Safe Reinforcement Learning for Community Energy Systems
Abstract
Community energy systems, where neighbouring households share solar generation, batteries and electric-vehicle charging, could cut emissions and bills substantially. Coordination is difficult: demand depends on how people behave, data is spread across homes, and a controller that misbehaves can damage equipment or the local grid. Reinforcement learning (RL), i.e. learning control strategies from experience, is a natural candidate, but it offers few guarantees of safe behaviour. This project will develop RL methods that carry control-theoretic safety certificates and that explicitly account for how residents respond to prices and recommendations. Applicants from control, machine learning or applied mathematics are welcome.
How to Apply
Please contact Dr Pietro Ferraro if you are interested in applying for this project.
For more information on submitting a PhD application, please consult our application pages here. When you submit your application, please cite this project title in the 'how you are planning to fund your PhD' section.
The deadline for submitting your application is 11 January 2027.