一种基于任务竞争力的工作流调度算法

Grid Workflow Scheduling Algorithm Based on Task Competitiveness

网格计算聚集了大量的异构分布式的计算或存储资源,为科学研究提供了一个高性能环境.然而,网格资源的异构性和自治性特征使得任务调度变得极其复杂.针对DAG表示的科学工作流调度问题,根据任务可用资源率确定任务调度的优先级,以任务竞争力刻画任务对资源的最佳匹配度,基于分层调度策略提出了一种基于任务竞争力的工作流调度算法.采用GridSim模拟实验表明该算法相对于其他两个算法,具有更小的执行时间.

Currently deployed grid systems gather together thousands of computational and storage resources for the benefit of a large community of scientists, which provide the foundation for scientific exploration and research. Because of the autonomy and heterogeneity of Grid resources, efficient scheduling tasks ensuring user＇ QoS requirements is NP problem. Aimed at computing intensive workflow scheduling in Grid, a concept called Task Competitiveness discribing the matching degree between task and resource is defined. Based on workflow leveling strategy, a novel workflow scheduling algorithm based on task competitiveness is proposed. Simulation results show better makespan performance compared with others.