Model-based closed-loop wind farm control for power maximization using Bayesian optimization: A large eddy simulation study

Bart M. Doekemeijer; Daan C.Van Der Hoek; Jan Willem Van Wingerden

doi:10.1109/CCTA.2019.8920587

Model-based closed-loop wind farm control for power maximization using Bayesian optimization: A large eddy simulation study

Bart M. Doekemeijer, Daan C.Van Der Hoek, Jan Willem Van Wingerden

Team Jan-Willem van Wingerden

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

8 Citations (Scopus)

193 Downloads (Pure)

Abstract

Modern wind farm control (WFC) methods in the literature typically rely on a surrogate model of the farm dynamics that is computationally inexpensive to enable real-time computations. As it is very difficult to model all the relevant wind farm dynamics accurately, a closed-loop approach is a prerequisite for reliable WFC. As one of the few in its field, this paper showcases a closed-loop wind farm control solution, which leverages a steady-state surrogate model and Bayesian optimization to maximize the wind-farm-wide power production. The estimated quantities are the time-averaged ambient wind direction, wind speed and turbulence intensity. This solution is evaluated for a wind farm with nine 10 MW wind turbines in large-eddy simulation, showing a time-averaged power gain of 4.4%. This is the first WFC algorithm that is tested for wind turbines of such scale in high fidelity.

Original language	English
Title of host publication	Proceedings of the 3rd IEEE Conference on Control Technology and Applications (CCTA 2019)
Place of Publication	Piscataway, NJ, USA
Publisher	IEEE
Pages	284-289
ISBN (Electronic)	978-1-7281-2767-5
DOIs	https://doi.org/10.1109/CCTA.2019.8920587
Publication status	Published - 2019
Event	3rd IEEE Conference on Control Technology and Applications, CCTA 2019 - Hong Kong, China Duration: 19 Aug 2019 → 21 Aug 2019

Conference

Conference	3rd IEEE Conference on Control Technology and Applications, CCTA 2019
Country/Territory	China
City	Hong Kong
Period	19/08/19 → 21/08/19

Bibliographical note

Accepted Author Manuscript

Access to Document

10.1109/CCTA.2019.8920587

20190802_CCTAAccepted author manuscript, 1.85 MB

Cite this

@inproceedings{583e9c991e4a45b0aa54a23145cf823d,

title = "Model-based closed-loop wind farm control for power maximization using Bayesian optimization: A large eddy simulation study",

abstract = "Modern wind farm control (WFC) methods in the literature typically rely on a surrogate model of the farm dynamics that is computationally inexpensive to enable real-time computations. As it is very difficult to model all the relevant wind farm dynamics accurately, a closed-loop approach is a prerequisite for reliable WFC. As one of the few in its field, this paper showcases a closed-loop wind farm control solution, which leverages a steady-state surrogate model and Bayesian optimization to maximize the wind-farm-wide power production. The estimated quantities are the time-averaged ambient wind direction, wind speed and turbulence intensity. This solution is evaluated for a wind farm with nine 10 MW wind turbines in large-eddy simulation, showing a time-averaged power gain of 4.4%. This is the first WFC algorithm that is tested for wind turbines of such scale in high fidelity.",

author = "Doekemeijer, {Bart M.} and Hoek, {Daan C.Van Der} and Wingerden, {Jan Willem Van}",

note = "Accepted Author Manuscript; 3rd IEEE Conference on Control Technology and Applications, CCTA 2019 ; Conference date: 19-08-2019 Through 21-08-2019",

year = "2019",

doi = "10.1109/CCTA.2019.8920587",

language = "English",

pages = "284--289",

booktitle = "Proceedings of the 3rd IEEE Conference on Control Technology and Applications (CCTA 2019)",

publisher = "IEEE",

address = "United States",

}

Doekemeijer, BM, Hoek, DCVD & Wingerden, JWV 2019, Model-based closed-loop wind farm control for power maximization using Bayesian optimization: A large eddy simulation study. in Proceedings of the 3rd IEEE Conference on Control Technology and Applications (CCTA 2019). IEEE, Piscataway, NJ, USA, pp. 284-289, 3rd IEEE Conference on Control Technology and Applications, CCTA 2019, Hong Kong, China, 19/08/19. https://doi.org/10.1109/CCTA.2019.8920587

Model-based closed-loop wind farm control for power maximization using Bayesian optimization: A large eddy simulation study. / Doekemeijer, Bart M.; Hoek, Daan C.Van Der ; Wingerden, Jan Willem Van.
Proceedings of the 3rd IEEE Conference on Control Technology and Applications (CCTA 2019). Piscataway, NJ, USA: IEEE, 2019. p. 284-289.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Model-based closed-loop wind farm control for power maximization using Bayesian optimization

T2 - 3rd IEEE Conference on Control Technology and Applications, CCTA 2019

AU - Doekemeijer, Bart M.

AU - Hoek, Daan C.Van Der

AU - Wingerden, Jan Willem Van

N1 - Accepted Author Manuscript

PY - 2019

Y1 - 2019

N2 - Modern wind farm control (WFC) methods in the literature typically rely on a surrogate model of the farm dynamics that is computationally inexpensive to enable real-time computations. As it is very difficult to model all the relevant wind farm dynamics accurately, a closed-loop approach is a prerequisite for reliable WFC. As one of the few in its field, this paper showcases a closed-loop wind farm control solution, which leverages a steady-state surrogate model and Bayesian optimization to maximize the wind-farm-wide power production. The estimated quantities are the time-averaged ambient wind direction, wind speed and turbulence intensity. This solution is evaluated for a wind farm with nine 10 MW wind turbines in large-eddy simulation, showing a time-averaged power gain of 4.4%. This is the first WFC algorithm that is tested for wind turbines of such scale in high fidelity.

AB - Modern wind farm control (WFC) methods in the literature typically rely on a surrogate model of the farm dynamics that is computationally inexpensive to enable real-time computations. As it is very difficult to model all the relevant wind farm dynamics accurately, a closed-loop approach is a prerequisite for reliable WFC. As one of the few in its field, this paper showcases a closed-loop wind farm control solution, which leverages a steady-state surrogate model and Bayesian optimization to maximize the wind-farm-wide power production. The estimated quantities are the time-averaged ambient wind direction, wind speed and turbulence intensity. This solution is evaluated for a wind farm with nine 10 MW wind turbines in large-eddy simulation, showing a time-averaged power gain of 4.4%. This is the first WFC algorithm that is tested for wind turbines of such scale in high fidelity.

UR - http://www.scopus.com/inward/record.url?scp=85077802380&partnerID=8YFLogxK

U2 - 10.1109/CCTA.2019.8920587

DO - 10.1109/CCTA.2019.8920587

M3 - Conference contribution

SP - 284

EP - 289

BT - Proceedings of the 3rd IEEE Conference on Control Technology and Applications (CCTA 2019)

PB - IEEE

CY - Piscataway, NJ, USA

Y2 - 19 August 2019 through 21 August 2019

ER -

Model-based closed-loop wind farm control for power maximization using Bayesian optimization: A large eddy simulation study

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this