云计算数据中心虚拟机节能管理机制研究

云计算数据中心的耗电量巨大,但绝大多数的云计算数据中心并没有取得较高的资源利用率,通常只有15%-20%,有相当数量的服务器处于闲置工作状态,导致大量的能耗白白浪费。为了能够有效降低云计算数据中心的能耗,提出了一种适用于异构集群系统的云计算数据中心虚拟机节能调度算法(PVMAP算法),仿真实验结果表明：与经典算法PABFD相比,PVMAP算法的能耗明显更低,可扩展性与稳定性都更好。与此同时,随着〈Hosts,VMs〉数目的不断增加,PVMAP 算法虚拟机迁移总数和关闭主机总数的增长幅度都要低于PABFD算法。

Research on Virtual Machine Energy Saving Management Mechanism in Cloud Computing Data Center

The power consumption of cloud computing data centers is huge. Most cloud computing data centers do not achieve high resource utilization. Usually only 15%-20%, and a considerable number of servers are idle, resulting in a large number of The energy consumption is wasted. In order to effectively reduce the energy consumption of cloud computing data centers, a cloud computing data center virtual machine energy-saving scheduling algorithm (PVMAP algorithm) suitable for heterogeneous cluster systems is proposed. Simulation results show that compared with the classical algorithm PABFD, PVMAP The energy consumption of the algorithm is significantly lower, and the scalability and stability are better. At the same time, with the continuous increase in the number of , the total number of virtual machine migrations and the total number of shutdown hosts in the PVMAP algorithm will be lower than the PABFD algorithm.