Online transfer learning for climate control in residential buildings

Autoren Thomas Grubinger
Georgios C. Chasparis
Thomas Natschläger
Editoren
TitelOnline transfer learning for climate control in residential buildings
BuchtitelProceedings of the 5th Annual European Control Conference (ECC'16)
Typin Konferenzband
VerlagEUCA
ISBN978-1-5090-2590-9
MonatJune
Jahr2016
Seiten1183-1188
SCCH ID#1574
Abstract

This paper presents an online transfer learning framework for improving temperature predictions in residential buildings. In transfer learning, prediction models trained under a set of available data from a target domain (e.g., house with limited data) can be improved through the use of data generated from similar source domains (e.g., houses with rich data). Given also the need for prediction models that can be trained online (e.g., as part of a model-predictive-control implementation), this paper introduces generalized online transfer learning algorithm (GOTL). It employs a weighted combination of the available predictors (i.e., the target and source predictors) and guarantees convergence to the best weighted predictor. We further validate our results through experiments in climate control for residential buildings.