HELIOS：面向多云分布式系统的自主资源编排策略的护栏式LLM驱动演化

中文摘要 AI 辅助

在多个公有云上运行延迟敏感型服务，形成了一个任何单一提供商自动扩缩器都无法看到的优化面：按需vCPU价格因提供商而异，现货折扣和中断风险因提供商和实例类型而异，出站费用惩罚状态迁移，而提供商级故障可能使单云部署瘫痪。大型语言模型（LLM）是有吸引力的编排器，因为它们可以从自然语言环境描述中综合出非平凡的决策逻辑。然而，将LLM置于每个调度决策的关键路径上是不切实际的：对于200个服务的舰队，每次决策的推理成本将超过其管理的云容量，并为毫秒级控制循环增加多秒延迟。HELIOS将LLM移出关键路径。LLM针对固定特征接口上的可执行编排策略（小型Python程序）进行演化，并针对轨迹驱动的多云模拟器进行优化。只有冠军程序在生产中运行，并包裹在护栏中，无论演化代码的提议如何，都强制执行容量可行性、SLO类放置规则和变动预算。在真实工作负载轨迹（PlanetLab、Bitbrains、Azure）与来自AWS、Azure和GCP的2026年价格和中断频率数据结合下，演化策略相比单云最佳拟合基线将惩罚性运营成本降低了45%，相比校准的多云启发式方法降低了9-19%。它以比40%更低的成本匹配了基于预言机的MILP规划器的优质SLO性能，并优于使用2.6倍更多环境交互训练的DQN元控制器。护栏至关重要：没有它们，同一策略族在10倍现货危险压力测试下会退化到97-98%的优质层停机时间，而有护栏时为0.17%。我们发布了模拟器、策略、LLM提示/响应存档和每代适应度日志，以实现完全可复现性。

英文摘要

Operating latency-sensitive services across multiple public clouds creates an optimization surface no single provider autoscaler can see: on-demand vCPU prices differ by provider, spot discounts and interruption risks vary by provider and instance type, egress fees penalize state movement, and provider-level failures can take down single-cloud deployments. Large language models (LLMs) are appealing orchestrators because they can synthesize non-trivial decision logic from a natural-language environment description. However, placing an LLM on the critical path of every scheduling decision is impractical: for a 200-service fleet, per-decision inference would cost more than the cloud capacity it manages and add multi-second latency to a millisecond-scale control loop. HELIOS moves the LLM off the critical path. The LLM evolves executable orchestration policies, small Python programs over a fixed feature interface, against a trace-driven multi-cloud simulator. Only the champion program runs in production, wrapped in guardrails that enforce capacity feasibility, SLO-class placement rules, and churn budgets regardless of evolved code's proposal. On real workload traces (PlanetLab, Bitbrains, Azure) combined with 2026 price and interruption-frequency data from AWS, Azure, and GCP, the evolved policy reduces penalized operating cost by 45% versus a single-cloud best-fit baseline and by 9-19% versus calibrated multi-cloud heuristics. It matches an oracle-informed MILP planner's premium-SLO performance at 40% lower cost and outperforms a DQN meta-controller trained with 2.6x more environment interactions. Guardrails are essential: without them, the same policy family degrades to 97-98% premium-tier downtime under a 10x spot-hazard stress test, versus 0.17% when guarded. We release the simulator, policies, LLM prompt/response archive, and per-generation fitness logs for full reproducibility.

发表机构

• New York University（纽约大学）
• Pepperdine University（佩珀代因大学）

机构由 AI 辅助整理，请以论文原文为准。