Online building thermal parameter estimation via Unscented Kalman Filtering

Abstract

This study demonstrates how an Unscented Kalman Filter augmented for parameter estimation can accurately learn and predict a building's thermal response. Recent studies of buildings' heating, ventilating, and air-conditioning systems have shown 25% to 30% energy conservation is possible with advanced occupant and weather responsive control systems. Hindering the widespread deployment of such prediction-based control systems is an inability to readily acquire accurate, robust models of individual buildings' unique thermal envelope. Low-cost generation of these thermal models requires deployment of online data-driven system identification and parameter estimation routines. We propose a novel gray-box approach using an Unscented Kalman Filter based on a multi-zone thermal network and validate it with EnergyPlus simulation data. The filter quickly learns parameters of a thermal network during periods of known or constrained loads and then characterizes unknown loads in order to provide accurate 48+ hour energy predictions. Besides enabling advanced controllers, the model and predictions could provide useful analysis, monitoring, and fault detection capabilities.