DDBS:云数据中心基于数据依赖的虚拟机选择策略

DDBS: a Data Dependency Based Virtual Machine Selection Strategy for Cloud Data Centers

提出了一种云数据中心基于数据依赖的虚拟机选择算法DDBS(data dependency based VM selection).参考Cloudsim项目中方法,将虚拟机迁移过程划分为虚拟机选择操作(VM selection)和虚拟机放置(VM placement)操作.DDBS在虚拟机选择过程中考虑虚拟机之间的数据依赖关系,把选择与迁移代价值比较小的虚拟机形成侯选虚拟机列表,配合后续的虚拟机放置策略最终完成虚拟机的迁移过程.以Cloudsim云计算模拟器中的虚拟机选择及放置策略作为性能比较对象.实验结果表明:DDBS与Cloudsim中已有能量感知的算法比较起来,在虚拟机迁移次数和能量消耗方面都比较少,可用性比较高.

A data dependency based virtual machine selection strategy for cloud data centers called DDBS was proposed in this paper.DDBS referred Cloudsim Project and thus virtual machine migration was composed of VM selection and VM placement. Based on the dependency,between the tasks,the cost to migrate the virtual machines was calculated and the policy will select the virtual machine which requires less cost compared to others. The VM placement policy selects the target physical machine on which the migrating VM should be deployed. Energy aware Algorithms and several VM migration policies in Cloudsim were also used for comparison purposes.Simulation results show that DDBS reduced the cost incurred on the system due to migration. The reduced number of virtual machine migrations and improved energy-efficiency had been also obtained in our test.