Model predictive control for energy-efficient buildings: An airport terminal building study

Heating, ventilation, and air conditioning (HVAC) systems in commercial buildings consume a large proportion of energy in the world. One possible way to reduce the cost is to optimize HVAC operation through predictive control methods. Such approaches rely on dynamic models to meet comfort constraints and to minimize energy usage. In this paper, we employ two different model types: an resistance-capacitance (R-C) network model and an artificial neural network (ANN) model, in order to model thermal dynamics of an airport terminal building. The R-C model serves as a control model and its parameters are identified using a gray box identification technique. The ANN model is built in recursive form and works as a simulator to provide system feedback to the controller. We implement a model predictive control (MPC) with two supervisory scenarios on such a simulation environment to evaluate their energy- saving potential. Simulation results during cooling season show 5% to 18% of daily energy savings can be achieved when the proposed MPC is applied to the building.