面向不确定性下用户感知云编排的闭环决策聚焦学习
Closed-Loop Decision-Focused Learning for User-Aware Cloud Orchestration under Uncertainty
AI总结：
针对不确定性下云编排的资源调度问题，提出CL-DFL框架并结合GNeuro-PLS策略，在多真实数据集上实现了违规率、用户满意度与资源利用率的更优权衡。
AI中文摘要：
时变云工作负载常导致非高峰时段资源利用率不足、高峰时段资源竞争问题。现有“预测后优化（PTO）”框架存在两阶段解耦问题，阻碍了违规率、用户满意度与资源利用率间的平衡。我们将异构作业调度建模为不确定约束下的多目标组合优化问题（MOCOP），并提出用于云编排的闭环决策聚焦学习（CL-DFL）框架。CL-DFL将基于多元时间序列图神经网络（MTGNN）的时空预测器，与基于树状Parzen估计器（TPE）的零阶决策聚焦学习（DFL）机制相集成，在资源感知与调度决策间建立端到端（E2E）反馈通路。此外，我们通过将分组相对策略优化（GRPO）融入协同局部搜索，开发了GNeuro-PLS策略以提升异构工作负载下的鲁棒性。在四个真实世界数据集上的大量实验表明，CL-DFL在违规率、用户满意度与资源利用率间实现了更优权衡，与现有最优基线相比，可有效控制常规工作负载下的过载风险，并在高饱和场景下保持韧性。
英文摘要：
Time-varying cloud workloads often cause resource under-utilization during off-peak periods and resource contention during peak periods. Existing prediction-then-optimization (PTO) frameworks suffer from two-stage decoupling, hindering the balance among violation rate, user satisfaction, and resource utilization. We formulate heterogeneous job scheduling as a multi-objective combinatorial optimization problem (MOCOP) under uncertain constraints and propose a closed-loop decision-focused learning (CL-DFL) framework for cloud orchestration. CL-DFL integrates a Multivariate Time-series Graph Neural Network (MTGNN)-based spatio-temporal predictor with a zeroth-order decision-focused learning (DFL) mechanism based on the tree-structured Parzen estimator (TPE). This integration establishes an end-to-end (E2E) feedback pathway between resource perception and scheduling decisions. Furthermore, we develop the GNeuro-PLS strategy by incorporating group relative policy optimization (GRPO) into cooperative local search to improve robustness under heterogeneous workloads. Extensive experiments on four real-world datasets demonstrate that CL-DFL achieves superior trade-offs among violation rate, user satisfaction, and resource utilization. It effectively controls overload risks under regular workloads and maintains resilience under highly saturated scenarios compared with state-of-the-art baselines.
