发表机构
Michigan Technological University; Cornell University(密歇根理工大学; 康奈尔大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
该研究针对AI数据中心冷负荷仿真,提出可配置热动力学模型,经Marconi100超级计算机数据验证,可降低冷负荷预测误差,提升日峰值与波动复现能力,为电力系统研究提供可行的冷负荷曲线生成方法。
AI 中文摘要
冷负荷是AI数据中心电力消耗中重要且具有灵活性的组成部分,但时间同步测量数据匮乏,且恒定性能系数模型无法表征热动力学特性。本文提出一种用于混合风冷与液冷数据中心的可配置热动力学仿真模型。与现有以温度预测或设备级冷却分析为核心的模型不同,该模型旨在为长时间电力系统研究生成动态冷电力曲线。通过Marconi100超级计算机的运行遥测数据对模型进行验证,与基线模型相比,所提模型将平均绝对误差从95.80 kW降至20.88 kW,均方根误差从109.79 kW降至27.27 kW;对约520条日负荷曲线的评估进一步显示,模型对日峰值需求及日内波动的复现能力得到提升,为电力系统研究提供了一种计算上可行、且具备物理解释性的冷负荷曲线生成方法。
英文摘要
Cooling demand constitutes a significant and flexible component of AI data center electricity consumption, but time-synchronized measurements are scarce and constant coefficient-of-performance models cannot represent thermal dynamics. This letter proposes a closed-loop simulation model which couples a linear thermal dynamic model with deadband-based control to capture the nonlinear cooling dynamics. The model is validated using operational telemetry from the Marconi100 supercomputer. Compared with the baseline, the proposed model reduces the mean absolute error from 95.80 to 20.88~kW and the root-mean-square error from 109.79 to 27.27~kW. Evaluation over approximately 520 daily profiles further shows improved reproduction of daily peak demand and intraday variability. The proposed model provides a computationally tractable means of generating physically interpretable cooling load profiles for power system studies.