Delay-Optimal Scheduling of VMs in a Queueing Cloud Computing System with Heterogeneous Workloads

This paper studies virtual machine (VM) scheduling in a queueing cloud computing system with stochastical arrivals of heterogeneous jobs by considering jobs’ delay requirements. The delay-optimal VM such is formulated as multi-resource multi-class problem minimize the average job completion time, which often NP-hard. To solve problem, we first propose model that buffers same type one queue. then divides into two parallel low-complexity algorithms, i.e., intra-queue buffering and inter-queue scheduling. A min-min best fit (MM-BF) policy used to schedule different queues remaining resources, while shortest-job-first (SJF) buffer requests each queue based on their lengths an ascending order. avoid starvation for long-duration SJF-MMBF, further queue-length-based MaxWeight (QMW) Lyapunov drift jobs, called SJF-QMW. Simulation results show that, SJF-MMBF SJF-QMW achieve low performance terms time high throughput hosting ratio.