用视觉模型快速预测数据中心温度分布，实现实时节能调控。
Fast 3D Surrogate Modeling for Data Center Thermal Management
- 基于3D体素输入，融合服务器负载与空调参数建模温度场。
- 推理速度提升20,000倍，从数小时降至毫秒级，准确预测热点。
- 适合数据中心运维、绿色算力优化者参考，推动智能冷却系统落地。
通过实现数据中心实时温度预测以降低能耗和碳排放，对可持续发展与运行效率至关重要。这需要精确建模三维温度场以捕捉气流动力学与热交互关系，但传统热力学CFD求解器虽精度高，却计算成本高昂，需人工构建网格与边界条件，难以用于实时场景。为此，我们提出一种基于视觉的代理建模框架，直接在数据中心的3D体素表示上操作，整合服务器工作负载、风扇转速与空调设定温度等输入。评估了多种架构，包括3D CNN U-Net变体、3D傅里叶神经算子及3D视觉变压器，将热力输入映射为高保真热图。结果表明，该代理模型可泛化至不同数据中心配置，计算速度提升20,000倍，从数小时缩短至毫秒级，从而支持实时冷却控制与负载调度，实现7%的显著节能并降低碳足迹。
原文摘要 · Abstract (English)
Reducing energy consumption and carbon emissions in data centers by enabling real-time temperature prediction is critical for sustainability and operational efficiency. Achieving this requires accurate modeling of the 3D temperature field to capture airflow dynamics and thermal interactions under varying operating conditions. Traditional thermal CFD solvers, while accurate, are computationally expensive and require expert-crafted meshes and boundary conditions, making them impractical for real-time use. To address these limitations, we develop a vision-based surrogate modeling framework that operates directly on a 3D voxelized representation of the data center, incorporating server workloads, fan speeds, and HVAC temperature set points. We evaluate multiple architectures, including 3D CNN U-Net variants, a 3D Fourier Neural Operator, and 3D vision transformers, to map these thermal inputs to high-fidelity heat maps. Our results show that the surrogate models generalize across data center configurations and significantly speed up computations (20,000x), from hundreds of milliseconds to hours. This fast and accurate estimation of hot spots and temperature distribution enables real-time cooling control and workload redistribution, leading to substantial energy savings (7\%) and reduced carbon footprint.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。