云计算中面向能耗降低的虚拟机多资源放置算法.pdfVIP

计算机测量与控制.2015.23 (1 2) 酶法、设计与应用| Computer Measurement Control • 4133 • 文章编号: 1671 - 4598( 2015) 12 - 4133 - 06 DOI: 10. 16526/j. cnki. 11-4762/tp. 2015. 12.064 申图分类号:TP391 文献标识码:A 云计算中面向能耗降低的虚拟机多资源放置算法 革新主1 ，啻~主1 ，乒 华l ， 1非本钱2 (1.四川大学电子信息学院，成都 610065; 2. 郑州机械研究所，郑州 450052) 摘要:为降低云计算系统产生的能耗.实现系统多类型资源的合理利用，提出虚拟机多资源能耗优化放置模型，并给出虚拟机多目 标资源随机多组优化算法 (RMRÜ); RMRO 算法随机生成多组虚拟机放置序列，并对每组序列进行优化，从中选出最优的序列作为最 终的虚拟机序列;基于 RMRO，进一步提出了 3 种虚拟机放置序列的再优化策略，通过实验对比，选择 MMBA 策略作为最佳策略;仿 真结果表明， RMRO 相比传统的 MBFD 和 MBFH 算法，能明显降低数据中心的能耗，同时使系统多种资源利用更合理。 关键词:云计算:虚拟机放置;能挺降低;多资源 Virtual Machine Multi - resource Placement AIgorithm to Reduce Energy Consumption in Cloud Computing l l l Z Wang Xinjie , Lei Yinjie , Yan Hua , Qiao Yongqin (1. College of Electronics and Information Engineering , Sichuan University , Chengdu 610065 , China; 2. Inst. of Zhengzhou Machinery Research , Zhengzhou 450052 , China) Abslract: To reduce the enormous energy produced by the c!oud computing system and achieve reasonable utilization of a variety of re sources , a virtual machine placing model with multi- resource energy consumption optimization is built and a vìrtual machine placement algo- rithm-multi-object resources random multiple sets re 一 optimization algorithm (RMRO) is proposed. In RMRO , the multi - group se quences of the virtual machine is randomly generated , and after each sequence is optimized , the optimal sequence is selected from the opti- mized multi-group sequenc臼. Based on RMRO , to optimize t