Control of a Wind-Turbine via Machine Learning techniques

TL;DR

This paper introduces two model-free controllers for wind-turbine management using reinforcement learning and Bayesian optimization, outperforming classical PID controllers in simulations by increasing power output and reducing loads.

Contribution

It presents novel model-free control strategies for wind turbines that do not depend on mathematical models of turbine dynamics.

Findings

Model-free controllers outperform PID in simulations.

Power harvesting is increased with reduced loads.

Controllers are based on RL and BO techniques.

Abstract

This article presents two model-free controllers for wind-turbine torque and pitch control. These controllers are based on reinforcement learning (RL) and Bayesian optimization (BO) and do not rely on any mathematical model of the wind-turbine dynamics, in contrast to classical approaches designed on linearized models. The model-free controllers were benchmarked against a proportional-integral-derivative (PID) regulator in a numerical environment using Blade Element Momentum theory for computing the aerodynamic torque and the blade loads. The results showed that the model-free approaches could increase power harvesting while reducing wind turbine loads.