Decentralized Predictive Secure VS Placement in Cloud Environment

Abstract

Hosts in distributed cloud environment configured with Local Resource Monitors (LRM) that runs autonomously, monitors underlying host's resource usage and balances underlying host's resource usage by migrating Virtual Machine (VM) to other hosts. LRM takes decision for VM migration at fixed interval considering own current CPU usage and the other hosts CPU usage. The peer hosts unawares about the decision taken by the other hosts LRM about VS migration. As a result of this, there are chances that the same host selection from multiple hosts during the VS placement. This results into destination host to over utilized or the LRM at destination host initiates the VS migration. Several approaches have been proposed for decentralized VS placement that includes two threshold based VS placement, hypercube based VM placement, Ant Colony based VS placement. These approaches does not considers future behavior of the destination hosts after VS placement. This paper discusses the decentralized peer to peer Virtual Server Placement Approach (DPPVP) that considers host's current as well future CPU utilization for VS placement. The results shows that the proposed system avoids the over utilization of the destination host and host identification by the multiple hosts during VS placement.