cp i ) represents Cp i exist t Active power at any given moment; π t ( a i | L pre () indicates timet At that time L pre implement a i ; n Indicates the number of commercial areas.

[0027] travel π t ( a i | L pre The probability of () can be expressed as: (4) In this embodiment of the invention, step S1, which involves obtaining a distance calculation matrix for adjacent hub points based on travel chains of different electric vehicle types and then using a path search algorithm to obtain the shortest path, includes: Record the hub of the travel route as v i Adjacent hub points i and j The Euclidean distance can be expressed using a Euclidean matrix. D ij express: (5) If two hub points are not adjacent and can only be reached through an intermediate hub point, then the hub point... i and hub points j The distance between them can be expressed as: (6) In the formula, d ij Indicates the hub point i and j The distance between, x n and y n Indicates the hub point n The coordinates.

[0028] Based on the above, the pivot point is obtained using a path search algorithm. i and j The shortest distance between them, a specific example algorithm flowchart is as follows: Figure 4 As shown.

[0029] In a specific exemplary technical solution of the present invention, step S1 involves randomly selecting electric vehicle types to determine the number of paths N in their travel chain. Electric vehicle types are divided into three categories: private cars, taxis, and buses. The travel chain is a travel behavior carried out according to a time sequence, which can clearly represent the daily travel hub points of users using electric vehicles. The travel chains of different vehicle types have obvious differences. The travel path of private cars is: residential area - commercial area - office area - residential area; the travel path of taxis is: residential area - office area - residential area; and the travel path of buses is: residential area - office area - commercial area - residential area.

[0030] In a specific exemplary technical solution of the present invention, step S1 calculates the arrival time and battery power at the destination: Assuming the initial charge of an electric vehicle is random, its probability density function is: (7) In the formula, SOC st This indicates the initial charge level of the electric vehicle; SOC st,max This indicates the initial maximum charge level of the electric vehicle; SOC st,min This indicates the initial minimum charge level of the electric vehicle; like D E Let represent the distance traveled by the electric vehicle. Then, the battery level of the electric vehicle after reaching its destination is: (8) If the probability of an electric vehicle leaving a certain location follows a normal distribution, then the probability density of its departure time is: (9) In the formula, μ le express t le The average value, σ le express t le The standard deviation.

[0031] In step S1, the probability of the electric vehicle being charged and the charging time are calculated, and n = n + 1 is set: Electric vehicles are divided into two modes: charging and non-charging. When an electric vehicle is in charging mode... c k When the power grid outputs power to the electric vehicle, the electric vehicle's battery level increases; when the electric vehicle is in non-charging mode... d kWhen the electric vehicle is in motion, the power grid does not output power to it. If the electric vehicle is in motion, its power consumption decreases; otherwise, the power consumption remains unchanged.

[0032] like q k This represents the probability of switching from non-charging mode to charging mode. p k This represents the probability of switching from charging mode to non-charging mode. δ k This represents the probability of stopping. T 1. T 2 and T 3 represents the charging time, driving time, and parking time of an electric vehicle, respectively. Then, the discrete state space of electric vehicle charging... S dis for: (10) (11) In the formula, { c k}and{ d k} represent the sets of electric vehicle charging modes and non-charging modes, respectively; k Indicates the percentage of battery charge in an electric vehicle; round Indicates rounding; p 0=0, q 0=1, p 100 =1, q 100 =0.

[0033] Therefore, the probabilities of an electric vehicle being in charging mode and not charging mode are respectively: (12) (13) In the formula, P s This indicates the probability of being in that mode.

[0034] Combining the above two equations, we can obtain the probability that the electric vehicle is in non-charging mode without including variables for the next time step: (14) therefore c k From this moment on, the battery capacity of electric vehicles will increase. k The probability of 1 can be expressed as: (15) The charging time, driving time, and parking time of an electric vehicle can be expressed as follows: (16) (17) (18) In the formula, η c Indicates the power transmission efficiency of the charging pile; P c Indicates the rated charging power of electric vehicles; t le Indicates the departure time; t ar Indicates the time of arrival; k 2 indicates from d k The amount of electricity consumed by the electric vehicle from that moment on; E km This indicates the amount of electricity consumed by an electric vehicle per unit distance. v This indicates the average speed per hour.

[0035] In a specific exemplary technical solution of the present invention, step S2 sums up all electric vehicle charging demands from the previous step, letting a = a + 1: Based on the established probabilistic model of charging demand for a single electric vehicle, the charging duration function and probability function for a single electric vehicle were obtained. Therefore, the probability function of the total charging power for all electric vehicles can be calculated: (19) In the formula, P cha.sum This represents the total charging power of all electric vehicles; P cha.ev Indicates the first e The charging power of an electric vehicle; N ev This represents the total number of electric vehicles at that moment.

[0036] The number of times an electric vehicle charges per day and the probability of each charge depend on factors such as its battery percentage, battery capacity, next trip distance, and power consumption per unit distance. Since an electric vehicle only has the possibility of charging after reaching its destination, the more hubs it passes through during its journey, the greater the likelihood of charging, and the more complex the probability model becomes. The probability model for the number of times an electric vehicle charges per day can be expressed as: (20) In the formula, f Indicates the number of times an electric vehicle is charged per day; k i This indicates whether the current battery level is greater than or equal to the battery level required for the next trip (if the current battery level is greater than or equal to the battery level required for the next trip, ...). kiIf the current battery level is 0, the probability of charging is 0. Conversely, if the current battery level is less than the battery level required for the next trip, then... ki (1) G Represents a set of travel hubs; p i Indicates at the hub point i The probability of charging.

[0037] In summary, the embodiments of the present invention provide an ordered charging power prediction method that considers the fine classification and driving trajectory of electric vehicles. The total power demand of electric vehicles at the hub point is obtained by multiplying and accumulating the hub point probability, the number of charging times, and the charging demand. It can also be used to adjust the output of charging piles or coordinate multiple charging stations. It can better provide a reference for solving problems such as grid connection economy, rational layout of charging stations, and reliability of electricity price setting faced by electric vehicle charging and discharging, and overcome the problem of low accuracy of traditional single prediction and evaluation methods.

[0038] Specifically, taking the 2024 BYD Yuan Plus as a reference model, the various parameters of the electric vehicle are shown in Table 1: Table 1 Electric Vehicle Parameters

[0039] Please see Figure 5 As shown, this is the electric vehicle charging power prediction result of method D1 (the charging probability and charging time of electric vehicles are both random models) of the "ordered charging power prediction method considering the fine classification and driving trajectory of electric vehicles" of the present invention.

[0040] Depend on Figure 5 It can be seen that, under the stochastic model of both the charging probability and charging duration of electric vehicles, the average charging power demand of electric vehicles in the residential area (hub points 1-11) is less than 100kW at the peak (0:00), and is basically zero at other times. The peak charging power demand in the office area (hub points 12-18) is approximately 970kW, occurring at hub point 16, with charging mainly occurring from 8:00 to 19:00, and basically zero at other times. The peak charging power demand in the commercial area (hub points 19-23) is approximately 880kW, occurring at hub point 19, with charging in the office area concentrated between 9:00 and 12:00 and between 19:00 and 21:00. Therefore, the office area has the highest electric vehicle charging power demand, followed by the commercial area, while the residential area hub points have the lowest demand. Charging in the office area is concentrated during daytime working hours, charging in the commercial area is concentrated at noon and in the evening, and charging in the residential area is concentrated at night.

[0041] Please see Figure 6The figure shown is the electric vehicle charging power prediction result of method D2 (the charging probability of electric vehicles is defined as a random model but the charging time is a fixed value) of the "ordered charging power prediction method considering the fine classification and driving trajectory of electric vehicles" of the present invention.

[0042] Depend on Figure 6 It can be seen that, under the condition that the charging probability of electric vehicles is defined as a random model but the charging time is a fixed value, the peak charging power demand of electric vehicles in the residential area (hub points 1~11) is about 130kW, which occurs around 18:00, and the average charging power demand is basically 0; the peak charging power demand in the office area (hub points 12~18) is about 980kW, which occurs at hub point 14, and charging mainly occurs from 8:00 to 18:00, with the rest of the time being basically 0; the peak charging power demand in the commercial area (hub points 19~23) is about 1.06MW, which occurs at hub point 19.

[0043] Please see Figure 7 As shown, this is a graph illustrating the daily total charging power prediction results at different time points using different prediction methods of the "orderly charging power prediction method considering the fine classification and driving trajectory of electric vehicles" of the present invention.

[0044] Depend on Figure 7 It can be seen that the peak time of the daily total charging power prediction curve for Method D1 occurs at 11:00, with a value of 8.15MW. The peak time for Method D2 also occurs at 11:00, with a value of 6.78MW, which is less than that of Method D1. The main reason why the peak daily charging power of Method D2 is lower than that of Method D1 is that the charging probability model of Method D2 calculates the charging probability of electric vehicles based on the decreasing battery level, while the charging probability of Method D1 decreases exponentially with the decreasing battery level. When the battery level is low, the charging probability of Method D2 is lower than that of Method D1. From 19:00 to 6:00 the next day, the average charging power demand of Method D2 is higher than that of Method D1 because the charging demand of Method M1 is higher from 7:00 to 18:00 due to the psychological factors of car owners, resulting in higher battery levels and lower charging probability for electric vehicles at night.

[0045] Please see Figure 8 As shown, this is a graph illustrating the predicted daily total charging power at hub points using different prediction methods of the "Ordered Charging Power Prediction Method Considering Fine Classification and Driving Trajectory of Electric Vehicles" of this invention.

[0046] Depend on Figure 8It can be seen that the peak daily charging power demand for both methods D1 and D2 occurs at hub point 18, with values ​​of 670 MW·h and 440 MW·h respectively. Electric vehicle charging for both methods primarily occurs in office areas (hub points 12-18). In residential areas (hub points 1-11), the daily charging power demand for method D2 is greater than that for method D1, with an average daily charging power of 43 MW·h for method D1 and 11 MW·h for method D2. In office areas (hub points 12-18), the daily charging power demand for method D2 is greater than that for method D1, with an average daily charging power of 386 MW·h for method D1 and 428 MW·h for method D2. In commercial areas (hub points 19-23), the total daily charging power demand for method D1 is greater than that for method D2, with an average daily charging power of 83 MW·h for method D1 and 1 MW·h for method D2.

[0047] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0048] Please see Figure 9 In this embodiment of the invention, an electric vehicle orderly charging power prediction system is provided, comprising: The data acquisition module is used to acquire location and type information of each hub point, path information between hub points, historical load data of hub points, total number of vehicles, vehicle type and driving range information based on the selected area to be predicted. The prediction module is used to obtain the predicted charging power of each vehicle at each hub point based on the acquired data information; then, for each hub point, the predicted charging power of each vehicle is summed to obtain the predicted charging power of each hub point in the area to be predicted. The specific steps for obtaining the predicted charging power of each vehicle at each hub point include: selecting vehicles one by one and obtaining the predicted charging power of the selected vehicles at each hub point until all vehicles are selected; the process of obtaining the predicted charging power of the selected vehicles at each hub point involves calculating the travel probability of each driving path based on the historical load data of the hub point where the selected vehicle is located, combined with the path information between hub points, and calculating the probability of each other hub point in the area to be predicted as the destination based on the travel probability of each driving path; for each hub point with a certain probability of being the destination, the shortest path from the vehicle to the destination is obtained by using a path search algorithm based on the vehicle type of the selected vehicle; based on the shortest path and the range information of the selected vehicle, the charging probability and charging time of the selected vehicle are calculated, and the predicted charging power of the selected vehicle at the destination hub point is obtained based on the charging probability and charging time.

[0049] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used to execute the operation of an electric vehicle ordered charging power prediction method.

[0050] In one embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the operating system of the terminal. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor, which can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the electric vehicle ordered charging power prediction method in the above embodiments.

[0051] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0052] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0053] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0054] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting the orderly charging power of electric vehicles, characterized in that, Includes the following steps: Based on the selected area to be predicted, obtain the location and type information of each hub point, the path information between hub points, the historical load data of hub points, as well as the total number of electric vehicles, the vehicle type and driving range information. Based on the acquired data, predict the charging power of each vehicle at each hub point. Then, for each hub point, the predicted charging power values ​​of each vehicle are summed to obtain the predicted charging power of each hub point in the area to be predicted. The specific steps for obtaining the predicted charging power of each vehicle at each hub point include: selecting vehicles one by one and obtaining the predicted charging power of the selected vehicles at each hub point until all vehicles are selected; the process of obtaining the predicted charging power of the selected vehicles at each hub point involves calculating the travel probability of each driving path based on the historical load data of the hub point where the selected vehicle is located, combined with the path information between hub points, and calculating the probability of each other hub point in the area to be predicted as the destination based on the travel probability of each driving path; for each hub point with a certain probability of being the destination, the shortest path from the vehicle to the destination is obtained by using a path search algorithm based on the vehicle type of the selected vehicle; based on the shortest path and the range information of the selected vehicle, the charging probability and charging time of the selected vehicle are calculated, and the predicted charging power of the selected vehicle at the destination hub point is obtained based on the charging probability and charging time.

2. The method for predicting the orderly charging power of an electric vehicle according to claim 1, characterized in that, The type information for each hub point is residential area, commercial area, or office area; the type information for each vehicle is private car, taxi, or bus.

3. The method for predicting the orderly charging power of an electric vehicle according to claim 2, characterized in that, In the steps of calculating the travel probability of each driving route based on the historical load data of the hub where the selected vehicle is located, combined with the route information between hubs, and calculating the probability of each other hub in the area to be predicted as the destination based on the travel probability of each driving route, Among the remaining hub points within the area to be predicted, when the hub point's type information is residential area or office area, the expression for the probability of it being a destination is: ； In the formula, z des Indicates the destination. P { z des = i } represents the pivot point i The probability of it being a destination; P load,i hub point i The average daily load; N wp The total number of hub points. R This is a set of hub points of type residential area. W A set of hub points of type office area; Among the remaining hub points within the area to be predicted, when the hub point's type information is a commercial area, the expression for the probability of it being a destination is: ； ； ； In the formula, a i Indicates the first i vehicle; L pre Indicates the destination; Cp i Indicates the first i The area where the vehicle is located; v ( π i )express π ( a i | L pre The probability of ). d ( L pre |Cp i ) indicates from L pre To Cp i The shortest distance; d (Cp i | L pre ) indicates from Cp i arrive L next The shortest distance; σ 1. σ 2 represents the uniformity coefficient; P t (Cp i ) represents Cp i exist t Active power at any given moment; π t ( a i | L pre () indicates time t At that time L pre implement a i ; n Indicates the number of commercial areas.

4. The method for predicting the orderly charging power of an electric vehicle according to claim 3, characterized in that, In the step of finding the shortest path from each hub point that has a certain probability of being the destination, based on the vehicle type of the selected vehicle, using a path search algorithm, Based on the travel chain of the selected vehicle, the distance calculation matrix of adjacent hub points is obtained, and then the path search algorithm is used to obtain the shortest path; When the selected vehicle is a private car, its travel route is: residential area - commercial area - office area - residential area; when the selected vehicle is a taxi, its travel route is: residential area - office area - residential area; when the selected vehicle is a bus, its travel route is: residential area - office area - commercial area - residential area. The distance calculation matrix for adjacent pivot points uses a Euclidean matrix. D ij express: ； In the formula, D ij This represents the distance matrix between adjacent pivot points. d ij Indicates from the hub point i To the hub j The distance between them; If two hub points are not adjacent and can only be reached through an intermediate hub point, then the hub point... i and hub points j The distance between them can be expressed as: ； In the formula, d ij Indicates from the hub point i To the hub j The distance between them x i and y i Representing hub points i The horizontal and vertical coordinates on the map.

5. The method for predicting the orderly charging power of an electric vehicle according to claim 4, characterized in that, In the step of calculating the charging probability and charging time of the selected vehicle based on the shortest path and the selected vehicle's range information, and obtaining the predicted charging power value of the selected vehicle at the destination hub based on the charging probability and charging time, Assuming the initial charge of an electric vehicle is random, its probability density function is: ； In the formula, f ( SOC st ) represents the probability density function of the initial charge of an electric vehicle; SOC st This indicates the initial charge level of the electric vehicle; SOC st,max This indicates the initial maximum charge level of the electric vehicle; SOC st,min This indicates the initial minimum charge level of the electric vehicle; The electric vehicle's remaining charge after reaching its destination will be: ； In the formula, SOC ar This indicates the battery level of the electric vehicle after it reaches its destination. D E Indicates the distance traveled by the electric vehicle. E km This indicates the electricity consumption per kilometer an electric vehicle travels. B c Indicates the volatility coefficient; If the probability of an electric vehicle leaving a certain location follows a normal distribution, then the probability density of its departure time is: ； In the formula, f ( t le () represents the probability density function at the departure time. t le Indicates the time of departure. μ le This represents the average value at departure time. σ le The standard deviation represents the departure time; like q k This represents the probability of switching from non-charging mode to charging mode. p k This represents the probability of switching from charging mode to non-charging mode. δ k This represents the probability of stopping. T 1. T 2 and T 3 represents the charging time, driving time, and parking time of an electric vehicle, respectively. Then: Discrete state space of electric vehicle charging S dis for: ； ； In the formula, S dis Represents the discrete state space of electric vehicle charging; c k and d k These represent the charging mode and non-charging mode of the electric vehicle, respectively; c k }and{ d k } represent the sets of electric vehicle charging modes and non-charging modes, respectively; k Indicates the percentage of battery charge in an electric vehicle; round Indicates rounding; SOC indicates the current battery level of the electric vehicle; Therefore, the probabilities of an electric vehicle being in charging mode and not charging mode are respectively: ； ； In the formula, P s () represents the probability of being in a certain state; p k-1 This indicates that the electric vehicle transitioned from a charging state to a non-charging state at the previous moment. c k-1 This indicates that the electric vehicle was in a charging state at the previous moment; d k This indicates that the electric vehicle is currently not charging. N bat This indicates the maximum percentage of battery charge in an electric vehicle. δ k Indicates the amount of electricity. k Stop at the designated time; subscript N This indicates that the electric vehicle's battery level is... N ; p 0=0, q 0=1, p 100 =1, q 100 =0; By combining the probabilities of the electric vehicle being in charging mode and not charging mode, we can obtain the probability of the electric vehicle being in not charging mode without including variables for the next time step: ； therefore, c k From this moment on, the battery capacity of electric vehicles will increase. k The probability of 1 is expressed as: ； In the formula, P s ( c k,k1 This indicates an increase in the electric vehicle's battery level. k The probability of 1; p k+k1 express k + k The probability that an electric vehicle will switch from charging to non-charging state at time 1. The charging time, driving time, and parking time of an electric vehicle are expressed as follows: ； ； ； In the formula, η c Indicates the power transmission efficiency of the charging pile; P c Indicates the rated charging power of electric vehicles; t le Indicates the departure time; t ar Indicates the time of arrival; k 2 indicates from d k The amount of electricity consumed by the electric vehicle from that moment on; E km This indicates the amount of electricity consumed by an electric vehicle per unit distance. v Indicates average speed; Therefore, the charging power of electric vehicles P cha exist t ar and t le Between P c The remaining time values ​​are 0; predicted charging power for electric vehicles. P cha.e Electric vehicle charging power P cha Electric vehicle charging probability P s ( c k ) of accumulation.

6. The method for predicting the orderly charging power of an electric vehicle according to claim 5, characterized in that, In the step of calculating the probability function of the total charging power of all electric vehicles in the selected area based on the predicted charging power of each electric vehicle, The probability function for the total charging power of all electric vehicles is: ； In the formula, P cha.sum This represents the total charging power of all electric vehicles; P cha.e Indicates the first e The charging power of an electric vehicle; N ev This represents the total number of electric vehicles at that moment.

7. A power prediction system for orderly charging of electric vehicles, characterized in that, include: The data acquisition module is used to acquire location and type information of each hub point, path information between hub points, historical load data of hub points, and information on the total number of electric vehicles, vehicle types, and driving range based on the selected area to be predicted. The prediction module is used to obtain the predicted charging power of each vehicle at each hub point based on the acquired data information. Then, for each hub point, the predicted charging power values ​​of each vehicle are summed to obtain the predicted charging power of each hub point in the area to be predicted. The specific steps for obtaining the predicted charging power of each vehicle at each hub point include: selecting vehicles one by one and obtaining the predicted charging power of the selected vehicles at each hub point until all vehicles are selected; the process of obtaining the predicted charging power of the selected vehicles at each hub point involves calculating the travel probability of each driving path based on the historical load data of the hub point where the selected vehicle is located, combined with the path information between hub points, and calculating the probability of each other hub point in the area to be predicted as the destination based on the travel probability of each driving path; for each hub point with a certain probability of being the destination, the shortest path from the vehicle to the destination is obtained by using a path search algorithm based on the vehicle type of the selected vehicle; based on the shortest path and the range information of the selected vehicle, the charging probability and charging time of the selected vehicle are calculated, and the predicted charging power of the selected vehicle at the destination hub point is obtained based on the charging probability and charging time.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the electric vehicle orderly charging power prediction method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the electric vehicle orderly charging power prediction method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program or instructions that, when executed by a communication device, cause the electric vehicle orderly charging power prediction method of any one of claims 1 to 6 to be performed.

Images