摘要
针对目前已有的云计算任务资源分配模型仅考虑独立任务资源分配,提出了一种基于虚拟DAG图的云计算环境下协作型任务资源分配模型;首先,定义了云计算协作型任务资源分配DAG模型,为了实现任务的统一分配,将传统DAG图改造为虚拟DAG图,并以此为基础定义了一种以最小化任务执行费用为目标的任务资源分配算法,为了防止其陷入局部最优,以其获得的解作为禁忌算法初始解并进行邻域搜索,以获得全局最优解;仿真实验表明:文章方法在迭代较少次数时获得了全局最优解684.21,较其它方法具有较大的优越性。
Aiming at the given resource allocation model in cloud computing only considering independent task scheduling, a resource al- locating model for cooperation--type task based on virtual DAG model was designed. Firstly, the resource allocating model for cooperation-- type task was designed, in order to schedule uniformly, the traditional DAG was transformed to virtual DAG, and the resource allocating al- gorism based on virtual DAG using the task executing cost as the goal. For prevent the algorism get the local optimum solution, the tabu al- gorism was used to get the neighbor search to obtain the global optimum solution. The simulation experiment shows the result in the solution in this paper only needing less iteration times can get the global solution 684. 21, so it has larger priority over the other methods.
出处
《计算机测量与控制》
北大核心
2013年第7期1892-1894,1898,共4页
Computer Measurement &Control
基金
2012年度河南省教育厅科学技术研究重点项目(12B520072)
关键词
资源分配
任务
云计算
禁忌算法
resource allocation task cloud computing tabu algorism