Electric Vehicle Charging Load Forecasting: An Experimental Comparison of Machine Learning Methods
Iason Kyriakopoulos, Yannis Theodoridis
TL;DR
This study addresses the EV charging load forecasting problem by systematically comparing five forecasting methods—ARIMA, XGBoost, GRU, LSTM, and Transformer—across short-, mid-, and long-term horizons and across station, regional, and city-level aggregations. Using four public datasets, a unified preprocessing and evaluation framework (MAE and RMSE) is applied, enabling fair, multi-scale benchmarking. Key findings show Transformer models excel in short-term forecasts at coarse spatial scales, while GRU/LSTM provide stronger performance for longer horizons and aggregated levels, with ARIMA and XGBoost offering limited gains in many settings. The work delivers a comprehensive, reproducible benchmark that informs method selection for grid planning and smarter city initiatives, and points to future gains from hyperparameter tuning, exogenous features, and transfer learning.
Abstract
With the growing popularity of electric vehicles as a means of addressing climate change, concerns have emerged regarding their impact on electric grid management. As a result, predicting EV charging demand has become a timely and important research problem. While substantial research has addressed energy load forecasting in transportation, relatively few studies systematically compare multiple forecasting methods across different temporal horizons and spatial aggregation levels in diverse urban settings. This work investigates the effectiveness of five time series forecasting models, ranging from traditional statistical approaches to machine learning and deep learning methods. Forecasting performance is evaluated for short-, mid-, and long-term horizons (on the order of minutes, hours, and days, respectively), and across spatial scales ranging from individual charging stations to regional and city-level aggregations. The analysis is conducted on four publicly available real-world datasets, with results reported independently for each dataset. To the best of our knowledge, this is the first work to systematically evaluate EV charging demand forecasting across such a wide range of temporal horizons and spatial aggregation levels using multiple real-world datasets.