Load constrained wind farm flow control through multi-objective multi-agent reinforcement learning

TL;DR

This paper develops a multi-agent reinforcement learning framework for wind farm flow control that maximizes power output while limiting structural loads, using real-time damage estimates and a sophisticated simulation environment.

Contribution

It introduces an integrated MARL approach with a surrogate model for load estimation, enabling load-constrained wind farm control in a realistic simulation setting.

Findings

MARL agents learn to balance power gain and load constraints effectively.

The framework successfully limits DELs while improving power output.

Agents adapt their strategies to avoid high-DEL control actions.

Abstract

This study presents a multi-agent reinforcement learning (MARL) framework for load-constrained wind farm flow control (WFFC). While wake steering can enhance total wind farm power, it often introduces increased structural loads on downstream turbines. To address this, we integrate an Independent Soft Actor-Critic (I-SAC) architecture with a data-driven, local inflow sector-averaged surrogate model to provide real-time estimates of Damage Equivalent Loads (DELs). By incorporating these estimates into a shaped reward function, turbine-specific agents are trained to maximize power production while adhering to specific load-increase thresholds ($\Delta_{max}$) of 10%, 20%, and 30% relative to a baseline controller. The framework is implemented within the WindGym environment using the DYNAMIKS flow solver with Dynamic Wake Meandering (DWM) model to capture non-stationary wake physics. Results indicate that the MARL agents successfully learn collaborative policies that prioritise power gain while actively retreating from high-DEL control strategies.