一种能耗—性能协调优化的虚拟机重放置策略

发布时间：2018-03-25 03:06

本文选题：能耗　切入点：性能感知　出处：《计算机应用研究》2016年11期

【摘要】：在云计算环境中虚拟机重放置方法方面,现有多数算法通常聚焦单一目标的优化,而聚焦一个单一目标通常会牺牲其他目标来达到最优效果,因此有必要考虑多目标权衡的虚拟机重放置方法。以降低能耗和保证虚拟机的服务质量为目标,提出一种能耗—性能协调的虚拟机重放置优化算法,即能耗—性能优化配合降序最佳适应算法(energy-performance awareness best fit descending virtual machine relocating,EPAR),把资源使用率转换为能耗,同时权衡了能耗和性能之间的关系。该算法在选择重放置虚拟机时使用自回归模型预测下一时间段的性能,有效避免了不必要的迁移。通过原型验证,EPAR算法能够在确保虚拟机服务的情况下,有效降低宿主机的能耗,避免不必要的虚拟机的迁移。
[Abstract]:In the aspect of virtual machine replacement in cloud computing environment, most existing algorithms usually focus on the optimization of a single objective, while focusing on a single goal usually sacrifices other objectives to achieve the optimal results. Therefore, it is necessary to consider the multi-objective trade-off method of virtual machine replacement. Aiming at reducing energy consumption and ensuring the quality of service of virtual machine, an optimization algorithm of virtual machine replacement with energy consumption and performance coordination is proposed. That is, energy consumption and performance optimization combined with descending order optimal adaptation algorithm, energy consumption and performance awareness best fit descending virtual machine relocating EPARN, which convert resource utilization to energy consumption, At the same time, the relationship between energy consumption and performance is weighed. The autoregressive model is used to predict the performance of the next period of time when the virtual machine is replaced. The prototype verification of EPAR algorithm can effectively reduce the energy consumption of host and avoid the unnecessary migration of virtual machine while ensuring the service of virtual machine.
【作者单位】：广西大学计算机与电子信息学院;
【基金】：国家自然科学基金资助项目(61063012,61363003) 国家科技支撑计划资助项目(2015BAH55F02) 广西自然科学基金资助项目(2012GXNSFAA053222) 广西高校优秀人才计划资助项目([2011]40)
【分类号】：TP302

【相似文献】