Cloud computing is the fastest growing distributed computing paradigm that provides online IT resources on demand by following a pay-as-you-go billing model. The success of this computing paradigm enables cloud providers to offer an extensive collection of parallel computing resources to deal with Big Data workflow scheduling problems. Although, workflow scheduling has been extensively studied, however, most of them are unable to achieve user-specified deadline constraints at the cheap cost. In this paper, a Dynamic Cost-Efficient Deadline-Aware (DCEDA) heuristic algorithm is proposed for scheduling Big Data workflow that produces the cheapest schedule while achieving the deadline constraints. DCEDA dynamically takes appropriate scheduling decisions for workflow tasks based on the fact that deadline constraint is not violated in the future. Also, it continuously monitors the VM pool for identifying the active idle VMs that incur extra costs and overheads, and subsequently de-provision them. The experimental analysis based on Montage workflow and randomly generated synthetic workflow with various characteristics prove that DCEDA delivers better performance in comparison to the existing algorithms.

云计算是增长最快的分布式计算范例，通过遵循“按需付费”计费模型来按需提供在线IT资源。这种计算范例的成功使云提供商可以提供大量并行计算资源来处理大数据工作流调度问题。尽管已经对工作流调度进行了广泛的研究，但是，大多数工作流无法以低廉的成本实现用户指定的期限约束。在本文中，提出了一种动态成本有效的截止日期感知（DCEDA）启发式算法，用于调度大数据工作流，该工作流产生最便宜的调度，同时又达到了截止日期约束。DCEDA基于将来不会违反截止期限约束这一事实，动态地为工作流任务制定适当的调度决策。也，它会持续监视VM池，以识别活动的空闲VM，这些活动的VM会产生额外的成本和开销，并随后对其进行预配置。基于蒙太奇工作流和随机生成的具有各种特征的合成工作流的实验分析证明，DCEDA与现有算法相比具有更好的性能。