A Threshold-based Dynamic Resource Allocation Scheme for Cloud Computing

Compared to traditional distributed computing paradigms, a major advantage of cloud computing is the ability to provide more reliable, affordable, flexible resources for the applications (or users). The need to manage the applications in cloud computing creates the challenge of on-demand resource provisioning and allocation in response to dynamically changing workloads. Currently most of these existing methods focused on the optimization of allocating physical resources to their associated virtual resources and migrating virtual machines to achieve load balance and increase resource utilization. Unfortunately, these methods require the suspension of the cloud computing applications due to the mandatory shutdown of the associated virtual machines. In this paper, we study the resource allocation at the application level, instead of studying how to map the physical resources to virtual resources for better resource utilization in cloud computing environment. We propose a threshold-based dynamic resource allocation scheme for cloud computing that dynamically allocate the virtual resources (virtual machines) among the cloud computing applications based on their load changes (instead of allocating resources needed to meet peak demands) and can use the threshold method to optimize the decision of resource reallocation. The proposed threshold-based dynamic resource allocation scheme is implemented by using CloudSim, and experimental results show the proposed scheme can improve resource utilization and reduce the user usage cost. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [name organizer]