云边协同环境下基于局部关键路径的工作流应用调度策略

Workflow Applications Scheduling Strategy Based on Partial Critical Path in Cloud-edge Environment

针对不确定性云边协同环境下工作流应用调度问题,考虑服务器的负载压力、网络拥塞等计算环境因素造成计算性能和传输带宽的不稳定性,采用三角模糊数表示模糊云边协同环境中服务器的计算性能和传输带宽.对于泊松到达的多工作流应用,提出一种基于局部关键路径的多工作流应用调度策略,将局部关键路径作为调度单元进行统一调度,充分避免任务之间的数据传输,旨在满足多工作流应用截止日期约束的前提下,降低其模糊执行代价.仿真结果表明,与其他基准策略相比,在不同的截止时间约束下,该策略都能获得多工作流应用最优的可行调度方案,同时实现了模糊执行代价的有效优化.

Aiming at the workflow application scheduling in the uncertain cloud-edge environment,considering the instability of computing performance and transmission bandwidth caused by computing environment factors such as server load pressure and network congestion,triangular fuzzy numbers(TFNs)are employed to describe the computing performance of servers and transmission bandwidth between them in the uncertain cloud-edge environment.Specially,the Workflow applications Scheduling strategy based on Partial Critical Path(WSPCP)is proposed for workflow applications with Poisson arrival rate,where the partial critical path is used as the scheduling unit to fully avoid the data transmission between tasks,aiming to reduce the fuzzy execution cost under the premise of satisfying the deadline constraints of workflow applications.Compared with other benchmark strategies,simulation results demonstrate that the proposed strategy can obtain the optimal feasible scheduling scheme for workflow applications within different deadline constraints,and significantly realize the optimization of fuzzy execution cost.