Learning the optimal power flow: Environment design matters
Thomas Wolgast, Astrid Nieße
Abstract
To solve the optimal power flow (OPF) problem, reinforcement learning (RL) emerges as a promising new approach. However, the RL-OPF literature is strongly divided regarding the exact formulation of the OPF problem as an RL environment. In this work, we collect and implement diverse environment design decisions from the literature regarding training data, observation space, episode definition, and reward function choice. In an experimental analysis, we show the significant impact of these environment design options on RL-OPF training performance. Further, we derive some first recommendations regarding the choice of these design decisions. The created environment framework is fully open-source and can serve as a benchmark for future research in the RL-OPF field. • The Optimal Power Flow can be solved with Reinforcement Learning. • Literature is strongly divided regarding its formulation as a learning environment. • Systematic experiments with diverse design options from literature. • The environment design decisions impact training performance drastically. • Recommendations on how to design Optimal Power Flow environments.