ARX Model of a Residential Heating System With Backpropagation Parameter Estimation Algorithm

Model predictive control (MPC) strategies hold great potential for improving the performance and energy efficiency of building heating, ventilation, and air-conditioning (HVAC) systems. A challenge in the deployment of such predictive thermo-static control systems is the need to learn accurate models for the thermal characteristics of individual buildings. This necessitates the development of online and data-driven methods for system identification. In this paper, we propose an autoregressive with exogenous terms (ARX) model of a thermal zone within a building. To learn the model, we present a backpropagation approach for recursively estimating the parameters. Finally, we fit the linear model to data collected from a residential building with a forced-air heating and ventilation system and validate the accuracy of the trained model.