LAUSR

To optimize the operation of a heating, ventilation, and air-conditioning (HVAC) system with advanced techniques such as artificial neural network (ANN), previous studies usually need forecast information in their method. However, the forecast information inevitably contains errors all the time, which degrade the performance of the HVAC operation. Hence, in this study, we propose a mixed-integer linear programming (MILP)-based imitation learning method to control an HVAC system without using the forecast information in order to reduce energy cost and maintain thermal comfort at a given level. Our proposed controller is a deep neural network (DNN) trained by using data labeled by an MILP solver with historical data. After training, our controller is used to control the HVAC system with real-time data. For comparison, we develop two different methods named forecast-based MILP method and model predictive control (MPC) method which control the HVAC system using the forecast information and a deep reinforcement learning (RL) method which controls HVAC using the real-time data. The performance of the four methods is verified by using real outdoor temperatures and real day-ahead prices in Detroit city, MI, USA. Numerical results clearly show that the performance of the MILP-based imitation learning is better than that of other methods in terms of hourly power consumption, daily energy cost, and thermal comfort. Moreover, the difference between the results of the MILP-based imitation learning method and optimal results is almost negligible. These optimal results are achieved only by using the MILP solver at the end of the day when we have full information on the weather and prices for the day.