Generalized Online Transfer Learning for Climate Control in Residential Buildings

TL;DR

This paper introduces GOTL, a novel online transfer learning algorithm that combines multiple source domains to improve temperature prediction and energy efficiency in residential building climate control.

Contribution

The paper proposes GOTL, a generalized online transfer learning algorithm that integrates multiple source domains and guarantees convergence, enhancing predictive accuracy and energy savings.

Findings

GOTL improves temperature prediction accuracy.

GOTL achieves energy savings in climate control.

Using multiple sources enhances model robustness.

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 the 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. Furthermore, the use of Transfer Component Analysis (TCA) allows for using more than a single source domains, since it may facilitate the fit of a single model on more than one source domains (houses). This allows GOTL to transfer knowledge from more than one source domains. We further validate our results through experiments in climate control for residential buildings and show that GOTL may lead to non-negligible energy savings for given comfort levels.