Search

CN-121998056-A - Charging and discharging resource prediction method, device and equipment based on user travel characteristics

CN121998056ACN 121998056 ACN121998056 ACN 121998056ACN-121998056-A

Abstract

The application discloses a charge and discharge resource prediction method, a device and equipment based on user travel characteristics, and relates to the technical field of power resource scheduling. The method comprises the steps of obtaining driving behaviors of a user in a prediction scene based on a preset electric automobile travel model and a dynamic map, predicting charge and discharge power boundaries in different time periods based on the driving behaviors and battery characteristic parameters of the user driving the automobile, and aggregating the charge and discharge power boundaries of all the automobile in the same time period and a functional area to obtain space-time distribution of charge and discharge resources in the prediction scene. Therefore, more reliable and more refined data support is provided for load regulation and control at the power grid side, charging facility planning and vehicle network interaction strategy formulation, prediction deviation of charging and discharging resources of the electric vehicle is reduced, and accuracy of time-space distribution testing of the charging and discharging resources of the electric vehicle is improved.

Inventors

  • Wen Yixun

Assignees

  • 温亦浔

Dates

Publication Date
20260508
Application Date
20260115

Claims (10)

  1. 1. A charge and discharge resource prediction method based on user travel characteristics is characterized by comprising the following steps: acquiring a predicted scene and a dynamic map of the predicted scene, wherein the dynamic map comprises a plurality of functional areas; Obtaining driving behaviors of a user in the predicted scene based on a preset electric automobile travel model and the dynamic map; Predicting charge-discharge power boundaries at different time periods based on the driving behavior and battery characteristic parameters of the user driving a vehicle; And aggregating the charge and discharge power boundaries of all vehicles in the same time period and the functional area to obtain the space-time distribution of charge and discharge resources in the prediction scene.
  2. 2. The method of claim 1, wherein the step of obtaining the driving behavior of the user in the predicted scene based on the preset electric vehicle travel model and the dynamic map comprises: Predicting a travel track of a vehicle in the prediction scene based on a preset electric vehicle travel model; carrying out congestion analysis on each travel period based on the dynamic map to obtain the influence degree of road conditions on the travel of the user; And correcting the travel track based on the influence degree to obtain the driving behavior of the user in the predicted scene, wherein the driving behavior comprises the travel track and the travel willingness of the user.
  3. 3. The method according to claim 2, wherein the step of predicting the travel track of the vehicle in the predicted scene based on the preset electric vehicle travel model includes: Acquiring historical vehicle driving data; Analyzing probability relations between each historical track and travel willingness from the historical vehicle travel data; based on the probability relation, an electric automobile travel model is constructed; Analyzing travel willingness and historical track of a user from the historical vehicle driving data; and carrying out Markov chain analysis on the travel willingness and the history track to obtain an electric automobile travel model.
  4. 4. The method of claim 3, wherein the travel intent comprises an average intensity, a row discrete coefficient, and a travel peak concentration with a travel rate above a preset threshold; the step of analyzing the probability relation between each historical track and travel willingness from the historical vehicle travel data comprises the following steps: identifying functional areas from the historical vehicle travel data; Counting the average intensity, the line discrete coefficient and the line peak concentration of the travel quantity of the user in each functional area reflected in the historical vehicle travel data; Evaluating the transition probability among the functional areas in different time periods based on the average intensity, the travel discrete coefficient and the travel peak concentration; and determining the probability relation between the history track and travel willingness in different time periods among the functional areas based on the transition probability.
  5. 5. The method of claim 2, wherein the step of predicting the travel track of the vehicle in the predicted scene based on the preset electric vehicle travel model comprises: Performing weather analysis on the predicted scene to obtain date, place and weather data of the predicted scene; And inputting the date, the place and the weather data into a preset electric vehicle travel model to obtain a travel track of the vehicle in the prediction scene, wherein the electric vehicle travel model predicts the travel track of the vehicle based on travel willingness determined by the date, the place and the weather data.
  6. 6. The method of claim 1, wherein the driving behavior further comprises the user driving habits, and the predicting the charge-discharge power boundaries at different time periods based on the driving behavior and the battery characteristic parameters of the user-driven vehicle comprises: Predicting the travel energy consumption of the vehicle in different time periods based on the travel track in the driving behavior; Based on the battery characteristic parameters of the vehicle driven by the user and the driving habit, predicting auxiliary energy consumption of the user in driving at different periods; and predicting the charge and discharge power boundaries in different time periods based on the travel energy consumption and the auxiliary energy consumption.
  7. 7. The method of claim 6, wherein predicting charge-discharge power boundaries at different time periods based on the travel power consumption and the auxiliary power consumption comprises: predicting a theoretical charging period and a theoretical charging place of the vehicle in the travel track based on the travel energy consumption and the auxiliary energy consumption; simulating the process of selecting a charging period and a charging place by the user based on the current charging price, battery depreciation loss and charging convenience to obtain a charging decision; And modifying the theoretical charging period and the theoretical charging place based on the charging decision to obtain charging and discharging power boundaries in different periods.
  8. 8. The method of claim 1, wherein the step of aggregating all vehicles at the same time period with the charge-discharge power boundaries in the functional area to obtain the spatiotemporal distribution of charge-discharge resources in the predicted scenario is preceded by the step of: Determining attractive force parameters of each functional area in different time periods based on attractive force of each functional area in different time periods; The step of aggregating the charge and discharge power boundaries of all vehicles in the same time period and the functional area to obtain the space-time distribution of the charge and discharge resources in the prediction scene further comprises the following steps: And based on the attractive force parameters, aggregating the charge and discharge power boundaries of all vehicles in the same time period and the functional area to obtain the space-time distribution of charge and discharge resources in the prediction scene.
  9. 9. A charge and discharge resource prediction device based on travel characteristics of a user, the device comprising: the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring a prediction scene and a dynamic map of the prediction scene, and the dynamic map comprises a plurality of functional areas; The processing module is used for obtaining the driving behavior of the user in the prediction scene based on a preset electric automobile travel model and the dynamic map; a prediction module for predicting charge-discharge power boundaries at different periods based on the driving behavior and battery characteristic parameters of the user driving a vehicle; and the aggregation module is used for aggregating the charge and discharge power boundaries of all vehicles in the same time period and the functional area to obtain the space-time distribution of charge and discharge resources in the prediction scene.
  10. 10. A charge and discharge resource prediction device based on user travel characteristics, characterized in that it comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the charge and discharge resource prediction method based on user travel characteristics according to any one of claims 1 to 8.

Description

Charging and discharging resource prediction method, device and equipment based on user travel characteristics Technical Field The application relates to the technical field of power resource scheduling, in particular to a charge and discharge resource prediction method, a device and equipment based on user travel characteristics. Background Along with the propulsion of the double-carbon targets, the conservation quantity of the electric vehicles is rapidly increased, a large number of electric vehicles are connected into the power distribution network, so that new electric loads are brought to the power grid, and meanwhile, the electric vehicles have energy storage properties and are regarded as potential distributed flexible regulation resources. At present, the prediction of the charge and discharge resources of the electric automobile is mainly based on the power consumption and the driving mileage of the vehicle in unit mileage of the user, and the charge and discharge load of the vehicle is predicted by combining psychological factors such as the electric quantity anxiety cost preference of the user and the like. However, the current prediction method does not combine the dynamic map with the characteristics of the electric vehicle, so that the prediction result is deviated. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The application mainly aims to provide a charge and discharge resource prediction method, a device and equipment based on travel characteristics of a user, and aims to solve the technical problem that the current prediction method does not combine the characteristics of a dynamic map and an electric vehicle, so that a prediction result is deviated. In order to achieve the above purpose, the present application provides a method for predicting charge and discharge resources based on travel characteristics of users, the method comprising: acquiring a predicted scene and a dynamic map of the predicted scene, wherein the dynamic map comprises a plurality of functional areas; Obtaining driving behaviors of a user in the predicted scene based on a preset electric automobile travel model and the dynamic map; Predicting charge-discharge power boundaries at different time periods based on the driving behavior and battery characteristic parameters of the user driving a vehicle; And aggregating the charge and discharge power boundaries of all vehicles in the same time period and the functional area to obtain the space-time distribution of charge and discharge resources in the prediction scene. In an embodiment, the step of obtaining the driving behavior of the user in the predicted scene based on the preset electric vehicle travel model and the dynamic map includes: Predicting a travel track of a vehicle in the prediction scene based on a preset electric vehicle travel model; carrying out congestion analysis on each travel period based on the dynamic map to obtain the influence degree of road conditions on the travel of the user; And correcting the travel track based on the influence degree to obtain the driving behavior of the user in the predicted scene, wherein the driving behavior comprises the travel track and the travel willingness of the user. In an embodiment, before the step of predicting the travel track of the vehicle in the predicted scene based on the preset electric vehicle travel model, the method includes: Acquiring historical vehicle driving data; Analyzing probability relations between each historical track and travel willingness from the historical vehicle travel data; based on the probability relation, an electric automobile travel model is constructed; Analyzing travel willingness and historical track of a user from the historical vehicle driving data; and carrying out Markov chain analysis on the travel willingness and the history track to obtain an electric automobile travel model. In an embodiment, the travel willingness includes an average intensity, a row discrete coefficient, and a travel peak concentration of a travel rate higher than a preset threshold; the step of analyzing the probability relation between each historical track and travel willingness from the historical vehicle travel data comprises the following steps: identifying functional areas from the historical vehicle travel data; Counting the average intensity, the line discrete coefficient and the line peak concentration of the travel quantity of the user in each functional area reflected in the historical vehicle travel data; Evaluating the transition probability among the functional areas in different time periods based on the average intensity, the travel discrete coefficient and the travel peak concentration; and determining the probability relation between the history track and travel willingness in different time p