Data-driven symbolic ensemble models for wind speed forecasting through evolutionary algorithms

Non-linear data-driven symbolic models have been gaining traction in many fields due to their distinctive combination of modeling expressiveness and interpretability. Despite that, they are still rather unexplored for ensemble wind speed forecasting, leaving behind new promising avenues for advancing the development of more accurate models which impact the efficiency of energy production. In this work, we develop a methodology based on the evolutionary algorithm known as grammatical evolution, and apply it to build forecasting models of near-surface wind speed over five locations in northeastern Brazil. Taking advantage of the symbolic nature of the models built, we conducted an extensive series of post-analyses. Overall, our models reduced the forecasting errors by 7%–56% when compared with other techniques, including a real-world operational ensemble model used in Brazil.