基于蚁群优化算法的服务网格的作业调度

A Job Scheduling for Service Grid Using Ant Colony Algorithm

提出了利用蚁群算法来优化服务网格的作业调度系统的方法和一个两层的作业调度模型,该模型可以在网格的动态和异构环境下实现对作业执行时间的预测,然后根据作业的预测执行时间并利用蚁群优化算法使适应函数取得最小值,从而得到最优化的作业调度。基于开发的校园网格实验床,通过实验显示该方法可以优化服务网格的性能,减少作业的平均执行时间,提高系统的吞吐率。

This paper presents a new approach to scheduling jobs on service grid using ant colony algorithm. A two-level job-scheduling model is provided; this model can predict the execution time of job in heterogeneous and dynamic environment, then on the basis of the predicted execution time, it can optimize the job scheduling procedure using ant colony algorithm. Experiments on a campus grid test bed show a significant reduction of the average execution time and a higher throughput.