Simplified data-driven models for model predictive control of residential buildings

Owing to recent advancements in Internet of Things technologies, data-driven model predictive control (MPC) has received significant research interest as a promising strategy to optimize building operation. As the MPC performance relies on the model prediction accuracy, complex building prediction models have been used in MPC applications, despite their high computational cost for optimization. This study examines whether linear-form prediction models are reliable to support the MPC of residential buildings equipped with single types of heating systems. This study developed linear-form models, namely an autoregressive with exogenous inputs (ARX) for predicting the indoor temperature and threshold-piecewise models for the return and supply water temperatures. The MPC performance on the basis of the linear models was evaluated under varying prediction horizons and weights associated with objective attributes. A case study of a residential unit through the simulated virtual building showed that the proposed models achieved the high goodness-of fit values greater than 0.9. The resulting MPC framework achieved heating energy savings up to approximately 12% relative to a simple on/off thermostat or reduction of comfort violation magnitude less than 0.5 °C. The influences of weight and prediction horizon on MPC performance were also investigated.