Machine Learning-Based Approach for EV Charging Behavior

Abstract

As smart city applications are moving from conceptual models to the development phase, smart transportation, of smart cities’ applications, is gaining ground nowadays. Electric vehicles (EVs) are considered to be one of the major pillars of smart transportation. EVs are ever-growing in popularity due to their potential contribution in reducing dependency on fossil fuels and greenhouse gas emissions. However, large-scale deployment of EV charging stations poses multiple challenges to the power grid and public infrastructure. The solution to this problem lies in the utilization of scheduling algorithms to better manage the growing public charging demand. Modeling EV charging behavior using data-driven tools and machine learning algorithms can improve scheduling algorithms. Researchers have focused on using historical charging data for predictions of behaviors such as departure time and energy needs. However, variables such as weather, traffic, and nearby events, which have been neglected to a large extent, can perhaps add meaningful representations, and provide more accurate predictions. Therefore, in this thesis we propose the usage of historical charging data in conjunction with the weather, traffic, and events data to predict EV departure time and energy consumption. Several popular machine learning algorithms including random forest, support vector machine, XGBoost, and deep neural networks are investigated. The best predictive performance is achieved by an ensemble-learning model, which improves upon the existing works in the literature with SMAPES of 9.9% and 11.6% for session duration and energy consumptions, respectively. In both predictions, we demonstrate a significant improvement compared to previous work on the same dataset and we highlight the importance of traffic and weather information for charging behavior predictions.