Retrospective de-trending of wind site turbulence using machine learning
Tough, Fraser and Hart, Edward (2022) Retrospective de-trending of wind site turbulence using machine learning. Wind Energy, 25 (7). pp. 1173-1187. ISSN 1095-4244 (https://doi.org/10.1002/we.2720)
Preview |
Text.
Filename: Tough_Hart_WE_2022_Retrospective_de_trending_of_wind_site_turbulence.pdf
Final Published Version License: Download (2MB)| Preview |
Abstract
This paper considers the removal of low-frequency trend contributions from turbulence intensity values at sites for which only 10-min statistics in wind speed are available. It is proposed the problem be reformulated as a direct regression task, solvable using machine learning techniques in conjunction with training data formed from measurements at sites for which underlying (non-averaged) wind data are available. Once trained, the machine learning models can de-trend sites for which only 10-min statistics have been retained. A range of machine learning techniques are tested, for cases of linear and filtered approaches to de-trending, using data from 14 sites. Results indicate this approach allows for excellent approximation of de-trended turbulence intensity distributions at unobserved sites, providing significant improvements over the existing recommended method. The best results were obtained using Neural Network, Random Forest and Boosted Tree models.
-
-
Item type: Article ID code: 79670 Dates: DateEventJuly 2022Published17 February 2022Published Online30 January 2022Accepted23 April 2021SubmittedSubjects: Technology > Engineering (General). Civil engineering (General) > Environmental engineering
Technology > Engineering (General). Civil engineering (General)Department: Faculty of Engineering > Electronic and Electrical Engineering Depositing user: Pure Administrator Date deposited: 18 Feb 2022 15:56 Last modified: 16 Apr 2024 00:31 URI: https://strathprints.strath.ac.uk/id/eprint/79670