Reinforcement learning-based real-time control of a reversible pump turbine for reduced response time in pumped hydropower

This paper investigates reinforcement learning (RL) for real-time control of a reversible pump turbine in pumped hydropower systems. Although RL shows strong potential for adaptive control, its adoption in safety-critical energy systems remains limited by challenges in training, deployment, and trust. To address these, a digital twin–based framework enables safe offline training, structured validation, and controlled simulation-to-real transfer of a Proximal Policy Optimization agent. The learned policy is distilled into an interpretable rule-based surrogate for experimental deployment. Validation on a 400 kW laboratory-scale pump turbine shows that the RL-derived strategy reduces start-up time by over 30% compared to a conventional control approach, achieving faster synchronization and earlier target discharge. The results underline RL’s capacity to discover efficient, non-intuitive control strategies while revealing key limits in sim-to-real transfer due to model errors and delays. Overall, the work establishes a systematic methodology for integrating RL into safety-critical energy control—bridging adaptive learning with physically interpretable and verifiable operation. • Reinforcement learning is applied to unit-level control of a pump turbine. • A digital twin enables safe training and sim-to-real deployment of reinforcement learning control. • Reinforcement learning reduces pump start-up time by over 30% in laboratory experiments. • A rule-based surrogate improves safety and interpretability of RL policies. • Experimental results reveal key challenges in sim-to-real transfer for energy systems.