Cloud Computing, Security, Privacy in New Computing Environments. 7th International Conference, CloudComp 2016, and First International Conference, SPNCE 2016, Guangzhou, China, November 25–26, and December 15–16, 2016, Proceedings

Research Article

Correlation-Aware Virtual Machine Placement in Data Center Networks

  • @INPROCEEDINGS{10.1007/978-3-319-69605-8_3,
        author={Tao Chen and Yaoming Zhu and Xiaofeng Gao and Linghe Kong and Guihai Chen and Yongjian Wang},
        title={Correlation-Aware Virtual Machine Placement in Data Center Networks},
        proceedings={Cloud Computing, Security, Privacy in New Computing Environments. 7th International Conference, CloudComp 2016, and First International Conference, SPNCE 2016, Guangzhou, China, November 25--26, and December 15--16, 2016, Proceedings},
        proceedings_a={CLOUDCOMP},
        year={2017},
        month={11},
        keywords={Virtual machine Prediction Correlation Placement},
        doi={10.1007/978-3-319-69605-8_3}
    }
    
  • Tao Chen
    Yaoming Zhu
    Xiaofeng Gao
    Linghe Kong
    Guihai Chen
    Yongjian Wang
    Year: 2017
    Correlation-Aware Virtual Machine Placement in Data Center Networks
    CLOUDCOMP
    Springer
    DOI: 10.1007/978-3-319-69605-8_3
Tao Chen1,*, Yaoming Zhu1,*, Xiaofeng Gao1,*, Linghe Kong1,*, Guihai Chen1,*, Yongjian Wang2,*
  • 1: Shanghai Jiao Tong University
  • 2: The Third Research Institute of Ministry of Public Security
*Contact email: tchen@sjtu.edu.cn, grapes_islet@sjtu.edu.cn, gao-xf@cs.sjtu.edu.cn, linghe.kong@sjtu.edu.cn, gchen@cs.sjtu.edu.cn, wangyongjian@stars.org.cn

Abstract

The resource utilization (CPU, memory) is a key performance metric in data center networks. The goal of the cloud platform supported by data center networks is achieving high average resource utilization while guaranteeing the quality of cloud services. Previous work focus on increasing the time-average resource utilization and decreasing the overload ratio of servers by designing various efficient virtual machine placement schemes. Unfortunately, most of virtual machine placement schemes did not involve the service level agreements and statistical methods. In this paper, we propose a correlation-aware virtual machine placement scheme that effectively places virtual machines on physical machines. First, we employ Neural Networks model to forecast the resource utilization trend according to the historical resource utilization data. Second, we design correlation-aware placement algorithms to enhance resource utilization while meeting the user-defined service level agreements. The results show that the efficiency of our virtual machine placement algorithms outperform the previous work by about 15%.