能耗感知下云资源三支粒度调度策略研究

云资源调度是云数据中心的一种重要节能方式。然而，实际云平台中，受单一物理机资源限制，存在虚拟机资源竞争和利用率低的问题。对此，通过分析虚拟机负载相似性及资源占有度问题，提出一种基于三支决策的能耗感知虚拟机迁移策略。首先，在虚拟机迁移过程中，设计云资源的三支划分策略，并使用K-means算法在划分区域选择待迁移的虚拟机序列；其次，依据虚拟机与物理机的负载相似度，获取虚拟机放置顺序；最后，依托CloudSimPlus云仿真平台验证了所提方法的有效性。实验结果表明，所提方法能够有效降低云能耗，实现资源充分利用。

Energy consumption-aware virtual machine migration strategy based on three-way decision

Cloud resource scheduling is an essential energy-saving method in cloud datacenter. However, this method still has some problems in the scheduling process: load similarity of virtual machines and low utilization of cloud resources. Therefore, for solving the problem of low resource utilization and waste of energy consumption, this paper proposed an energy consumption-aware virtual machine migration strategy based on the three-way decision for these problems. Firstly, it designed a trisecting strategy of multi-granularity for virtual machine migration and used the K-means method to cluster for each division region and then selected the virtual machine sequence that needed to be migrated. Secondly, it calculated the similarity between the virtual and physical machine resources and placed the virtual machin. Finally, a simulation experiment is conducted on the CloudSimPlus platform, and the results show that this method can effectively reduce energy consumption and fully utilize resources.