A Traffic and Power-aware Algorithm for Virtual Machine Placement in Cloud Data Center

Abstract

In cloud computing model, virtualized resources is provided to customers as a service over the Internet with reasonable price. This model effectively helps customers focus on their creative business because computing resources are provided on demand by cloud provider. Because of the convenient for cloud customers, the demand for cloud resource grows, thus make cloud data center enlarge and energy consumption becomes a critical issue for cloud provider as well as the carbon dioxide emission. In order to save energy, virtual machines are consolidated to reduce the number of servers required to host them. However, for applications that require communication among services, this migration can increase the latency which causes bad effect on their performance. This paper presents an algorithm that improve communication performance by reducing overall traffic cost of virtual machines and while energy by increasing CPU utilization.