Model Predictive HVAC Control with Online Occupancy Model

This paper presents an occupancy-predictive control method for heating, ventilation, and air conditioning (HVAC) systems in buildings that incorporates the building’s thermal properties, local weather predictions, and a self-tuning stochastic occupancy model to reduce energy consumption while maintaining occupant comfort. Contrasting with existing approaches, its occupancy model requires no manual tuning and adapts to changes in occupancy patterns during operation. A prediction-weighted cost function provides preconditioning of thermal zones before occupancy begins and reduces system output before occupancy ends. Simulation results with conference room occupancy data demonstrate its effectiveness.