Effective Resource Allocation in Cloud Systems

Abstract

As the virtual machine (VM) technology being developed rapidly and services being used by multiple users, resources in cloud systems needs to be shared more effectively and allocated on demand. Cloud computingenvironment involves high cost infrastructure on one hand andneed high scale computational resources on the other hand.These resources need to be provisioned (allocation andscheduling) to the end users in most efficient manner so that thetremendous capabilities of cloud are utilized effectively andefficiently.But there are some constraints on cloud computing like payment budget and on demand resources.This paper formulates a deadline-driven resource allocation approach based on VM resource isolation technology, and also propose a novel solution with polynomial time, which could minimize users’ payment in terms of their expected deadlines. By analyzing the upper bound of task execution length based on the possibly inaccurate workload prediction, further propose an error-tolerant method to guarantee task’s completion within its deadline. Validate its effectiveness over a real VM-facilitated cluster environment under different levels of competition