期刊名称：International Journal of Grid and Distributed Computing
印刷版ISSN：2005-4262
出版年度：2014
卷号：7
期号：3
页码：31-40
DOI：10.14257/ijgdc.2014.7.3.04
出版社：SERSC
摘要：Focusing on the problem that users would remove or delete the task at any time in cloud computing environment, a new scheduling algorithm for adapting to dynamic changes of user task is proposed. At first, the algorithm uses directed acyclic graph (DAG) to describe the association relation of cloud computing tasks. When a task needs to be removed, the algorithm utilizes a cost function to determine whether to cancel this task, and then updates the DAG according to its dependence on removed task. Finally, it uses a heuristic algorithm to perform scheduling. Experimental results show that this algorithm can better avoid scheduling execution of revoked tasks and improve the executive efficiency of cloud computing resource. Its performance is better than Min-Min and Max-Min in executive time span.
