基于蚂蚁群体智能的多目标虚拟机合并优化

MULTI-OBJECTIVE VIRTUAL MACHINE CONSOLIDATION OPTIMIZATION BASED ON ANT COLONY INTELLIGENT

为了优化数据中心中虚拟机的合并过程,提高物理主机利用率和降低虚拟机的迁移代价,利用蚂蚁群体智能方法提出一种新的多目标虚拟机合并算法。该算法基于重要性按序优化了两个目标,第一目标是最大化虚拟机合并过程中的主机释放量。同时,由于虚拟机迁移是资源密集型操作,第二目标选择最小化虚拟机迁移量。通过修正的蚂蚁搜索过程,最终得到了最优的虚拟机合并效果。与两种代表性蚂蚁算法进行实验对比,结果表明,在所有四个实验场景下,新算法在多数场景和参数配置条件下得到的主机释放量、虚拟机迁移量、包装效率以及算法运行时间均有更佳表现。

In order to optimizate virtual machines consolidation process in data center,improve the physical hosts utilization and reduce the virtual machines migraiton cost,a novel multi-objective virtual machines consolidation algorithm using ant colony intelligent is designed in this paper.It optimizes two objectives that are ordered by their importance.The first and foremost objective is the proposed algorithm is to maximize the number of released physical hosts.Moreover,since virtual machine migration is a resource-intensive operation,is also tries to minimize the number of virtual machine migration.Our algorithm finally obtains the optimal virtual machine consolidation effect through modified ant search process.Some constrast experiments are carried on with the other two kinds of typical ant algorithms.The experimental results show that,in all four test scenarios,under the condition of most scenarios and parameter configuration,our new algorithm has a better performance on the number of released physical hosts,the number of virtual machine migration,the packing efficiency and the algorithm running time.