|Anderlini, E., Forehand, D.I.M., Bannon, E. and Abusara, M. Control of a Realistic Wave Energy Converter Model Using Least-Squares Policy Iteration, IEEE Transactions on Sustainable Energy, 8 (4): 1618 - 1628, 2017. https://doi.org/10.1109/TSTE.2017.2696060. Cite this using DataCite
|An algorithm has been developed for the resistive control of a nonlinear model of a wave energy converter using least-squares policy iteration, which incorporates function approximation, with tabular and radial basis functions being used as features. With this method, the controller learns the optimal power take-off damping coefficient in each sea state for the maximization of the mean generated power. The performance of the algorithm is assessed against two online reinforcement learning schemes: Q-learning and SARSA. In both regular and irregular waves, least squares policy iteration outperforms the other strategies, especially when starting from unfavourable conditions for learning. Similar performance is observed for both basis functions, with a smaller number of radial basis functions under-fitting the Q-function. The shorter learning time is fundamental for a practical applicationon a real wave energy converter. Furthermore, this paper shows that least-squares policy iteration is able to maximize the energy absorption of a wave energy converter despite strongly nonlinear effects due to its model-free nature, which removes the influence of modelling errors. Additionally, the floater geometry has been changed during a simulation to show that reinforcement learning control is able to adapt to variations in the system dynamics.
This work was partly funded via IDCORE, the Industrial Doctorate Centre for Offshore Renewable Energy, which trains research engineers whose work in conjunction with sponsoring companies aims to accelerate the deployment of offshore wind, wave and tidal-current technologies