Model‐free closed‐loop wind farm control using reinforcement learning with recursive least squares
Wind Energy · 2024-11 · 27 (11) · 1173-1187
DOI: 10.1002/we.2852 ↗Kurz gefasst
Fachartikel in der Zeitschrift Wind Energy, online erschienen am 07.07.2023. Verfasst von Jaime Liew und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Wind farms experience significant power losses due to wake interactions between turbines. Research shows that wake steering can alleviate these losses by redirecting the flow through the farm. However, dynamic closed‐loop implementations of wake steering are rarely presented. We present a model‐free closed‐loop control method using reinforcement learning methodology known as policy gradients in combination with recursive least squares to perform real‐time wake steering in a wind farm. We present dynamic simulations of a four‐turbine wind farm row using HAWC2Farm, implementing the reinforcement learning control method for various inflow conditions and controller configurations. By controlling the three most upstream turbines, mean power gains of and (95% confidence interval) are observed in partial wake and full wake conditions respectively at 7.5% turbulence intensity. The study helps to bridge the gap between theoretical wind farm control and real‐world wind farm systems.
Zitieren
APA
Liew, J., Göçmen, T., Lio, W. H., & Larsen, G. C. (2024). Model‐free closed‐loop wind farm control using reinforcement learning with recursive least squares. Wind Energy, 27(11), 1173-1187. https://doi.org/10.1002/we.2852
Vancouver
Liew J, Göçmen T, Lio WH, Larsen GC. Model‐free closed‐loop wind farm control using reinforcement learning with recursive least squares. Wind Energy. 2024;27(11):1173-1187. doi:10.1002/we.2852
BibTeX
@article{Liew2024,
author = {Liew, Jaime and Göçmen, Tuhfe and Lio, Wai Hou and Larsen, Gunner Chr.},
title = {Model‐free closed‐loop wind farm control using reinforcement learning with recursive least squares},
journal = {Wind Energy},
year = {2024},
volume = {27},
number = {11},
pages = {1173--1187},
doi = {10.1002/we.2852}
}
EUVIMED