WACE - Wave energy AI-based Control Enhancement

Important results from the project

The goal of this project was to achieve a performance improvement of a wave energy converter using reinforcement learning to enhance CorPower Ocean’s proprietary control strategy. The strategy was efficiently implemented using open-source software packages developed by the University of Freiburg and the Norwegian University of Science and Technology (NTNU). The resulting controller demonstrated measurable gains in energy capture and robustness across varying operating conditions.

Expected long term effects

This project has achieved a significant performance improvement in terms of wave energy capture across multiple WEC operating conditions, verified through model-in-the-loop testing. Further work is required before full-implementation in the WEC but it is clear that this approach offers a promising way to reduce the levelised cost of energy of WECs which in turn will accelerate the commercialization of wave energy and helping decarbonize energy systems worldwide.

Approach and implementation

The development of the AI‑enhanced control strategy was organized into four work packages. The project began by defining control system requirements and establishing a shared GitLab environment to support collaboration and version control. The main objective of improving an existing MPC strategy using RL was achieved and demonstrated through MIL testing. Regular follow‑up meetings throughout the project ensured continuous coordination between the partners.