Abstract
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 unfavorable conditions for learning. Similar performance is observed for both basis functions, with a smaller number of radial basis functions underfitting the Q-function. The shorter learning time is fundamental for a practical application on 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 modeling 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.
Highlights
W AVE energy has the potential to become a significant contributor to the future energy mix thanks to a resource of up to 2.1 TW of power worldwide [1], with a consequent reduction in greenhouse gas emissions
The design of an effective control scheme can considerably reduce the levelised cost of energy associated with wave energy converters (WECs), since it can bring about a gain in energy absorption with little additional hardware costs
An efficient reinforcement learning (RL) algorithm has been suggested for the control of a WEC, with its performance being compared with Qlearning and SARSA
Summary
W AVE energy has the potential to become a significant contributor to the future energy mix thanks to a resource of up to 2.1 TW of power worldwide [1], with a consequent reduction in greenhouse gas emissions. The design of an effective control scheme can considerably reduce the levelised cost of energy associated with WECs, since it can bring about a gain in energy absorption with little additional hardware costs. By achieving resonance between the device and the incident waves, complex-conjugate control would result theoretically in optimal power absorption [3]. This is infeasible in practice because of the resulting large motions of the WEC in energetic sea states and the associated high loads. Alternative control algorithms have been developed, which limit the motions, forces and power ratings of the device [4]. It is possible to differentiate between two main types of control schemes: time-averaged and real-time
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
