Research

Paper

AI LLM March 16, 2026

Switching-Reference Voltage Control for Distribution Systems with AI-Training Data Centers

Authors

Mingyuan Yan, Trager Joswig-Jones, Baosen Zhang, Yize Chen, Wenqi Cu

Abstract

Large-scale AI training workloads in modern data centers exhibit rapid and periodic power fluctuations, which may induce significant voltage deviations in power distribution systems. Existing voltage regulation methods, such as droop control, are primarily designed for slowly varying loads and may therefore be ineffective in mitigating these fast fluctuations. In addition, repeated control actions can incur substantial cost. To address this challenge, this paper proposes a decentralized switching-reference voltage control framework that exploits the structured behavior of AI training workloads. We establish conditions for voltage convergence and characterize an effective reference design that aligns with the two dominant operating levels of the AI training workload. The switching rule for voltage references is implemented solely using local voltage measurements, enabling simple local implementation while significantly reducing control effort. Simulation studies demonstrate that the proposed method substantially reduces both voltage deviations and reactive control effort, while remaining compatible with internal data center control strategies without requiring extensive coordination.

Metadata

arXiv ID: 2603.15588
Provider: ARXIV
Primary Category: eess.SY
Published: 2026-03-16
Fetched: 2026-03-17 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.15588v1</id>\n    <title>Switching-Reference Voltage Control for Distribution Systems with AI-Training Data Centers</title>\n    <updated>2026-03-16T17:48:27Z</updated>\n    <link href='https://arxiv.org/abs/2603.15588v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.15588v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large-scale AI training workloads in modern data centers exhibit rapid and periodic power fluctuations, which may induce significant voltage deviations in power distribution systems. Existing voltage regulation methods, such as droop control, are primarily designed for slowly varying loads and may therefore be ineffective in mitigating these fast fluctuations. In addition, repeated control actions can incur substantial cost. To address this challenge, this paper proposes a decentralized switching-reference voltage control framework that exploits the structured behavior of AI training workloads. We establish conditions for voltage convergence and characterize an effective reference design that aligns with the two dominant operating levels of the AI training workload. The switching rule for voltage references is implemented solely using local voltage measurements, enabling simple local implementation while significantly reducing control effort. Simulation studies demonstrate that the proposed method substantially reduces both voltage deviations and reactive control effort, while remaining compatible with internal data center control strategies without requiring extensive coordination.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-03-16T17:48:27Z</published>\n    <arxiv:primary_category term='eess.SY'/>\n    <author>\n      <name>Mingyuan Yan</name>\n    </author>\n    <author>\n      <name>Trager Joswig-Jones</name>\n    </author>\n    <author>\n      <name>Baosen Zhang</name>\n    </author>\n    <author>\n      <name>Yize Chen</name>\n    </author>\n    <author>\n      <name>Wenqi Cu</name>\n    </author>\n  </entry>"
}