The increasing demand for flexibility in hydropower systems requires pumped storage power plants to change operating modes and compensate reactive power more frequently. In this work, we demonstrate the potential of applying reinforcement learning (RL) to control the blow-out process of a hydraulic machine during pump start-up and when operating in synchronous condenser mode. Even though RL is a promising method that is currently getting much attention, safety concerns are stalling research on RL for the control of energy systems. Therefore, we present a concept that enables process control with RL through the use of a digital twin platform. This enables the safe and effective transfer of the algorithm’s learning strategy from a virtual test environment to the physical asset. The successful implementation of RL in a test environment is presented and an outlook on future research on the transfer to a model test rig is given.

This study introduces DigiWind, an extensible digital twin platform specifically designed for the wind energy domain. The research aims to identify the fundamental requirements and architectural design for such a platform. Functional requirements are identified through a requirements engineering process using the use-case methodology. Existing digital twin and co-simulation platforms are reviewed, and the proposed DigiWind architecture is presented in detail. Three use cases are presented to highlight the integration of workflows and simulation models in the digital twin process. The DigiWind platform features a layered architecture with core implementations such as the template service, model assembly service, co-simulation service, and measurement data service. These components enable the automation of simulations, incorporation of historic measurement data, and data feedback and exchange. The platform supports various use cases including retrospective evaluation, performance monitoring, and scenario simulations. Additionally, a knowledge base and a versioning system ensure automation, documentation, and reproducibility of simulation results. The platform’s openness promotes collaboration among wind energy stakeholders and supports standardized models for co-simulation using the Functional Mock-up Interface. Overall, DigiWind offers a solution for developing, managing, and integrating digital twins in the wind energy sector, enhancing wind farm performance and operational efficiency.

Reinforcement learning (RL) offers a promising framework for controlling transient processes in hydraulic machines. In this study, we apply RL to the start-up control of a reversible pump-turbine in a simulation of a pumped storage power system. A physics-based simulation environment capturing the system’s key hydraulic and mechanical dynamics is developed to train a Proximal Policy Optimization agent. Compared to a conventional control approach, the RL-based policy yields a higher cumulative reward in simulation by significantly reducing start-up time and cumulative operational cost. The approach demonstrates the potential of RL in a simulated pump start-up case, highlighting its ability to autonomously discover efficient control strategies for highly dynamic processes, such as pump start-up, without relying on predefined procedural logic. Future work includes experimental validation on a laboratory-scale pump-turbine to further investigate the policy’s performance under real-world conditions.