Transfer learning for thermal comfort prediction in multiple cities

The HVAC (Heating, Ventilation and Air Conditioning) system is an important part of a building, which constitutes up to 40% of building energy usage. The main purpose of HVAC, maintaining appropriate thermal comfort, is crucial for the best energy usage. Additionally, thermal comfort is also important for well-being, health, and work productivity. Recently, data-driven thermal comfort models have achieved better performance than traditional knowledge-based methods (e.g. the predicted mean vote model). An accurate thermal comfort model requires a large amount of self-reported thermal comfort data from indoor occupants which undoubtedly remains a challenge for researchers. In this research, we aim to address this data-shortage problem and boost the performance of thermal comfort prediction. We utilize sensor data from multiple cities in the same climate zone to learn thermal comfort patterns. We present a transfer learning-based multilayer perceptron model from the same climate zone (TL-MLP-C*) for accurate thermal comfort prediction. Extensive experimental results on the ASHRAE RP-884, Scales Project and Medium US Office datasets show that the performance of the proposed TL-MLP-C* exceeds the performance of state-of-the-art methods in accuracy and F1-score.

Automated summary

The HVAC system is crucial in buildings, accounting for up to 40% of energy usage, and maintaining thermal comfort is important for energy efficiency and well-being. Recent advancements in data-driven thermal comfort models have shown better performance than traditional methods, contributing to more accurate predictions despite challenges in data availability.