Identifying Grey-box Thermal Models with Bayesian Neural Networks

TL;DR

This paper demonstrates that Bayesian neural networks can effectively identify grey-box thermal models from smart thermostat data, enabling quick, accurate, and adaptable temperature predictions across homes and seasons.

Contribution

It introduces a Bayesian neural network approach for thermal model identification that outperforms black-box models and enables rapid adaptation to new homes and seasonal changes.

Findings

Bayesian neural networks improve temperature prediction accuracy.

Pre-trained models can be adapted for similar homes quickly.

Short-term data enhances seasonal model transferability.

Abstract

Smart thermostats are one of the most prevalent home automation products. They learn occupant preferences and schedules, and utilize an accurate thermal model to reduce the energy use of heating and cooling equipment while maintaining the temperature for maximum comfort. Despite the importance of having an accurate thermal model for the operation of smart thermostats, fast and reliable identification of this model is still an open problem. In this paper, we explore various techniques for establishing a suitable thermal model using time series data generated by smart thermostats. We show that Bayesian neural networks can be used to estimate parameters of a grey-box thermal model if sufficient training data is available, and this model outperforms several black-box models in terms of the temperature prediction accuracy. Leveraging real data from 8,884 homes equipped with smart thermostats, we discuss how the prior knowledge about the model parameters can be utilized to quickly build an accurate thermal model for another home with similar floor area and age in the same climate zone. Moreover, we investigate how to adapt the model originally built for the same home in another season using a small amount of data collected in this season. Our results confirm that maintaining only a small number of pre-trained thermal models will suffice to quickly build accurate thermal models for many other homes, and that 1~day smart thermostat data could significantly improve the accuracy of transferred models in another season.