云数据中心高效的虚拟机整合方法

被引:5
作者
喻新荣 [1 ]
李志华 [1 ,2 ]
闫成雨 [1 ]
李双俐 [1 ]
机构
[1] 江南大学物联网工程学院
[2] 江南大学物联网应用技术教育部工程研究中心
关键词
云计算; 虚拟机整合; 高斯混合模型; 主机过载概率; 服务质量;
D O I
暂无
中图分类号
TP302 [设计与性能分析];
学科分类号
081201 ;
摘要
针对传统虚拟机整合(VMC)方法难以保持主机工作负载长期稳定的问题,提出一种基于高斯混合模型的高效虚拟机整合(GMM-VMC)方法。为了准确地预测主机负载的变化趋势,首先,使用高斯混合模型(GMM)对活动物理主机的工作负载历史记录进行拟合;然后,根据活动物理主机工作负载的GMM和主机自身的资源配置情况计算主机的过载概率,并根据过载概率判定主机是否存在过载风险;对存在过载风险的物理主机,根据部署在该物理主机上的虚拟机对降低主机过载风险的贡献和虚拟机迁移所需的时间这两个指标进行待迁移虚拟机选择;最后,使用GMM估算待迁移虚拟机对各个目标主机过载风险的影响,并选择受影响最小的主机作为目标主机。通过Cloud Sim仿真平台模拟该GMM-VMC方法,并根据能源消耗、服务质量(QoS)、整合效率等指标与已有的整合方法进行对比,实验结果表明,GMM-VMC方法能够有效地降低数据中心能耗,提高服务质量。
引用
收藏
页码:550 / 556
页数:7
相关论文
共 16 条
[1]  
LiRCUP:Linear regression based CPU usage prediction algorithm for live migration of virtual machines in data centers. Farahnakian F,Liljeberg P,Plosila J. Proceedings of the 39th EUROMICRO Conference on Software Engineering and Advanced Applications (SEAA’’13) . 2013
[2]  
Energy efficient allocation of virtual machines in cloud computing environments based on demand forecast. Cao J,Wu Y,Li M. Advances in Grid and Pervasive Computing . 2012
[3]  
Stochastic load balancing for virtual resource management in datacenters. Yu L,Chen L,Cai Z,et al. IEEE Transactions on Cloud Computing . 2016
[4]  
Toward dynamic and attribute based publication, discovery and selection for cloud computing[J] . Andrzej Goscinski,Michael Brock. &nbspFuture Generation Computer Systems . 2010 (7)
[5]  
CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms[J] . Rodrigo N.Calheiros,RajivRanjan,AntonBeloglazov,César A. F.De Rose,RajkumarBuyya. &nbspSoftw: Pract. Exper. . 2010 (1)
[6]  
Energy-aware resource allocation heuristics for efficient management of data centers for Cloud computing[J] . Anton Beloglazov,Jemal Abawajy,Rajkumar Buyya. &nbspFuture Generation Computer Systems . 2011 (5)
[7]  
Effective vm sizing in virtualized data centers. Chen M,Zhang H,Su Y Y,et al. Proceedings of IFIP/IEEE International Symposium on Integrated Networking Management . 2011
[8]  
Efficient VM placement with multiple deterministic andstochastic resources in data centers. Jin H,Pan D,Xu J, et al. Global Communications Conference (GLOBECOM),2012IEEE . 2012
[9]  
Adaptive background mixture models for real-time tracking. Stauffer C,Grimson W E L. Proceedings of IEEE Conference on Computer Vision and Patern Recognition . 1999
[10]  
Power provisioning for a warehouse-sizedcomputer. Fan X,Weber W,Barroso L. A. Proceedings of the34th annual international symposium on Computerarchitecture . 2007