A Transfer Learning Approach to Minimize Reinforcement Learning Risks in Energy Optimization for Smart Buildings
This addresses the risk of RL deployment in energy optimization for smart buildings, offering a domain-specific solution to reduce initial discomfort for residents.
The paper tackles the problem of deploying reinforcement learning (RL) for energy optimization in smart buildings without historical data, which risks discomfort during the agent's warm-up period, by introducing ReLBOT, a transfer learning approach that reduces the warm-up duration by up to 6.2 times and prediction variance by up to 132 times.
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 6.2 times in the duration, and up to 132 times in prediction variance, for the reinforcement learning agent's warm-up period.