Can time-series foundation models perform building energy management tasks?
Data-Centric Engineering · 2026 · 7
DOI: 10.1017/dce.2026.10040 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data-Centric Engineering, online erschienen am 02.03.2026. Verfasst von Ozan Baris Mulayim und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health, DEVCOM Army Research Laboratory, National Science Foundation.
Abstract (Originalsprache)
Building energy management (BEM) tasks require processing and learning from a variety of time-series data. Existing solutions rely on bespoke task- and data-specific models to perform these tasks, limiting their broader applicability. Inspired by the transformative success of Large Language Models (LLMs), Time-Series Foundation Models (TSFMs), trained on diverse datasets, have the potential to change this. Were TSFMs to achieve a level of generalizability across tasks and contexts akin to LLMs, they could fundamentally address the scalability challenges pervasive in BEM. To understand where they stand today, we evaluate TSFMs across four dimensions: (1) generalizability in zero-shot univariate forecasting, (2) forecasting with covariates for thermal behavior modeling, (3) zero-shot representation learning for classification tasks, and (4) robustness to performance metrics and varying operational conditions. Our results reveal that TSFMs exhibit limited generalizability, performing only marginally better than statistical models on unseen datasets and modalities for univariate forecasting. Similarly, inclusion of covariates in TSFMs does not yield performance improvements, and their performance remains inferior to conventional models that utilize covariates. While TSFMs generate effective zero-shot representations for downstream classification tasks, they may remain inferior to statistical models in forecasting when statistical models perform test-time fitting. Moreover, TSFMs’ forecasting performance is sensitive to evaluation metrics, and they struggle in more complex building environments compared to statistical models. These findings underscore the need for targeted advancements in TSFM design, particularly their handling of covariates and incorporating context and temporal dynamics into prediction mechanisms, to develop more adaptable and scalable solutions for BEM.
Förderung
- National Institutes of Health
- DEVCOM Army Research Laboratory
- National Science Foundation
- Air Force Office of Scientific Research
Zitieren
APA
Mulayim, O. B., Quan, P., Han, L., Ouyang, X., Hong, D., Bergés, M., & Srivastava, M. (2026). Can time-series foundation models perform building energy management tasks?. Data-Centric Engineering, 7. https://doi.org/10.1017/dce.2026.10040
Vancouver
Mulayim OB, Quan P, Han L, Ouyang X, Hong D, Bergés M, et al. Can time-series foundation models perform building energy management tasks?. Data-Centric Engineering. 2026;7. doi:10.1017/dce.2026.10040
BibTeX
@article{Mulayim2026,
author = {Mulayim, Ozan Baris and Quan, Pengrui and Han, Liying and Ouyang, Xiaomin and Hong, Dezhi and Bergés, Mario and Srivastava, Mani},
title = {Can time-series foundation models perform building energy management tasks?},
journal = {Data-Centric Engineering},
year = {2026},
volume = {7},
doi = {10.1017/dce.2026.10040}
}
EUVIMED