Toward a foundational thermal model for residential buildings

TL;DR

This paper introduces a physics-informed transformer architecture designed to create a universal thermal model for residential buildings, capable of generalizing across diverse climates and building types without calibration.

Contribution

The work presents a novel transformer-based model that embeds domain knowledge and demonstrates zero-shot transferability across different buildings and climates.

Findings

Achieves RMSE of 0.30°C in Texas and 0.29°C in Vermont for one-step predictions.

Outperforms traditional baselines and fine-tuned foundation models.

Models trained on few buildings generalize to unseen buildings and climates.

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{\deg}C in Texas, 0.29{\deg}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.