Exploring Reward Strategies for Wind Turbine Pitch Control by Reinforcement Learning
Open Access
- 23 October 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (21), 7462
- https://doi.org/10.3390/app10217462
Abstract
In this work, a pitch controller of a wind turbine (WT) inspired by reinforcement learning (RL) is designed and implemented. The control system consists of a state estimator, a reward strategy, a policy table, and a policy update algorithm. Novel reward strategies related to the energy deviation from the rated power are defined. They are designed to improve the efficiency of the WT. Two new categories of reward strategies are proposed: “only positive” (O-P) and “positive-negative” (P-N) rewards. The relationship of these categories with the exploration-exploitation dilemma, the use of ϵ-greedy methods and the learning convergence are also introduced and linked to the WT control problem. In addition, an extensive analysis of the influence of the different rewards in the controller performance and in the learning speed is carried out. The controller is compared with a proportional-integral-derivative (PID) regulator for the same small wind turbine, obtaining better results. The simulations show how the P-N rewards improve the performance of the controller, stabilize the output power around the rated power, and reduce the error over time.This publication has 35 references indexed in Scilit:
- Simulation of a Fuzzy Control Applied to a Variable Speed Wind System Connected to the Electrical NetworkIEEE Latin America Transactions, 2018
- Hybrid Genetic Algorithm Fuzzy-Based Control Schemes for Small Power System with High-Penetration Wind FarmsApplied Sciences, 2018
- Adaptive neuro-fuzzy algorithm to estimate effective wind speed and optimal rotor speed for variable-speed wind turbineNeurocomputing, 2018
- Experiments of conditioned reinforcement learning in continuous space control tasksNeurocomputing, 2018
- Variable speed wind turbine controller adaptation by reinforcement learningIntegrated Computer-Aided Engineering, 2016
- Reinforcement learning for microgrid energy managementEnergy, 2013
- Electric grid dependence on the configuration of a small-scale wind and solar power hybrid systemRenewable Energy, 2013
- Dyna-: A heuristic planning reinforcement learning algorithm applied to role-playing game strategy decision systemsKnowledge-Based Systems, 2012
- Modelado y Simulación de un Sistema Conjunto de Energía Solar y Eólica para Analizar su Dependencia de la Red EléctricaRevista Iberoamericana de Automática e Informática Industrial, 2012
- Review of wind turbine controlInternational Journal of Control, 1990