AMS: Adaptive Migration Scheme in Cloud Computing

Due to the necessity of high availability for Cloud Systems, most organizations need cloud services which minimize system down-time. Virtual Machine (VM) Migration is a simple solution for what is called a Hot-Spot or highly utilized PM. Live Migrating VMs allows migration of VMs while they are running their applications with no shutdown or down-time. Therefore, it provides Hot-Spot relieve, helps in Business Continuity, and provides a high available system. In this paper, an adaptive migration scheme (AMS) is proposed in order to preserve the system’s load balance state. It considers migrating VMs in groups, where each group includes a number of VMs increases from two to a maximum concurrent limit. AMS provides a way to find a maximum concurrent limit for the number of migrated VMs to be used to enhance the migration process. AMS is applied on a real case study. Two metrics are used to evaluate the improvements in migrations; concurrent time reduction and transfer rate improvement. The experimental results show that AMS achieves a time reduction percentage reaches 44%. This percentage is increased proportionally with the increasing of used memory. In addition, the migrated memory transfer rate is improved by a ratio ranges from 27% to 86%.