PROJECT TITLE :

Autonomic Performance and Power Control for Co-Located Web Applications in Virtualized Datacenters

ABSTRACT:

In a very datacenter, complicated and time-varying interactions between various tiers and services of internet applications, and the competition of shared resources among co-located virtual machines have significant impact on the user perceived performance and power consumption of the underlying system. We propose and develop APPLEware, an autonomic middleware for joint performance and power control of co-located internet applications in virtualized datacenters. It features a distributed control structure that gives predictable performance and energy efficiency for giant advanced systems. It applies Machine Learning primarily based self-adaptive modeling to capture the complex and time-varying relationship between the application performance and allocation of resources to varied application parts, in the face of highly dynamic and bursty workloads. The distributed controllers coordinate with each different and allocate resources to fulfill the service level agreements of applications in an agile and energy-efficient manner. Experimental results based mostly on a testbed implementation with benchmark applications and large scale simulations demonstrate APPLEware's effectiveness, energy potency and scalability.