Reinforcement learning-based pitch control for wind turbines using double deep q-networks

This paper presents a novel reinforcement learning-based framework for pitch control in wind turbines, addressing the challenges posed by high nonlinearity and uncertainties in wind dynamics. Traditional pitch control methods, such as proportional-integral controllers, often struggle with adaptabili...

Descripción completa

Detalles Bibliográficos
Autores: Espinoza, Víctor, Ormaza, Carolina, Tutivén Gálvez, Christian|||0000-0001-6322-4608, Vidal Seguí, Yolanda|||0000-0003-4964-6948
Tipo de recurso: artículo
Fecha de publicación:2026
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/454077
Acceso en línea:https://hdl.handle.net/2117/454077
https://dx.doi.org/10.1016/j.isatra.2026.01.015
Access Level:acceso abierto
Palabra clave:Pitch control
Reinforcement learning
Double deep Q-network
OpenFAST
ROSCO
Àrees temàtiques de la UPC::Energies::Energia eòlica::Aerogeneradors
Descripción
Sumario:This paper presents a novel reinforcement learning-based framework for pitch control in wind turbines, addressing the challenges posed by high nonlinearity and uncertainties in wind dynamics. Traditional pitch control methods, such as proportional-integral controllers, often struggle with adaptability and load mitigation under fluctuating wind conditions. To enhance control efficiency, the proposed framework employs a two-stage approach: policy transfer and policy refinement. In the policy transfer stage, a proportional-integral controller is used to estimate an initial control policy. This policy is then refined using the double deep Q-Network algorithm. Furthermore, a novel reward function is introduced as an improved version of a recent formulation in the literature, ensuring better alignment with practical operational scenarios. Simulations demonstrate that the proposed controller outperforms the industry-standard ROSCO controller, achieving a 15.87% reduction in power fluctuations, while preserving comparable structural load levels, with slight reductions in some cases. These results highlight the potential of reinforcement learning-based control to enhance wind turbine power regulation without compromising structural safety in terms of loads and vibrations.