Can a wind turbine learn to operate itself? Evaluation of the potential of a heuristic, data-driven self-optimizing control system for a 5MW offshore wind turbine

Stefan Gueorguiev Iordanov, Maurizio Collu, Yi Cao

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Larger and more expensive offshore wind turbines, subject to more complex loads, operating in larger wind farms, could substantially benefit from more advanced control strategies. Nonetheless, the wind industry is reluctant to adopt such advanced, more efficient solutions, since this is perceived linked to a lower reliability. Here, a relatively simple self-optimizing control strategy, capable to "learn" (data-driven) which is the optimum control strategy depending on the objective defined, is presented. It is proved that it "re-discovers", model-free, the optimum strategy adopted by commercial wind turbine in region 2. This methodology has the potential to achieve advanced control performance without compromising its simplicity and reliability.

LanguageEnglish
Pages26-37
Number of pages12
JournalEnergy Procedia
Volume137
DOIs
Publication statusPublished - 30 Oct 2017

Fingerprint

Offshore wind turbines
Wind turbines
Control systems
Farms
Industry

Keywords

  • advanced control systems
  • data-driven
  • self-optimising control
  • wind turbines

Cite this

@article{11818fb2d50f4d4696301b85c140872f,
title = "Can a wind turbine learn to operate itself? Evaluation of the potential of a heuristic, data-driven self-optimizing control system for a 5MW offshore wind turbine",
abstract = "Larger and more expensive offshore wind turbines, subject to more complex loads, operating in larger wind farms, could substantially benefit from more advanced control strategies. Nonetheless, the wind industry is reluctant to adopt such advanced, more efficient solutions, since this is perceived linked to a lower reliability. Here, a relatively simple self-optimizing control strategy, capable to {"}learn{"} (data-driven) which is the optimum control strategy depending on the objective defined, is presented. It is proved that it {"}re-discovers{"}, model-free, the optimum strategy adopted by commercial wind turbine in region 2. This methodology has the potential to achieve advanced control performance without compromising its simplicity and reliability.",
keywords = "advanced control systems, data-driven, self-optimising control, wind turbines",
author = "Iordanov, {Stefan Gueorguiev} and Maurizio Collu and Yi Cao",
year = "2017",
month = "10",
day = "30",
doi = "10.1016/j.egypro.2017.10.332",
language = "English",
volume = "137",
pages = "26--37",
journal = "Energy Procedia",
issn = "1876-6102",

}

Can a wind turbine learn to operate itself? Evaluation of the potential of a heuristic, data-driven self-optimizing control system for a 5MW offshore wind turbine. / Iordanov, Stefan Gueorguiev; Collu, Maurizio; Cao, Yi.

In: Energy Procedia, Vol. 137, 30.10.2017, p. 26-37.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Can a wind turbine learn to operate itself? Evaluation of the potential of a heuristic, data-driven self-optimizing control system for a 5MW offshore wind turbine

AU - Iordanov, Stefan Gueorguiev

AU - Collu, Maurizio

AU - Cao, Yi

PY - 2017/10/30

Y1 - 2017/10/30

N2 - Larger and more expensive offshore wind turbines, subject to more complex loads, operating in larger wind farms, could substantially benefit from more advanced control strategies. Nonetheless, the wind industry is reluctant to adopt such advanced, more efficient solutions, since this is perceived linked to a lower reliability. Here, a relatively simple self-optimizing control strategy, capable to "learn" (data-driven) which is the optimum control strategy depending on the objective defined, is presented. It is proved that it "re-discovers", model-free, the optimum strategy adopted by commercial wind turbine in region 2. This methodology has the potential to achieve advanced control performance without compromising its simplicity and reliability.

AB - Larger and more expensive offshore wind turbines, subject to more complex loads, operating in larger wind farms, could substantially benefit from more advanced control strategies. Nonetheless, the wind industry is reluctant to adopt such advanced, more efficient solutions, since this is perceived linked to a lower reliability. Here, a relatively simple self-optimizing control strategy, capable to "learn" (data-driven) which is the optimum control strategy depending on the objective defined, is presented. It is proved that it "re-discovers", model-free, the optimum strategy adopted by commercial wind turbine in region 2. This methodology has the potential to achieve advanced control performance without compromising its simplicity and reliability.

KW - advanced control systems

KW - data-driven

KW - self-optimising control

KW - wind turbines

UR - http://www.scopus.com/inward/record.url?scp=85040306830&partnerID=8YFLogxK

U2 - 10.1016/j.egypro.2017.10.332

DO - 10.1016/j.egypro.2017.10.332

M3 - Article

VL - 137

SP - 26

EP - 37

JO - Energy Procedia

T2 - Energy Procedia

JF - Energy Procedia

SN - 1876-6102

ER -