Individual information

The growing use of electric vehicles (EVs) is key to reducing greenhouse gas emissions and promoting sustainable transportation. However, this rapid growth creates challenges, such as managing peak charging demand, maintaining power grid stability, and ensuring efficient use of charging stations. This study examines EV charging behavior within a potential local energy community in France, using data from September 2021 to August 2023 from 23 charging terminals. The analysis explores patterns in charging times, session durations, and energy consumption, uncovering trends and inefficiencies that impact power grid management. To improve energy planning, the study uses three machine learning models to forecast day-ahead EV charging demand. Gradient Boosting outperformed the others, achieving the lowest errors and highest R² (0.664), demonstrating the potential of advanced forecasting techniques for optimizing energy management systems. The results show how accurate forecasts can help balance energy demand and supply, making charging more efficient. This study demonstrates the value of integrating advanced forecasting techniques into energy management systems to support the growing adoption of EVs, reduce energy costs and improve power grid stability.