Control of a Point Absorber Using Reinforcement Learning

@article{Anderlini2016ControlOA,
title={Control of a Point Absorber Using Reinforcement Learning},
author={Enrico Anderlini and David I. M. Forehand and Paul Stansell and Qing Xiao and Mohammad A. Abusara},
journal={IEEE Transactions on Sustainable Energy},
year={2016},
volume={7},
pages={1681-1690}
}

Published 2016 in IEEE Transactions on Sustainable Energy

This work presents the application of reinforcement learning for the optimal resistive control of a point absorber. The model-free Q-learning algorithm is selected in order to maximise energy absorption in each sea state. Step changes are made to the controller damping, observing the associated penalty, for excessive motions, or reward, i.e. gain in associated power. Due to the general periodicity of gravity waves, the absorbed power is averaged over a time horizon lasting several wave periods… CONTINUE READING