Treffer: Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems

The ongoing energy transition drives the development of decentralisedrenewable energy sources, which are heterogeneous and weather-dependent,complicating their integration into energy systems. This study tackles thisissue by introducing a novel reinforcement learning (RL) framework tailored forthe co-optimisation of design and control in energy systems. Traditionally, theintegration of renewable sources in the energy sector has relied on complexmathematical modelling and sequential processes. By leveraging RL's model-freecapabilities, the framework eliminates the need for explicit system modelling.By optimising both control and design policies jointly, the framework enhancesthe integration of renewable sources and improves system efficiency. Thiscontribution paves the way for advanced RL applications in energy management,leading to more efficient and effective use of renewable energy sources.