Machine Learning Based Live VM Migration for Efficient Cloud Data Center

被引:3
作者
Zaw, Ei Phyu [1 ]
机构
[1] Univ Comp Studies, Pathein, Pathein, Myanmar
来源
BIG DATA ANALYSIS AND DEEP LEARNING APPLICATIONS | 2019年 / 744卷
关键词
Virtual machine; Live VM migration; Machine learning; Total migration time;
D O I
10.1007/978-981-13-0869-7_15
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Increasing users' service demands, large-scale IaaS cloud data centers are used in everywhere. IaaS cloud data centers run with thousands of heterogeneous servers and so virtualization is state-of-arts in today IT trend to reduce the energy consumption. Virtualization is a methodology of logically dividing computer resources. It allows multiple virtual machines, with heterogeneous operating systems to run side by side on the same physical machine. Migration operation system instance across distinct physical hosts is a useful tool for administrators of data centers. Live migration is done by performing most of the migration while the operating system is still running, achieving very little downtime. By carrying out the majority of migration while OSes continue to run, we achieve impressive performance with minimal service downtime and total migration time. In this paper, machine learning based working set prediction is proposed to reduce the total migration time. It uses the prediction model with historical data during the live VM migration process. At first, it trains experimental dataset which includes the performance parameters collected from various workloads by machine learning techniques to build the best prediction model and then predict the working set which can affect the total migration time. We evaluated the effectiveness of the working set prediction algorithm with various workloads with simulation model and the experimental result shows that this method can more reduce the total migration time in live VM migration than XEN's default pre-copy based live migration.
引用
收藏
页码:130 / 138
页数:9
相关论文
共 7 条
  • [1] [Anonymous], 2007, P LINUX S
  • [2] Clark C, 2007, TLS-TIMES LIT SUPPL, P24
  • [3] HINES M. R., 2009, P INT C VIRT EX ENV, P51
  • [4] Li L, 2002, 2002 INTERNATIONAL SYMPOSIUM ON EMPIRICAL SOFTWARE ENGINEERING, PROCEEDINGS, P91, DOI 10.1109/ISESE.2002.1166929
  • [5] Nelson M, 2005, USENIX Association Proceedings of the General Track: 2005 UNENIX Annual Technical Conference, P391
  • [6] Vaidyanathan K., 1999, Proceedings 10th International Symposium on Software Reliability Engineering (Cat. No.PR00443), P84, DOI 10.1109/ISSRE.1999.809313
  • [7] A regression-based analytic model for capacity planning of multi-tier applications
    Zhang, Qi
    Cherkasova, Ludmila
    Mi, Ningfang
    Smirni, Evgenia
    [J]. CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2008, 11 (03): : 197 - 211