云科学工作流中任务可完成性预测方法

摘要

Cloud scientific workflow supplies a collaborative research platform for scholars in different regions in order to implement tasks,such as scientific computing,using various kinds of resources and services provided by cloud computing environment.Aimed to the uncertainty of task completion before a cloud scientific workflow instance starts,a novel task completion prediction model based on data availability/unavailability is proposed in this paper,together with the data availability relationship among them,called the data availability of positiveegative.In this way,the possibility of task completion can be acquired in advance using the data availability/unavailability propagation rules,therefore improves cloud scientific workflow task completion cognition to a large extent.Furthermore,the proposed task completion prediction model has some advantages,such as excellent description and judgement ability.In addition,some experiments have shown that the proposed task completion prediction method can reflect the task accomplishments in practice,and avoid the influence of early task failure to subsequent tasks as far as possible.In other words,it improves the task completion rate while reduces the resource rental expenses in cloud scientific workflow system.%云科学工作流利用云计算环境提供的各种资源与服务实现科学计算等任务处理,为不同地域的学者提供协作平台.针对云科学工作流启动前对任务完成情况未知的问题,提出一种基于数据可用性/不可用性的任务可完成性预测模型,并引入数据间可用性影响关系,即可用性支持/抑制关系.基于数据间可用性/不可用性传递规则,在任务启动前即对任务所需数据的可用性进行预判,以此提高对云科学工作流任务可完成性的认知.该任务可完成性预测模型,具有良好的描述能力和数据可用性判断能力.实验表明:基于数据可用性的任务可完成性预测结果能够真实反映实际任务执行情况,可尽可能地避免早期的任务失败对后续任务的影响,在提高云科学工作流任务完成率的同时,减少了资源的租赁费用.