一种改进的启发式网格任务调度算法

An Improved Heuristic Algorithm for Tasks Scheduling on Grid Computing

网格任务调度算法是影响网格成功与否的关键技术之一。网格计算中,一个好的任务调度算法不但要考虑所有任务的makespan,使其值尽量小,同样要考虑到整个系统机器间的负载平衡问题。文章对异构计算环境下的元任务调度算法进行了分析,针对Min-min算法可能引发的负载不平衡问题,结合网格计算环境的特点,提出了一种适用于网格计算环境中的任务调度算法。

Algorithm for Grid Tasks Scheduling is one of the key technologies which influence Grid success. Grid system is composed of heterogeneous resources. In grid computing, a good algorithm for tasks scheduling should not only decrease the makespan of all tasks but also balance the load among the resources in the grid system. We first analyze the scheduling of meta-tasks in the heterogeneous environment, and then according to the load imbalance question in the Min-min algorithm, propose an improved algorithm that suits to be used in the grid environment.