Building thermal dynamics modeling with deep transfer learning using a large residential smart thermostat dataset

Journal Article · Wed Dec 20 04:00:00 EST 2023 · Engineering Applications of Artificial Intelligence

DOI:https://doi.org/10.1016/j.engappai.2023.107701· OSTI ID:2377667

Li, Han ^[1]; Pinto, Giuseppe ^[2]; Piscitelli, Marco Savino ^[3]; Capozzoli, Alfonso ^[3]; Hong, Tianzhen ^[1]

---

1. Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
2. Politecnico di Torino (Italy); PassiveLogic, Inc., Salt Lake City, UT (United States)
3. Politecnico di Torino (Italy)

Understanding thermal dynamics and obtaining the computational model of residential buildings enable its scaled application in energy retrofits, control optimization and decarbonization. In this paper, we present a deep learning approach to model building thermal dynamics with smart thermostat data collected from residential buildings, with the goal to investigate model generalizability. In the first stage, we developed and compared different Deep Learning architectures including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) models and CNN-LSTM to predict indoor air temperature in a multi-step time horizon. In the second stage, we implemented a Transfer Learning (TL) process, which aims to improve the prediction performance on a new set of buildings (targets), exploiting the knowledge of related or similar buildings (sources). Different TL strategies and source model identification methods were investigated. The study showed that the CNN-LSTM performed the best among the architectures compared, with an average Mean Absolute Error (MAE) of 0.26 °C for one-hour-ahead (twelve 5-min future steps) predictions. Furthermore, the results showed that freezing the LSTM layer and fine-tuning the other layers of the CNN-LSTM achieved the best performance among four TL strategies, which further improved the performance with respect to a machine learning approach by 10%, and proving the effectiveness and generalizability of the proposed approach. A comparison of three different source model identification methods showed that randomly selecting source models constrained by similar building characteristics can provide good TL performance while retaining simplicity comparing with other quantitative source identification methods.

• Research Organization: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
• Grant/Contract Number: AC02-05CH11231
• OSTI ID: 2377667
• Journal Information: Engineering Applications of Artificial Intelligence, Journal Name: Engineering Applications of Artificial Intelligence Vol. 130; ISSN 0952-1976
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Building thermal dynamics
Data-driven model
Thermostat dataset
Transfer learning