CityTFT: Temporal Fusion Transformer for Urban Building Energy Modeling (Papers Track)

Ting-Yu Dai (The University of Texas at Austin); Dev Niyogi (The University of Texas at Austin); Zoltan Nagy (The University of Texas at Austin)

Paper PDF Slides PDF Poster File Recorded Talk NeurIPS 2023 Poster Cite
Buildings Time-series Analysis


Urban Building Energy Modeling (UBEM) is an emerging method to investigate urban design and energy systems against the increasing energy demand at urban and neighborhood levels. However, current UBEM methods are mostly physic-based and time-consuming in multiple climate change scenarios. This work proposes CityTFT, a data-driven UBEM framework, to accurately model the energy demands in urban environments. With the empowerment of the underlying TFT framework and an augmented loss function, CityTFT could predict heating and cooling triggers in unseen climate dynamics with an F1 score of 99.98 \% while RMSE of loads of 13571.3750 Wh.

Recorded Talk (direct link)