Household EV Charging Demand Prediction Using Machine and Ensemble Learning

The global popularization of electric vehicles (EVs) poses an opportunity for the construction of micro-grid and smart community within energy internet on competent the massive and concentrated energy switching and routing in the local environment. Smart EV charging is a promising solution to manage EV charging load that relies on an accurate prediction of EV charging demands. Evaluation of household EV charging demand is a primary factor for designing smart EV charging solutions on household and neighbourhood level. However, this subject has not been adequately discussed in the research community. In this paper, several widely used machine learning algorithms are adopted to forecast the household day-ahead EV charging occurrence-time and the "no charge" day respectively. The performance of the algorithms are evaluated and compared. A two-layer hybrid stacking ensemble learning method is also proposed, that combines multiple machine learning algorithms. This proposed model is demonstrated to achieve a better classification performance than individual algorithms.