Switching-Reference Voltage Control for Distribution Systems with AI-Training Data Centers
This addresses voltage stability issues for power grids with AI data centers, representing an incremental improvement over existing methods.
The paper tackles voltage deviations in power distribution systems caused by rapid power fluctuations from AI training data centers by proposing a decentralized switching-reference voltage control framework. Simulation results show the method substantially reduces voltage deviations and reactive control effort.
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.