Electric Vehicles Arrival and Departure Time Prediction Based on Deep Learning: The Case of Morocco

Abstract

The charging patterns of plug-in electric vehicle (PEV) owners have a substantial impact on the distribution network's reliability. Uncertainty over arrival and departure dates makes scheduling plug-in hybrid electric cars difficult, particularly in regulated (non-liberal) electricity markets. Monitoring the arrival and departure periods of electric vehicles (EVs) in general has become one of the most essential parts in green and intelligent micro-systems; hence, anticipating the arrival and departure times of PEVs may assist manage the grid effectively. The purpose of this paper is to predict the arrival and departure times of electric vehicles in public charging station in to better distribute electric power on the grid as well as assess the expected impact of additional EVs on the grid, considering specific characteristics of the Moroccan power system. Consequently, three deep learning methods are applied in this research and the approach is validated using a dataset consisting of 1793 charging events collected from public charging stations in Morocco. Obtained results will serve as a decision-making tool for electricity regulatory authorities (ONEE) and public utility companies in the selection and implementation of efficient smart charging strategies, including the potential for electric vehicles (EVs) to use renewable energy more efficiently, lowering costs while improving the Moroccan electricity grid's stability.