期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2014
期号：ICETS
页码：285
出版社：S&S Publications
摘要：Cloud computing allows cloud user toscale up and down their resource usage based onneeds. Many of the cloud models come fromresource multiplexing through virtualizationtechnology. In this paper, we present a system thatuses virtualization technology to allocate resourcedynamically based on application demands andsupport green computing by optimizing the numberof servers in use. We introduce the concept of“Temperature” to measure the unevenness in themultidimensional resource of a server. The result oftemperature value, we can combine different typesof workloads dynamically and improve the overallutilization of server resources. We develop a set ofheuristics that prevent overload in the systemeffectively while saving energy used. Trace drivensimulation and experiment results demonstrate thatour algorithm achieves good performance.
关键词：Cloud computing; virtual machine live;migration; hot and cold spots; resource;management; green computing
