A Simulation Study on Energy Optimization in Building Control with Reinforcement Learning

Peter Bolt, Volker Ziebart, Christian Jaeger, Nicolas Schmid, Thilo Stadelmann, Rudolf M. Füchslin

Abstract: We propose and evaluate a deep reinforcement learning control paradigm for building energy systems. In comparison to other advanced control techniques, namely Model Predictive Control, the reinforcement learning paradigm avoids the costs and uncertainties associated with the requirement for a control-oriented model. We apply a mixed agent for the Proximal Policy Optimization algorithm, similar to the algorithm proposed in [7] as well as a non-discounted finite horizon optimization scheme.