Closed-Loop Decision-Focused Learning for User-Aware Cloud Orchestration under Uncertainty
Heterogeneous job scheduling is formulated as a multi-objective combinatorial optimization problem (MOCOP) under uncertain constraints and a closed-loop decision-focused learning (CL-DFL) framework for cloud orchestration is proposed to improve robustness under heterogeneous workloads.
Dongbin Jiao, Xubo Zhang, Huakang Lin et al.
· 0 citations