Interference aware prediction mechanism for auto scaling in cloud

Advancements in cloud computing has transformed it into the most promising computing paradigm for business organizations. In a dynamic cloud environment, Virtual Machine (VM) migration is a critical step in resource management, especially in large scale datacenters. Most of the VM migration and load balancing policies are based on power consumption and response time, with little attention on the interferences caused due to VM migrations. Such interferences degrade the overall performance of the system, and consequently violates the service level agreement (SLA) between the customer and the provider. This paper introduces an interference aware prediction mechanism for VM migration, with auto scaling. The automatic scaling policies help to handle sudden load changes with precise prediction and minimum VM migration. The experimental results and comparative analysis show that the proposed model is capable of predicting the interference more accurately. It also provides an optimum threshold range for VM migration.