云环境下基于优先级的多QoS约束工作流调度

Workflow Scheduling Strategy with Multi-QoS Constraint Based on Priority in Cloud Environment

为了实现云计算环境中工作流调度的执行时间与代价的均衡优化,提出了一种截止时间与预算双QoS约束条件下的工作流均衡调度算法。该算法将最优调度方案的求解过程划分为两个阶段:资源分级调度阶段和任务分级调度阶段。资源分级调度阶段中,算法通过任务升秩值定义任务优先级,并将任务按升秩值排序后为任务选择满足双QoS约束的适合资源集;进一步,在任务分级调度阶段,算法定义了4条满足时间/代价均衡的最优资源选择规则,进而得到最优工作流调度方案。通过设计算例,详细阐述了新算法的思想。最后,通过现实科学工作流的仿真测试,将所提算法与同类算法进行了性能比较。结果表明,在不同紧密程度的约束条件下,所提算法在调度代价、调度时间和调度成功率等指标上均表现出更优的性能,可以有效实现均衡调度。

For implementing the trade-off optimization between the execution time and cost of scientific workflow scheduling in cloud environment,this paper proposed a Time-Cost trade-off workflow Task Scheduling algorithm (TCTS) under bi-constrainted condition of deadline and budget.TCTS divides the solving process of the optimal schedu- ling scheme into two stages:the resource level scheduling stage and the task level scheduling stage.In the resource level scheduling stage,the algorithm defines the priority of a task by the upward rank,and selects the suitable resource set satisfying bi-QoS constraints for tasks according to tasks’ rank.Further,in the task level scheduling stage,the algorithm defines four rules of selecting the optimal resource based upon Time-Cost trade-off,which can obtain the optimal workflow scheduling scheme.This paper elaborated the idea of the proposed algorithm by a designed example.Through the simulation tests of real-world scientific workflows,the proposed algorithm is compared with the same types of algorithms.The results show that under the constraint conditions with different tight degrees,the proposed algorithm has better perfor- mance on some indexes such as the scheduling cost,the scheduling time and the schedule success,which will effectively realize the balanced scheduling.