EUVIMEDEUVIMED entdecken
Crossref

Mitigating Power Fluctuations of Large Language Model Training via Hybrid Energy Storage Systems in Renewable-Powered Computing Centers

Qian Wang, Ying Xu, Zhongkai Yi

IEEE Transactions on Sustainable Energy · 2026-10 · 17 (4) · 4220-4235

DOI: 10.1109/tste.2026.3707837 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Sustainable Energy, 2026-10. Verfasst von Qian Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the demand for computing power surges, renewable-powered computing centers (RPCCs) are being deployed at an accelerating pace. During large language model (LLM) training, RPCCs exhibit highly fluctuating, broadband load characteristics that can excite grid resonances and thereby pose significant threats to the secure and stable operation of emerging power systems. To address this challenge, this paper proposes a hybrid energy storage system (HESS) planning approach tailored to mitigate the power fluctuations of RPCCs. First, a signal decomposition method based on symplectic geometric mode decomposition (SGMD) is developed to capture multi-timescale load power fluctuations, on top of which a HESS power allocation strategy is designed. Then, by explicitly accounting for the power fluctuation characteristics of LLM training, an energy storage demand assessment method is established and a distributionally robust optimization (DRO) model for HESS planning is formulated. Finally, case studies are conducted to validate the effectiveness of the proposed planning framework and to elucidate the impacts of power fluctuations inherent to different LLM training tasks.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Q., Xu, Y., & Yi, Z. (2026). Mitigating Power Fluctuations of Large Language Model Training via Hybrid Energy Storage Systems in Renewable-Powered Computing Centers. IEEE Transactions on Sustainable Energy, 17(4), 4220-4235. https://doi.org/10.1109/tste.2026.3707837

Vancouver

Wang Q, Xu Y, Yi Z. Mitigating Power Fluctuations of Large Language Model Training via Hybrid Energy Storage Systems in Renewable-Powered Computing Centers. IEEE Transactions on Sustainable Energy. 2026;17(4):4220-4235. doi:10.1109/tste.2026.3707837

BibTeX
@article{Wang2026,
  author = {Wang, Qian and Xu, Ying and Yi, Zhongkai},
  title = {Mitigating Power Fluctuations of Large Language Model Training via Hybrid Energy Storage Systems in Renewable-Powered Computing Centers},
  journal = {IEEE Transactions on Sustainable Energy},
  year = {2026},
  volume = {17},
  number = {4},
  pages = {4220--4235},
  doi = {10.1109/tste.2026.3707837}
}
Kostenlos starten →