DCoPilot: 基于生成AI的动态数据中心操作策略适应
DCoPilot: Generative AI-Empowered Policy Adaptation for Dynamic Data Center Operations
AI总结：
DCoPilot通过结合大型语言模型和超网络生成动态数据中心操作的控制策略，实现高效适应与稳定收敛。
摘要：
现代数据中心（DCs）托管的人工智能（AI）专用设备以高功率密度运行，具有快速变化的工作负载，使得分钟级的适应对于安全和节能运行至关重要。然而，手动设计分段深度强化学习（DRL）代理无法跟上频繁的动态变化和服务级别协议（SLA）变化。这种规格到策略的滞后导致缺乏及时有效的控制策略，可能导致服务中断。为弥合这一差距，我们提出了DCoPilot，一种用于动态数据中心操作生成控制策略的混合框架。DCoPilot结合了两种不同的生成范式，即一个大型语言模型（LLM），用于生成结构化的奖励形式，以及一个超网络，用于生成策略权重的参数化形式。DCoPilot通过三个协调阶段运行：（i）模拟规模扩展，该过程在多样化的模拟准备（SimReady）场景中压力测试奖励候选者；（ii）元策略蒸馏，其中超网络被训练以根据SLA和场景嵌入生成策略权重；（iii）在线适应，使零样本策略生成能够响应更新的规范。在五个控制任务家族上评估，覆盖了多样化的数据中心组件，DCoPilot实现了接近零的约束违反，并在规格变化方面优于所有基线。消融研究验证了基于LLM的统一奖励生成在促进稳定超网络收敛方面的有效性。
英文摘要：
Modern data centers (DCs) hosting artificial intelligence (AI)-dedicated devices operate at high power densities with rapidly varying workloads, making minute-level adaptation essential for safe and energy-efficient operation. However, manually designing piecewise deep reinforcement learning (DRL) agents cannot keep pace with frequent dynamics shifts and service-level agreement (SLA) changes of an evolving DC. This specification-to-policy lag causes a lack of timely, effective control policies, which may lead to service outages. To bridge the gap, we present DCoPilot, a hybrid framework for generative control policies in dynamic DC operation. DCoPilot synergizes two distinct generative paradigms, i.e., a large language model (LLM) that performs symbolic generation of structured reward forms, and a hypernetwork that conducts parametric generation of policy weights. DCoPilot operates through three coordinated phases: (i) simulation scale-up, which stress-tests reward candidates across diverse simulation-ready (SimReady) scenes; (ii) meta policy distillation, where a hypernetwork is trained to output policy weights conditioned on SLA and scene embeddings; and (iii) online adaptation, enabling zero-shot policy generation in response to updated specifications. Evaluated across five control task families spanning diverse DC components, DCoPilot achieves near-zero constraint violations and outperforms all baselines across specification variations. Ablation studies validate the effectiveness of LLM-based unified reward generation in enabling stable hypernetwork convergence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
