Abstract:The building energy community lacks a foundational thermal model, i.e., a single pretrained model capable of generalizing across diverse buildings, climates, and control strategies without building-specific calibration. Achieving this vision requires architectural principles that capture universal thermal dynamics rather than memorizing building-specific patterns. We take a step toward this goal by presenting a physics-informed transformer architecture that embeds domain knowledge, e.g., derivative enrichment and Euler-based numerical integration, into a decoder-only framework. We incorporate static building features extracted from simulation models and employ Rotary Position Embedding attention to capture temporal dependencies. Evaluated on the CityLearn dataset spanning 247 residential buildings across three climate zones, our model achieves one-step prediction accuracy (RMSE of 0.30°C in Texas, 0.29°C in Vermont) while outperforming both traditional baselines and fine-tuned Time-Series Foundation Models. We also demonstrate zero-shot transferability: models trained on as few as two buildings generalize to unseen buildings and climate zones without fine-tuning. Despite the limitation of simulated residential buildings, our results establish physics-informed architectural principles as a promising foundation for universal building thermal models.
| Subjects: | Machine Learning (cs.LG); Systems and Control (eess.SY) |
| Cite as: | arXiv:2605.01364 [cs.LG] |
| (or arXiv:2605.01364v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.01364 arXiv-issued DOI via DataCite (pending registration) |
From: Zoltan Nagy [view email]
[v1]
Sat, 2 May 2026 10:19:24 UTC (4,384 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。