发表机构
Siemens - Research & Predevelopment（西门子研究与预开发部）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于轨迹灵敏度的动态评估框架，用于含直流微电网的AI数据中心，在故障下快速估计系统响应，计算时间从秒降至毫秒，验证精度高。
AI 中文摘要
人工智能（AI）数据中心正成为以变流器为主导、参数丰富的电力系统，其动态响应取决于快速的负载驱动需求变化、严格调节的数据大厅变流器以及协调的现场电源。通过为每次故障、负载实现和参数扰动反复求解非线性时域模型来评估此类系统，计算成本高昂，且对响应灵敏度的洞察有限。本文提出了一种基于轨迹灵敏度（TS）的动态评估框架，用于一个由2 kV直流微电网供电并带有电网互联接口的自包含AI数据中心。该模型包括时变的数据大厅负载曲线、电压源变流器（VSC）、电池储能系统（BESS）单元、超级电容器以及同步发电侧电源。对于每次扰动，首先沿非线性扰动轨迹计算TS，捕捉电源跳闸、数据大厅故障、变流器控制和负载爬坡的局部影响。随后，利用计算得到的TS数据来估计在同时参数扰动下的系统轨迹。与在±15%扰动下进行的完整非线性常微分方程仿真的验证显示出良好的一致性。此外，基于TS的方法将动态响应评估的计算时间从秒级缩短到毫秒级，展示了其作为AI数据中心动力学可扩展筛选工具的潜力。
英文摘要
Artificial Intelligence (AI) data centers are emerging as converter-dominated, parameter-rich electrical systems whose dynamic response depends on fast workload-driven demand variations, tightly regulated data-hall converters, and coordinated on-site sources. Assessing such systems by repeatedly solving nonlinear time-domain models for every outage, load realization, and parameter perturbation is computationally expensive and provides limited insight into response sensitivity. This paper presents a trajectory sensitivity (TS)-based dynamic assessment framework for a self-contained AI data center supplied by a 2 kV DC microgrid with a grid-tied interface. The model includes time-varying data-hall load profiles, a voltage source converter (VSC), battery energy storage systems (BESS) units, supercapacitors, and synchronous-generation-side sources. For each disturbance, firstly, TS are computed along the nonlinear disturbance trajectory, capturing the local effect of source trips, data-hall outages, converter controls, and load ramps. Later, the computed TS data is used to estimate system trajectories under simultaneous parameter perturbations. Validation against full nonlinear ODE simulations with $\pm 15\%$ perturbations shows close agreement. In addition, the TS-based approach reduces computational time of dynamic-response evaluations from seconds to milliseconds, demonstrating its potential as a scalable screening tool for AI data center dynamics.
Comments7 pages, 5 figures
