用物理规律提升机器学习，让数据中心更智能更低碳
Toward Multiphysics-Informed Machine Learning for Sustainable Data Center Operations: Intelligence Evolution with Deployable Solutions for Computing Infrastructure
- 将物理规律嵌入机器学习模型，提升预测精度与安全性
- 实测可减少年碳排放达200万吨，且满足运行约束
- 适合关注绿色算力、智能运维的工程师与管理者
人工智能的快速发展给数据中心管理带来可持续性挑战，高功率密度机架导致高碳排放和快速冷却需求。尽管机器学习有望实现智能化管理，但其应用受限于安全与可靠性问题。为此，我们提出一种多物理场信息机器学习（MPIML）框架，将物理先验知识融入数据驱动模型，以提升准确性与安全性。构建了包含三大核心模块的集成系统：用于灵活设施建模的DCLib、高保真多物理场仿真工具DCTwin，以及决策优化引擎DCBrain。该系统支持碳感知的IT资源配置、安全导向的智能冷却控制及电池健康预测等关键应用。在某工业级数据中心冷却控制案例中，相比传统方法，本方案可降低年碳排放高达200千吨，同时确保运行约束不被突破。最后，我们展望了自主化、可持续数据中心发展的关键挑战与未来方向。
原文摘要 · Abstract (English)
The revolution in artificial intelligence (AI) has brought sustainable challenges in data center management due to the high carbon emissions and short cooling response time associated with high-power density racks. While machine learning (ML) offers promise for intelligent management, its adoption is hindered by safety and reliability concerns. To address this, we propose a multiphysics-informed machine learning (MPIML) framework that integrates physical priors into data-driven models for enhanced accuracy and safety. We introduce an integrated system architecture comprising three core engines: DCLib for versatile facility modeling, DCTwin for high-fidelity multiphysics simulation, and DCBrain for decision-making optimization. This system enables critical predictive and prescriptive applications, such as carbon-aware IT provisioning, safety-aware intelligent cooling control and battery health forecasting. An illustrative example on an industry-grade data center cooling control demonstrates that our MPIML approach reduces annual carbon emissions up to 200 kilotons compared with conventional methods while ensuring operational constraints are met. We conclude by outlining key challenges and future directions for developing autonomous and sustainable data centers.
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。