Deep Reinforcement Learning Control to Maximize Output Energy for a Wave Energy Converter
Open Access
- 1 January 2020
- journal article
- research article
- Published by Japan Society of Naval Architects and Ocean Engineers in Journal of the Japan Society of Naval Architects and Ocean Engineers
- Vol. 31, 229-238
Abstract
This paper presents a deep reinforcement learning control method to maximize output energy for a point absorber type wave energy converter (WEC) with a linear generator. Conventional control methods require the dynamic model of the WEC. Modeling errors of the dynamic model, however, make energy absorption smaller and cause incorrect control. The proposed method, which is a model-free control method learns the optimal damping and stiffness coefficients based on experiences. In the proposed control method, damping and stiffness coefficients are able to vary in time-domain depending on the incident waves by deep reinforcement learning. The performance of the proposed control method is investigated through numerical simulation in both regular and irregular waves. Compared with the conventional control method, averaged output power increased, and the power fluctuation decreased without the dynamic model. It is understood that the proposed method is more effective than the conventional control method.Keywords
This publication has 8 references indexed in Scilit:
- Power Production Efficiency Improvement of a Point Absorber Type Wave Energy Converter by Model Predictive ControlJournal of the Japan Society of Naval Architects and Ocean Engineers, 2019
- Study on Model Predictive Control for the Wave Energy Converter with a Linear GeneratorJournal of the Japan Society of Naval Architects and Ocean Engineers, 2018
- Experimental and Numerical Study on Point Absorber Type Wave Energy Converter With Linear Generator2017
- Constraints Implementation in the Application of Reinforcement Learning to the Reactive Control of a Point Absorber2017
- Control of a Realistic Wave Energy Converter Model Using Least-Squares Policy IterationIEEE Transactions on Sustainable Energy, 2017
- Experimental Validation of a Nonlinear MPC Strategy for a Wave Energy Converter Prototype2016
- Maximizing output power of linear generators for wave energy conversionInternational Transactions on Electrical Energy Systems, 2013
- Ocean Waves and Oscillating Systems2002