Wind power predictions from nowcasts to 4-hour forecasts: a learning approach with variable selection

TL;DR

This paper develops a machine learning approach combining weather model outputs and local data to improve short-term wind power forecasts up to 4 hours ahead, emphasizing variable selection and model comparison.

Contribution

It introduces a variable selection process for wind prediction models and compares linear and nonlinear methods for short-term wind speed and power forecasting.

Findings

Variable selection improves forecast accuracy.

Nonlinear models outperform linear ones in certain scenarios.

Direct wind power prediction is competitive with indirect methods.

Abstract

We study short-term prediction of wind speed and wind power (every 10 minutes up to 4 hours ahead). Accurate forecasts for these quantities are crucial to mitigate the negative effects of wind farms' intermittent production on energy systems and markets. We use machine learning to combine outputs from numerical weather prediction models with local observations. The former provide valuable information on higher scales dynamics while the latter gives the model fresher and location-specific data. So as to make the results usable for practitioners, we focus on well-known methods which can handle a high volume of data. We study first variable selection using both a linear technique and a nonlinear one. Then we exploit these results to forecast wind speed and wind power still with an emphasis on linear models versus nonlinear ones. For the wind power prediction, we also compare the indirect approach (wind speed predictions passed through a power curve) and the indirect one (directly predict wind power).