Renewable energy is an essential driver towards tackling the environmental crisis. Given the increasing need to ensure sustainability and reduce greenhouse gas emissions, wind energy has become one of the most relevant areas to consider in today’s society. However, it appears challenging to rely on this type of energy because of the uncertain nature of the wind. It is essential to use monitoring tools that can accurately capture the uncertainty of the underlying environmental processes and estimate the generated power to ensure the reliability of wind-based power systems. One of these monitoring tools is the power curve, which captures the relationship between environmental parameters (such as wind speed) and expected power production. Many regression techniques have previously been used to predict this power production, including Artificial Neural Networks (ANN). The problem is that they do not capture the uncertainty of the power production. In contrast with the power curve models already implemented when using ANNs, we propose a novel approach based on deep ensembles to predict the mean and model variance on the expected power production. We used three months of Supervisory Control and Data Acquisition data from a single wind turbine to set up the experiments. The results show that the mean and standard deviation fit the data well. It also appears that the expected mean curve goes through the center of the cloud of original data points, while the standard deviation accurately captures the spread of the data. We conclude that that the deep ensemble approach provides an accurate prediction mechanism to estimate the power production from the wind speed while also offering an uncertainty measure. Therefore, the deep ensemble approach allows us to construct a power curve with uncertainty information.
Perez Sanjines, FR , Verstraeten, T , Nowe, A & Helsen, J 2022, Deep ensemble with Neural Networks to model power-curve uncertainty . in Journal of Physics: Conference Series: EERA DeepWind Offshore Wind R&D Conference 19/01/2022 - 21/01/2022 Trondheim, Norway. 1 edn, vol. 2362, 012029, Journal of Physics: Conference Series, IOP Publishing, EERA DEEPWIND 2022, Trondheim, Norway, 19/01/22 .
Perez Sanjines, F. R. , Verstraeten, T. , Nowe, A. , & Helsen, J. (2022). Deep ensemble with Neural Networks to model power-curve uncertainty . In Journal of Physics: Conference Series: EERA DeepWind Offshore Wind R&D Conference 19/01/2022 - 21/01/2022 Trondheim, Norway (1 ed., Vol. 2362). [012029] (Journal of Physics: Conference Series). IOP Publishing.
@inproceedings{96ed8626299d418caa75390e7fa895d2,
title = " Deep ensemble with Neural Networks to model power-curve uncertainty " ,
abstract = " Renewable energy is an essential driver towards tackling the environmental crisis. Given the increasing need to ensure sustainability and reduce greenhouse gas emissions, wind energy has become one of the most relevant areas to consider in today{ extquoteright}s society. However, it appears challenging to rely on this type of energy because of the uncertain nature of the wind. It is essential to use monitoring tools that can accurately capture the uncertainty of the underlying environmental processes and estimate the generated power to ensure the reliability of wind-based power systems. One of these monitoring tools is the power curve, which captures the relationship between environmental parameters (such as wind speed) and expected power production. Many regression techniques have previously been used to predict this power production, including Artificial Neural Networks (ANN). The problem is that they do not capture the uncertainty of the power production. In contrast with the power curve models already implemented when using ANNs, we propose a novel approach based on deep ensembles to predict the mean and model variance on the expected power production. We used three months of Supervisory Control and Data Acquisition data from a single wind turbine to set up the experiments. The results show that the mean and standard deviation fit the data well. It also appears that the expected mean curve goes through the center of the cloud of original data points, while the standard deviation accurately captures the spread of the data. We conclude that that the deep ensemble approach provides an accurate prediction mechanism to estimate the power production from the wind speed while also offering an uncertainty measure. Therefore, the deep ensemble approach allows us to construct a power curve with uncertainty information. " ,
author = " {Perez Sanjines}, {Fabian Ramiro} and Timothy Verstraeten and Ann Nowe and Jan Helsen " ,
note = " Funding Information: This research was supported by funding from the Flemish Government under the “Onderzoeksprogramma Artifici{ " e}le Intelligentie (AI) Vlaanderen” programme and under the VLAIO Supersized 4.0 ICON project. Calculations were facilitated by the “Vlaams Supercomputer Centrum” and VSC Cloud. Publisher Copyright: { extcopyright} 2022 Institute of Physics Publishing. All rights reserved. Copyright: Copyright 2022 Elsevier B.V., All rights reserved. EERA DEEPWIND 2022, DEEPWIND Conference date: 19-01-2022 Through 21-01-2022 " ,
year = " 2022 " ,
month = nov,
day = " 9 " ,
doi = " 10.1088/1742-6596/2362/1/012029 " ,
language = " English " ,
volume = " 2362 " ,
series = " Journal of Physics: Conference Series " ,
publisher = " IOP Publishing " ,
booktitle = " Journal of Physics: Conference Series " ,
edition = " 1 " ,
url = " https://www.deepwind.no/programme/ " ,
}