Cost-effective deadline-aware stochastic scheduling strategy for workflow applications on virtual machines in cloud computing

摘要

This paper addresses the problems in scheduling the workflow tasks on cloud computingsystems such as minimizing the total price for execution (TPE) and total execution time (TET) oftheworkflowwhile meeting the deadline constraints ina stochastic environment. Scheduling suchprecedence-constrained stochastic tasks on the cloud with virtual machines of different computingcapabilities is a difficult problem. However, instead of TPE and TET, the virtual machine'sacquisition delay is one of the primary cloud's characteristics. The current paper first formulatesthe problem as a stochastic scheduling model on cloud. Then, a stochastic cost-effectivedeadline-aware (S-CEDA) resource scheduler is developed. S-CEDA incorporates the expectedvalue and variance of the task's processing time and inter-task communication time into theworkflow scheduling. The experimental results show that S-CEDA outperforms the existingstate-of-the-art algorithms such as stochastic heterogeneous earliest finish time (SHEFT) andcost-effective deadline-aware (CEDA) scheduling algorithms in terms of the TPE and TET of theworkflow.