Density-based clustering multiple linear regression model of energy consumption for electric vehicles

Abstract

With the increasing popularity of electric vehicles, energy consumption has become a key performance indicator for electric vehicle drivers, automakers and policy makers. Accurate and real-time prediction of energy consumption under real-world driving conditions is critical to reducing “range anxiety” and can support optimization of battery size, energy-saving route planning and charging facility operation. In this paper, data collected from 988 electric vehicles of the same model for one year in Zhengzhou, China, are obtained to study the energy consumption of electric vehicles in actual driving conditions. An improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model were established to classify the driving behaviors of the drivers. Then the key factors of energy consumption including velocity, accelerated velocity and temperature are studied and modeled. With that, an improved density-based clustering multiple linear regression model for energy prediction were established with driving behavior classification. The density-based clustering multiple linear regression model (DBC-MLR) has better prediction accuracy and can grasp the training features in energy consumption prediction in real driving. The proposed method shows a root mean error (RMSE) of 3.008 kwh/100 km, which is reduced by 11.3 % and 18.4 % compared to conventional machine learning method and multiple linear regression method respectively.