Wake steering yaws upstream wind turbines to deflect their wakes from downstream turbines, thus increasing the generated power. However, most wake steering methods rely on lookup tables obtained offline, which map a set of conditions, such as wind speed and direction, to yaw angles for each turbine in a farm. These tables assume all turbines are operational and can be significantly non–optimal when one or more turbines do not provide the rated power, because of low wind speed, faults, routine maintenance, or emergency maintenance. This work presents an intelligent wake steering method that adapts to turbine actual working conditions when determining yaw angles. Using a hybrid model–and a learning–based method, i.e. an active control, a neural network is trained online to determine yaw angles from operating conditions including turbine status. Unlike purely model–based approaches which use lookup tables provided by the wind turbine manufacturer or generated offline, the proposed control solution does not need to solve e.g. optimisation problems for each combination of the turbine non-optimal working conditions in a farm; the integration of learning strategy in the control design allows to obtain an active control scheme.

Simani S., Farsoni S., Castaldi P. (2023). Data–Driven Design of an Active Wake Steering Control for a Wind Farm Benchmark. Berlin : Springer Science and Business Media Deutschland GmbH [10.1007/978-3-031-37963-5_5].

Data–Driven Design of an Active Wake Steering Control for a Wind Farm Benchmark

Castaldi P.
Ultimo
Methodology
2023

Abstract

Wake steering yaws upstream wind turbines to deflect their wakes from downstream turbines, thus increasing the generated power. However, most wake steering methods rely on lookup tables obtained offline, which map a set of conditions, such as wind speed and direction, to yaw angles for each turbine in a farm. These tables assume all turbines are operational and can be significantly non–optimal when one or more turbines do not provide the rated power, because of low wind speed, faults, routine maintenance, or emergency maintenance. This work presents an intelligent wake steering method that adapts to turbine actual working conditions when determining yaw angles. Using a hybrid model–and a learning–based method, i.e. an active control, a neural network is trained online to determine yaw angles from operating conditions including turbine status. Unlike purely model–based approaches which use lookup tables provided by the wind turbine manufacturer or generated offline, the proposed control solution does not need to solve e.g. optimisation problems for each combination of the turbine non-optimal working conditions in a farm; the integration of learning strategy in the control design allows to obtain an active control scheme.
2023
Intelligent Computing SAI 2023, Lecture Notes in Networks and Systems
53
61
Simani S., Farsoni S., Castaldi P. (2023). Data–Driven Design of an Active Wake Steering Control for a Wind Farm Benchmark. Berlin : Springer Science and Business Media Deutschland GmbH [10.1007/978-3-031-37963-5_5].
Simani S.; Farsoni S.; Castaldi P.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/958824
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact