2025/07/08 by Yize Chen, Chen, Yize, Baosen Zhang +1 · 2 citations
Computer Science · Engineering · #Cloud Computing and Resource Management #FOS: Electrical engineering #Smart Grid Security and Resilience #Software-Defined Networks and 5G #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2507.06416
openalex publication_date 2025/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent boom in foundation models and AI computing have raised growing concerns on the power and energy trajectories of large-scale data centers. This paper focuses on the voltage issues caused by volatile and intensity of data center power demand, which also aligns with recent observations of more frequent voltage disturbances in power grids. To address these data center integration challenges, we propose a dynamic voltage control scheme by harnessing data center's load regulation capabilities. By taking local voltage measurements and adjusting power injections at each data center buses through the dynamic voltage and frequency scaling (DVFS) scheme, we are able to maintain safe voltage magnitude in a distributed fashion with higher data center computing load. Simulations using real large language model (LLM) inference load validate the effectiveness of our proposed mechanism. Both the LLM power data and proposed control scheme are open sourced.