Real-time wave energy control based on machine learning
Liang Li, University of Strathclyde
A controller is usually used to increase the power extraction of wave energy converters. Despite the development of various control strategies, the practical implementation of wave energy control is still difficult since the control inputs are the future wave forces. In this work, the artificial intelligence technique is adopted to tackle this problem. A multi-layer artificial neural network is developed and trained by the machine learning algorithm to forecast the future wave forces. The receding horizon strategy is used to implement control online. Analysis results show that the power extraction is increased substantially with the smart controller. The prediction error is quantified, and its influence on power extraction is examined. The wave force phase error leads to a substantial reduction of power extraction, whereas the effect of wave force amplitude error is nearly negligible.