Task Dependency Aware Selection (TDAS) in Cloud

Cloud Computing is one of the leading technologies that offer a promising future. One of the main tools that play a pivotal role in making Cloud a reality is virtualization. On one hand, virtualization provides Cloud with its benefits; while on the other hand, it gives rise to many decision problems. A significant decision problem among these is the virtual machine selection problem. Some of the works in literature aim to carry out migration in a cost-efficient manner, but, the dependencies among tasks have not been taken into consideration in these approaches. This paper proposes a technique that considers the dependency among the tasks running on different virtual machines during virtual machine migration. Experimental analysis shows that the proposed approach reduces the cost incurred on the system due to migration, and also improves the energy-efficiency of the system. The enhanced performance of the proposed system, due to the reduced number of virtual machine migrations indicates that there is much scope for this approach.