DemandCast: Global hourly electricity demand forecasting
This work addresses electricity demand forecasting for energy system planners and policymakers, but it is incremental as it applies an existing method (XGBoost) to a new large-scale dataset.
The paper tackles global hourly electricity demand forecasting by developing a machine learning framework using XGBoost, integrating historical demand, weather, and socioeconomic data to predict normalized demand profiles, resulting in accurate and scalable forecasts for energy planning.
This paper presents a machine learning framework for electricity demand forecasting across diverse geographical regions using the gradient boosting algorithm XGBoost. The model integrates historical electricity demand and comprehensive weather and socioeconomic variables to predict normalized electricity demand profiles. To enable robust training and evaluation, we developed a large-scale dataset spanning multiple years and countries, applying a temporal data-splitting strategy that ensures benchmarking of out-of-sample performance. Our approach delivers accurate and scalable demand forecasts, providing valuable insights for energy system planners and policymakers as they navigate the challenges of the global energy transition.