A transfer learning approach to minimize reinforcement learning risks in energy optimization for automated and smart buildings.

Energy optimization leveraging artificially intelligent algorithms has been proven effective. However, when buildings are commissioned, there is no historical data that could be used to train these algorithms. On-line Reinforcement Learning (RL) algorithms have shown significant promise, but their deployment carries a significant risk, because as the RL agent initially explores its action space it could cause significant discomfort to the building residents. In this paper we present ReLBOT – a new technique that uses transfer learning in conjunction with deep RL to transfer knowledge from an existing, optimized and instrumented building, to the newly commissioning smart building, to reduce the adverse impact of the reinforcement learning agent's warm-up period. We demonstrate improvements of up to 84% (40% average) in the duration, and up to 99% (62% average) in prediction variance, for the reinforcement learning agent's warm-up period. RL agent's prediction accuracy improved by up to 4% (1% average). • The first similarity-informed transfer learning method to implement reinforcement learning for building energy optimization. • Warm-up period duration reduced by up to 84% (40% average). • Prediction variance reduced by up to 99% (62% average). • RL agent's prediction accuracy improved by up to 4% (1% average). [ABSTRACT FROM AUTHOR]