Research on the Energy Consumption Estimation Method of Pure Electric Vehicle Based on XGBoost

Abstract

In recent years, with the vigorous development of the electric vehicle industry, the number of car ownership in China has increased year by year. However, due to the limitation of the storage capacity of lithium batteries, the mileage of pure electric vehicles is short, and the supporting facilities such as charging piles are not perfect enough, resulting in inconvenient charging. These troubles have brought about problems such as horizontal mileage anxiety and restricted the development of electric vehicles. This paper, based on the information collected by electric vehicle BMS, constructs the characteristics of driving energy consumption estimation and based on the energy gradient prediction model of extreme gradient enhancement (XGBoost): the model is finally determined through data preparation, feature extraction and model optimization. The experimental results show that the algorithm model based on the limit gradient lifting has higher prediction accuracy and can meet the requirements of actual working conditions.