A two‐step machine‐learning approach to statistical post‐processing of weather forecasts for power generation

Abstract

By the end of 2021, the renewable energy share of the global electricity capacity reached 38.3% and the new installations were dominated by wind and solar energy, showing global increases of 12.7% and 18.5% respectively. However, both wind and photovoltaic energy sources are highly volatile, making planning difficult for grid operators; thuss, accurate forecasts of the corresponding weather variables are essential for reliable electricity predictions. The most advanced approach in weather prediction is the ensemble method, which opens the door for probabilistic forecasting. However, ensemble forecasts are often underdispersive and subject to systematic bias. Hence, they require some form of statistical post‐processing, where parametric models provide full predictive distributions of the weather variables at hand. We propose a general two‐step machine‐learning‐based approach to calibrating ensemble weather forecasts, where, in the first step, improved point forecasts are generated, which then together with various ensemble statistics serve as input features of the neural network estimating the parameters of the predictive distribution. In two case studies based on 100 m wind speed and global horizontal irradiance forecasts of the operational ensemble prediction system of the Hungarian Meteorological Service, the predictive performance of this novel method is compared with the forecast skill of the raw ensemble and the state‐of‐the‐art parametric approaches. Both case studies confirm that, at least up to 48 hr, statistical post‐processing substantially improves the predictive performance of the raw ensemble for all forecast horizons considered. The variants of the proposed two‐step method investigated outperform in skill their competitors, and the suggested new approach is well applicable for different weather quantities and for a fair range of predictive distributions.