Benchmarking study compares short-term load forecasting accuracy using machine learning methods with TSO forecasts, indicating potential improvements.
Modern power systems require increasingly precise forecasts of electricity consumption, which are crucial for effective planning, reducing the risk of power shortages, and integrating renewable energy sources. This article presents the results of comparative benchmarking studies on short-term load forecasting (STLF) at a 15 min resolution. The study uses the rolling-window training method, and the results were compared with the official forecasts of the Transmission System Operator (TSO). The analysis is based on time series and machine learning methods, with the aim of improving the operational accuracy necessary for stable and secure management of the power management system.
No takes yet. Share an insight, caveat, or question.
Misiurek et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: