【摘要】 网格计算环境下,基于有向无环图(DAG)的成本-时间优化调度算法运用经济规律把网格用户的任务映射到网格资源中运行。OGS算法考虑了任务间的优先关系,使得任务完成时间最小,但没考虑到在网格环境中所需的成本。Nimrod/G模型中提出基于时间和成本限制下的优化调度算法(DBC)考虑了时间和成本,但没考虑任务间的优先关系。本文综合考虑了成本-时间因素以及任务间的优先关系,在不增加完成时间的基础上,把任务映射到价格便宜的机器上,提出了基于有向无环图的成本-时间优化调度算法。通过仿真表明,相对OGS算法,该算法减少了所需成本。更多还原

【Abstract】 Under the grid computing environment,the cost -time optimization dispatch algorithm based on Directed Acyclic Graph(DAG) enabled the grid users’tasks map to the grid resources by using the economic law. The priority of tasks had been considered in the OGS algorithm which enabled the completion time to be smallest, but the cost had not been considered in the grid environment. The time and the cost had been considered in the DBC algorithm based on the Nimrod/G model, but the priority of tasks had not been considered. The cost -time factor as well as the priority of tasks had been considered synthetically in this paper, the tasks had been mapped to the cheap machines without increasing the completion time , the cost -time optimization dispatch algorithm based on DAG was proposed. Simulation results showed that this algorithm reduced the cost compared with OGS algorithm.更多还原