Deep Reinforcement Learning Based Energy Management Strategy For Commercial Buildings Considering Comprehensive Comfort Levels

More than 30% of the total energy generated all over the world are consumed by buildings. Among it, 40% are consumed by commercial buildings which are great candidates to perform energy management strategy. Nonetheless, comfort levels of the occupants in the commercial building always have higher priority comparing to the energy-consuming cost, especially during the business hours. As a result, coordinating the operation of large appliances and other major components in commercial buildings needs a novel energy management strategy, which provides a trade-off between the comfort level and building operation cost. In this paper, we develop a deep reinforcement learning-based control strategy to determine optimal actions for major components in a commercial building to minimize operation costs while maximizing comprehensive comfort levels of occupants. An unsupervised deep Q-network method is introduced to handle the energy management problem by evaluating the influence of operation costs on comfort levels considering the environment factors at each time slot. An optimum control decision can be derived that targets both immediate and long-term goals, where exploration and exploitation are considered simultaneously. Extensive simulation results show that the proposed deep reinforcement learning-based energy management strategy is capable of both minimizing operation and maintenance costs and maximizing comprehensive comfort levels of occupants.