Wind Power Forecasting with Machine Learning: Single and combined methods

In Portugal, wind power represents one of the largest renewable sources energy in national mix. The investment started several decades ago and is still on roadmap political industrial players. One example that by 2030 it estimated going to represent up 35% production Portugal. With growth installed capacity, development methods forecast amount generated becomes increasingly necessary. Historically, Numerical Weather Prediction (NWP) models were used. However, forecasting accuracy depends many variables such as on-site conditions, surrounding terrain relief, local meteorology, etc. Thus, a challenge obtain improved results using methods. This article aims report machine learning pipeline with objective improving capability NWP’s an error lower than 10%.