As global energy demands and climate concerns continue to grow, the need for renewable energy is becoming increasingly clear and wave energy converter
(WEC) systems are receiving growing interest. WECs often utilize optimal control techniques for power take-off operation and leverage a prediction of the upcoming wave force to ensure power production optimization. Prior work has clearly demonstrated that high power production can be achieved when an exact system model is used and the upcoming wave conditions are known, but uncertainty in the underlying model or the wave prediction can degrade performance. The uncertainty in these predictions and the model could degrade the WEC’s power output. This work examines the impact of uncertainty on the control of a WEC system that leverages machine learning to predict wave forces over the upcoming time horizon. This paper quantifies wave prediction uncertainty and its seasonal variation and illustrates that this uncertainty may only minimally degrade power output on complex multi-axis WECs due to the strong influence of constraints in the system.
