A Model-Based Approach for Optimizing Power Consumption of IaaS

被引：3

作者：

Tam Le Nhan ^{[1
]}

Sunye, Gerson ^{[2
]}

Jezequel, Jean-Marc ^{[1
]}

机构：

[1] Univ Rennes 1, INRIA, Rennes, France

[2] Univ Nantes, INRIA, F-44035 Nantes, France

来源：

2012 IEEE SECOND SYMPOSIUM ON NETWORK CLOUD COMPUTING AND APPLICATIONS (NCCA 2012) | 2012年

关键词：

Model-driven deployment; feature models; cloud computing; virtual image provisioning; power consumption; DEPLOYMENT;

D O I：

10.1109/NCCA.2012.22

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Virtual Machine Image (VMI) provisioning is an important process of Infrastructure as a Service delivery model to provide virtual images in Cloud Computing. The power consumption and energy efficiency of VMI provisioning process depend not only on the hardware infrastructure, but also on the VMI's configuration, which helps to compose, configure and deploy VMIs in Cloud Computing environments. The major issue of improving the energy efficiency of VMI provisioning process is how to reduce the power consumption while ensuring the compatibility of software components installed in a virtual machine image. This paper describes a model-driven approach to improve the energy efficiency of VMI provisioning in Cloud Computing. This approach considers virtual images as product lines and uses feature models to represent their configurations. It uses model-based techniques to handle VMI specialization, automatic deployment and reconfiguration. The approach aims at minimizing the amount of unneeded software installed in VMIs, and thus to reduce the power consumption of VMI provisioning as well as the data transfer through the network.

引用

页码：31 / 39

页数：9