抽象的

Scheduling using Optimization Decomposition in Wireless Network with Time Performance Analysis

Aparna.C, Kavitha.V.kakade

Virtualization is a key technology underlying multi server computing platforms, where applications encapsulated within Virtual Machines are dynamically mapped onto a pool of physical servers. In this paper, we argue that multi server providers can significantly lower operational costs, and improve hosted application performance, by accounting for affinities and conflicts between co-placed Virtual Machines. The estimated Virtual Machine size is the basis for allocating resources commensurate with demand. In contrast to the traditional practice of estimating the size of Virtual Machines individually, we propose a joint-virtual machine provisioning approach in which multiple virtual machines are consolidated and provisioned together, based on an estimate of their aggregate capacity needs. This new approach exploits statistical multiplexing among the workload patterns of multiple virtual machines, i.e., the peaks and valleys in one workload pattern do not necessarily coincide with the others. Thus, the unused resources of a low utilized virtual machine can be borrowed by the other co-located virtual machines with high utilization. Compared to individual-virtual machine based provisioning; joint-virtual machine provisioning could lead to much higher resource utilization. This paper presents three design modules to enable such a concept in practice. Specifically, a performance constraint describing the capacity need of a virtual machine for achieving a certain level of application performance; an algorithm for estimating the aggregate size of multiplexed virtual machines; a virtual machine selection algorithm that seeks to find those virtual machine combinations with complementary workload patterns.