Articles | Volume 5, issue 3
Wind Energ. Sci., 5, 959–975, 2020
https://doi.org/10.5194/wes-5-959-2020

Special issue: Flow in complex terrain: the Perdigão campaigns (WES/ACP/AMT...

Wind Energ. Sci., 5, 959–975, 2020
https://doi.org/10.5194/wes-5-959-2020

Research article 26 Jul 2020

Research article | 26 Jul 2020

Decreasing wind speed extrapolation error via domain-specific feature extraction and selection

Daniel Vassallo et al.

Data sets

Perdigão Field Experiment Data UCAR/NCAR Earth Observing Laboratory https://data.eol.ucar.edu/project/Perdigao

wfip2/lidar.z03.00 A2e – Atmosphere to Electrons https://doi.org/10.21947/1328914

Model code and software

Wind Speed Extrapolation Codes D. Vassallo https://github.com/dvassall/Wind-Speed-Extrapolation-Codes

Download
Short summary
Model error and uncertainty is a challenge in the wind energy industry, potentially leading to mischaracterization of millions of dollars' worth of wind resource. This paper combines meteorological knowledge with machine learning techniques, specifically artificial neural networks (ANNs), to better extrapolate wind speeds. It is found that ANNs can reduce power-law extrapolation error by up to 52 % while simultaneously reducing uncertainty. A test case is shown to help decipher the ANN results.