Wind Power Forecasts Using Gaussian Processes and Numerical Weather Prediction

TLDR

Wind at the earth's surface is intrinsically complex and stochastic, making accurate wind‑power forecasts essential for safe and economic wind energy use. This study investigates combining a Gaussian process with a numerical weather prediction model to forecast wind power up to one day ahead. The approach corrects NWP wind‑speed forecasts with a Gaussian process, then models the relationship between corrected speed and turbine power output using a censored Gaussian process, and is validated on three real‑world datasets. Compared with classical models, the proposed method reduces mean absolute error by 9–14% versus an ANN and by nearly 17% on a new wind farm dataset with limited training data.

Abstract

Since wind at the earth's surface has an intrinsically complex and stochastic nature, accurate wind power forecasts are necessary for the safe and economic use of wind energy. In this paper, we investigated a combination of numeric and probabilistic models: a Gaussian process (GP) combined with a numerical weather prediction (NWP) model was applied to wind-power forecasting up to one day ahead. First, the wind-speed data from NWP was corrected by a GP, then, as there is always a defined limit on power generated in a wind turbine due to the turbine controlling strategy, wind power forecasts were realized by modeling the relationship between the corrected wind speed and power output using a censored GP. To validate the proposed approach, three real-world datasets were used for model training and testing. The empirical results were compared with several classical wind forecast models, and based on the mean absolute error (MAE), the proposed model provides around 9% to 14% improvement in forecasting accuracy compared to an artificial neural network (ANN) model, and nearly 17% improvement on a third dataset which is from a newly-built wind farm for which there is a limited amount of training data.