绿色云计算环境中基于温度感知的虚拟机迁移策略

Temperature-aware virtual machine migration strategy for green cloud computing environments

虚拟机迁移策略是提高云数据中心的物理主机利用率和降低能量消耗的关键技术。提出了绿色云计算环境中基于温度感知的虚拟机迁移策略(temperature-aware virtual machine migration,TA-VMM)。主要考虑物理主机处理器的温度情况作为选择和分配虚拟机的关键因素。建立了虚拟机迁移过程中物理资源的温度和能量的数学模型;以最小温度距离(minimum temperature distance,MTD)作为虚拟机选择的重要考虑因素;以温度距离比率(temperature distance ratio,TDR)作为虚拟机重新分配的重要考虑因素;以Cloudsim3.0云计算模拟器中的物理主机超负载检测算法和虚拟机分配策略作为TA-VMM的性能比较对象。利用Cloudsim3.0模拟器建立了TA-VMM的仿真环境,实验结果表明,与Cloudsim中已有的虚拟机迁移策略比较,TA-VMM在节省能量和虚拟机迁移次数方面具有较好的性能,服务协议(service level agreement,SLA)违规方面只有极小的增加。

Virtual machine migration strategy is one of the most important techniques for physical resource usage and power cost reduction in cloud data centers.A temperature-aware virtual machine migration strategy for green cloud computing environments named TA-VMM was proposed in this paper.As a critical factor,the host temperature had been taken into account during the virtual machine selection and allocation.The mathematic model of temperature and energy consumption in physical resources was constructed subsequently in TA-VMM.Minimum temperature distance(MTD)was used to select VMs to be migrated.Temperature distance ratio(TDR)was also adopted to find a suitable host for accommodating the migrated VMs.Host overloading detection algorithms and four VM selection policies in Cloudsim 3.0 had been used for comparison purposes.TA-VMM was implemented and evaluated on Cloudsim 3.0.The simulation results show that TA-VMM mechanism brings significant benefits in terms of energy saving and VMs migration numbers.The SLA violation increased slightly compared with other migration strategies in Cloudsim.