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.

Related authors

Utilizing physics-based input features within a machine learning model to predict wind speed forecasting error
Daniel Vassallo, Raghavendra Krishnamurthy, and Harindra J. S. Fernando
Wind Energ. Sci., 6, 295–309, https://doi.org/10.5194/wes-6-295-2021,https://doi.org/10.5194/wes-6-295-2021, 2021
Short summary

Related subject area

Wind and turbulence
The smoother the better? A comparison of six post-processing methods to improve short-term offshore wind power forecasts in the Baltic Sea
Christoffer Hallgren, Stefan Ivanell, Heiner Körnich, Ville Vakkari, and Erik Sahlée
Wind Energ. Sci., 6, 1205–1226, https://doi.org/10.5194/wes-6-1205-2021,https://doi.org/10.5194/wes-6-1205-2021, 2021
Short summary
Statistical impact of wind-speed ramp events on turbines, via observations and coupled fluid-dynamic and aeroelastic simulations
Mark Kelly, Søren Juhl Andersen, and Ásta Hannesdóttir
Wind Energ. Sci., 6, 1227–1245, https://doi.org/10.5194/wes-6-1227-2021,https://doi.org/10.5194/wes-6-1227-2021, 2021
Short summary
Probabilistic estimation of the Dynamic Wake Meandering model parameters using SpinnerLidar-derived wake characteristics
Davide Conti, Nikolay Dimitrov, Alfredo Peña, and Thomas Herges
Wind Energ. Sci., 6, 1117–1142, https://doi.org/10.5194/wes-6-1117-2021,https://doi.org/10.5194/wes-6-1117-2021, 2021
Short summary
Recovery processes in a large offshore wind farm
Tanvi Gupta and Somnath Baidya Roy
Wind Energ. Sci., 6, 1089–1106, https://doi.org/10.5194/wes-6-1089-2021,https://doi.org/10.5194/wes-6-1089-2021, 2021
Short summary
Extreme wind shear events in US offshore wind energy areas and the role of induced stratification
Mithu Debnath, Paula Doubrawa, Mike Optis, Patrick Hawbecker, and Nicola Bodini
Wind Energ. Sci., 6, 1043–1059, https://doi.org/10.5194/wes-6-1043-2021,https://doi.org/10.5194/wes-6-1043-2021, 2021
Short summary

Cited articles

Aggarwal, C. C.: Neural networks and deep learning, Springer, Cham, Switzerland, 2018. a, b
Akish, E., Bianco, L., Djalalova, I. V., Wilczak, J. M., Olson, J. B., Freedman, J., Finley, C., and Cline, J.: Measuring the impact of additional instrumentation on the skill of numerical weather prediction models at forecasting wind ramp events during the first Wind Forecast Improvement Project (WFIP), Wind Energy, 22, 1165–1174, 2019. a
A2e – Atmosphere to Electrons: wfip2/lidar.z03.00, Maintained by A2e Data Archive and Portal for US Department of Energy, Office of Energy Efficiency and Renewable Energy, https://doi.org/10.21947/1328914, 2017. a
Baklanov, A. A., Grisogono, B., Bornstein, R., Mahrt, L., Zilitinkevich, S. S., Taylor, P., Larsen, S. E., Rotach, M. W., and Fernando, H.: The nature, theory, and modeling of atmospheric planetary boundary layers, B. Am. Meteorol. Soc., 92, 123–128, 2011. a
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.