Photo: Carnegie’s CETO 6 wave energy technology concept (Courtesy of Carnegie Clean Energy)

Carnegie inks deal with Hewlett Packard Enterprise for CETO wave controls

Carnegie Clean Energy has signed a collaboration agreement with Hewlett Packard Enterprise (HPE) to work together on a project to develop a reinforcement learning based controller for the CETO wave energy technology.

An image of Carnegie’s CETO 6 wave energy technology concept (Courtesy of Carnegie Clean Energy)
Carnegie’s CETO 6 wave energy technology concept (Courtesy of Carnegie Clean Energy)

The work will extend the artificial intelligence development already underway at Carnegie as part of Microsoft AI for Earth initiative for which the company recently received a grant end of October 2020.

Related Article

Posted: 5 months ago

Carnegie lands Microsoft AI for Earth grant

Categories:
  • Business developments & projects
Posted: 5 months ago

Hewlett Packard Labs will contribute their reinforcement learning (RL) expertise and computational resources to the project, working alongside Carnegie’s team, which is already developing an intelligent controller for the CETO technology.

The RL based controller development in this project will occur in parallel with, and provide an opportunity to enhance, the Carnegie team’s ongoing work on a machine learning (ML) based intelligent controller.

Reinforcement learning is an area of artificial intelligence in which a machine learning model is built with the ability to self-learn.

While the intelligent controller currently under development has to optimise the device’s response for every wave (using ML models within the optimisation), the RL controller has the ability to directly learn and apply the optimum response to predicted waves, during operation, according to Carnegie.

The RL controller, which comes pre-loaded with a simple control scheme, explores away from this reference using the concept of reward to identify and learn good control actions.

What this means for wave energy is that a RL based controller can move beyond optimising CETO’s response using an ML model of the system trained on simulated data.

An RL based controller can actively adjust, experiment, learn and optimise by utilising what actually happens during operations. Initially, Carnegie envisions that a RL based controller would likely use a power-output-based reward to learn optimum operation, the company said.

Over time, the controller could become more advanced and could ultimately use a reward based on Levelised Cost of Energy (LCOE), thereby incorporating a range of variables into its operation (including not only energy production but also elements of operations and maintenance costs such as fatigue, avoiding large damaging waves, and even commercial considerations.)

“The teams at Carnegie and HPE look forward to working together to pursue this exciting innovation which has the potential to improve the performance and reduce the cost of the CETO technology and revolutionise control of wave energy converters”, Carnegie said.