Distance and Traffic Based Virtual Machine Migration for Scalability in Cloud Computing

Abstract

Virtual machine migration is an important method for achieving scalability through optimized resource utilization in the modern data centers. Most of the previous works concentrated on how to migrate the virtual machinewith huge traffic demands in the cloud environment. It mainly focused on energy consumed by the virtual machines and the network traffic between them. None of the earlier algorithms focused from the client's perspective, like the delay faced by them to get their services processed. In this paper a new paradigm for virtual machine migration, based on the demands of the clients is considered. One of the clients demand is faster service time. To achieve this an algorithm called Virtual Machine Migration Approach Based on Distance and Traffic is developed. The methodology is based on the traffic and the geographical locations of the data centers. The algorithm is executed at regular intervals to check for the traffic in the network. It also checks for the distance of the data centers where the client request has to be placed. The request is placed to the nearest data center with less traffic. This improves the performance by reducing the round trip time. As the traffic is less so there is an optimized utilization of the resources. The reduction in round trip time and maintaining the round trip time without much fluctuation even in the case of a failure of one of the physical machinehelps to improve the performance by providing faster services to the clients.