Given the characteristics of dynamic provisioning and illusion of unlimited resources, clouds are becoming a popular alternative for running scientific workflows. In a cloud system for processing workflow applications, the system’s performance is heavily influenced by two factors: the scheduling strategy and failure of components. Failures in a cloud system can simultaneously affect several users and depreciate the number of available computing resources. A bad scheduling strategy can increase the expected makespan and the idle time of physical machines. In this paper, we propose an optimization method for the scheduling of scientific workflows on cloud systems. The method comprises the use of a meta-heuristic algorithm coupled to a performability model that provides the fitnesses of explored solutions. For being able to represent the combined effect of scheduling and component failures, we adopted discrete event simulation for the performability model. Experimental results show the effectiveness of the hybrid simulation-optimization approach for optimizing the number of allocated virtual machines and the scheduling of tasks regarding performability.

中文翻译：

---

云环境中工作流应用程序的性能评估和优化

鉴于动态预配置的特性以及无限资源的幻觉，云正在成为运行科学工作流的流行替代方法。在用于处理工作流应用程序的云系统中，系统的性能在很大程度上受到两个因素的影响：调度策略和组件故障。云系统中的故障可能同时影响多个用户并降低可用计算资源的数量。不良的调度策略可能会增加预期的制造时间和物理机的空闲时间。在本文中，我们提出了一种用于在云系统上调度科学工作流的优化方法。该方法包括使用元启发式算法，该算法与可提供探索解决方案适用性的性能模型耦合。为了能够表示调度和组件故障的综合影响，我们对性能模型采用了离散事件模拟。实验结果表明，混合仿真优化方法对于优化分配的虚拟机数量和有关性能的任务调度的有效性。