Prediction of Electric Vehicles Charging Behavior Based on the Data of Connected Vehicles

With the rapid development of electric vehicles (EVs), large-scale EV charging behaviour brings tremendous pressure on electric power systems. To ensure the stability of the power grid, there is a need to accurately predict the potential charging behaviour for EVs. In this research, trip chain events extracted from EV data were used to identify factors that significantly affected charging behavior. The data analysis indicated that the end time, average velocity, start of SOC, total time, and charging behavior for the last trip chains were significant factors. Furthermore, due to the dichotomous nature of charging behavior, a binary logistic regression model was developed for charging behavior prediction. The results showed that the logistic regression model performed significantly well. This research is expected to contribute to the improvement of EV charging behavior significantly and provide important political implications for decision makers when taking steps to ensure grid stability.