摘要：

针对现有网格任务调度算法存在的问题，提出一种基于多维服务质量(QoS)约束的算法，综合考虑2种造成任务停滞的原因，从多维QoS参数匹配最优出发，利用过滤值进一步提高网格系统的利用率，减少任务的完成时间，降低任务的失效率，从而更好地满足用户的QoS需求。仿真实验结果表明，该算法符合网格的复杂环境，且是有效的。

关键词: 网格计算, 任务调度, 服务质量, 过滤值

Abstract:

Aiming at the shortcomings of grid task scheduling algorithm, a novel algorithm based on multi-dimensional Quality of Service(QoS) constraints is presented, which considers two reasons for the tasks stagnation. In view of the optimal multi-dimensional QoS parameter matching, the value of filters is used to improve the utilization rate of the grid system, reduce the task completion times, and lower failure rate of tasks. It is able to better meet the user’s QoS requirements. Simulation results show this algorithm accords with the grid complex environment. It is effective.

Key words: grid computing, task scheduling, Quality of Service(QoS), filtering value

中图分类号: 

• TP393