Estimation and modeling method for charging load of electric vehicle

Abstract

The invention relates to an electric vehicle charging load estimation and modeling method, and aims to solve the problems that the precision of model evaluation is low due to the fact that the existing similar method rarely adopts CNN and LSTM to quickly obtain charging spatial-temporal characteristics of different time periods and different scenes, and the precision of model evaluation is low due to the fact that the existing similar method rarely adopts a BP neural network to fit the charging preference of a user. And a smooth charging road section channel at the charging station is established. The method is characterized by comprising the following steps: acquiring a travel track of an electric vehicle, mining a travel mode and a charging mode of an electric vehicle user, and performing spatial-temporal feature extraction on travel mode data and charging mode data in different scenes and different time periods by fusing CNN and LSTM; on the basis of the spatial-temporal characteristics, a BP neural network is adopted to integrate the traffic network state to realize time-phased estimation of the charging load; meanwhile, according to the method, a BP neural network is adopted, charging load prediction in different scenes and different time periods is achieved in combination with traffic states, and charging preferences of users are fitted.

Description

Technical field [0001] The present invention relates to an electric vehicle charging load system, is an electric vehicle charging load estimation and modeling method. Background [0002] At present, the accurate electric vehicle charging load estimation model can provide reliable real-time charging estimation information for the optimal operation and control of the distribution network, and provide refined spatio-temporal and spatial characteristic inputs for the distribution network planning. Existing electric vehicle charging load technologies, such as application number 201710952465.0 disclosed in the Chinese patent literature, application publication date 2018.02.13, invention name "A method for predicting the charging load of electric vehicles considering spatio-temporal distribution"; and then application number 202110978765.2 disclosed in the Chinese patent literature, application publication date 2021.12.31, the invention name "A charging load prediction method for electr...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the above-mentioned shortcomings, the purpose of the present invention is to provide a method for estimating and modeling the charging load of electric vehicles in the field, so that it mainly solves the problem that existing similar methods rarely use CNN and LSTM to quickly obtain different scenarios in different time periods The time and space characteristics of charging lead to low accuracy of model evaluation, and seldom use BP neural network to fit users' charging preferences and establish smooth charging channels at charging stations.

Images