RT info:eu-repo/semantics/article
T1 Wind turbine pitch reinforcement learning control improved by PID regulator and learning observer
A1 Sierra Garcia, Jesús Enrique
A1 Santos, Matilde
A1 Pandit, Ravi
K1 Intelligent control
K1 Reinforcement learning
K1 Learning observer
K1 Pitch control
K1 Wind turbines
K1 Electrotecnia
K1 Electrical engineering
AB Wind turbine (WT) pitch control is a challenging issue due to the non-linearities of the wind device and itscomplex dynamics, the coupling of the variables and the uncertainty of the environment. Reinforcement learn-ing (RL) based control arises as a promising technique to address these problems. However, its applicabilityis still limited due to the slowness of the learning process. To help alleviate this drawback, in this work wepresent a hybrid RL-based control that combines a RL-based controller with a proportional–integral–derivative(PID) regulator, and a learning observer. The PID is beneficial during the first training episodes as the RL basedcontrol does not have any experience to learn from. The learning observer oversees the learning process byadjusting the exploration rate and the exploration window in order to reduce the oscillations during the trainingand improve convergence. Simulation experiments on a small real WT show how the learning significantlyimproves with this control architecture, speeding up the learning convergence up to 37%, and increasing theefficiency of the intelligent control strategy. The best hybrid controller reduces the error of the output powerby around 41% regarding a PID regulator. Moreover, the proposed intelligent hybrid control configuration hasproved more efficient than a fuzzy controller and a neuro-control strategy.
PB Elsevier
SN 0952-1976
YR 2022
FD 2022-05
LK http://hdl.handle.net/10259/7421
UL http://hdl.handle.net/10259/7421
LA eng
NO This work was partially supported by the Spanish Ministry of Sci- ence, Innovation and Universities under MCI/AEI/FEDER Project num- ber RTI2018-094902-B-C21.
DS Repositorio Institucional de la Universidad de Burgos
RD 11-dic-2024