Contingency-constrained economic dispatch with safe reinforcement learning
This addresses the safety-critical deployment of RL controllers in power systems, which is an incremental improvement for ensuring reliability in micro grids with high renewable energy integration.
The paper tackles the problem of ensuring safety in reinforcement learning controllers for economic dispatch in power systems with renewable energy sources, proposing a formally validated RL controller that uses set-based backwards reachability analysis and a safety layer to project unsafe actions into a safe space, achieving computational efficiency with constrained zonotope set representations and demonstrating it on a residential use case with real-world measurements.
Future power systems will rely heavily on micro grids with a high share of decentralised renewable energy sources and energy storage systems. The high complexity and uncertainty in this context might make conventional power dispatch strategies infeasible. Reinforcement-learning based (RL) controllers can address this challenge, however, cannot themselves provide safety guarantees, preventing their deployment in practice. To overcome this limitation, we propose a formally validated RL controller for economic dispatch. We extend conventional constraints by a time-dependent constraint encoding the islanding contingency. The contingency constraint is computed using set-based backwards reachability analysis and actions of the RL agent are verified through a safety layer. Unsafe actions are projected into the safe action space while leveraging constrained zonotope set representations for computational efficiency. The developed approach is demonstrated on a residential use case using real-world measurements.