Dong Ki Kang , Seong Hwan Kim , Chan Hyun Youn

KIPS Transactions on Computer and Communication Systems, Vol. 3, No. 7, pp. 219-230, Jul. 2014
10.3745/KTCCS.2014.3.7.219,   PDF Download:

Abstract

In the cloud computing environment, cloud service users purchase and use the virtualized resources from cloud resource providers on a pay as you go manner. Typically, there are two billing plans for computing resource allocation adopted by large cloud resource providers such as Amazon, Gogrid, and Microsoft, on-demand and reserved plans. Reserved Virtual Machine(VM) instance is provided to users based on the lengthy allocation with the cheaper price than the one of on-demand VM instance which is based on shortly allocation. With the proper mixture allocation of reserved and on-demand VM corresponding to users`` requests, cloud service providers are able to reduce the resource allocation cost. To do this, prior researches about VM allocation scheme have been focused on the optimization approach with the users`` request prediction techniques. However, it is difficult to predict the expected demands exactly because there are various cloudservice users and the their request patterns are heavily fluctuated in reality. Moreover, the previous optimization processing techniques might require unacceptable huge time so it is hard to apply them to the current cloud computing system. In this paper, we propose the cloud brokering system with the adaptive VM allocation schemes called A3R(Adaptive 3 Resource allocation schemes) that do not need any optimization processes and kinds of prediction techniques. By using A3R, the VM instances are allocated to users in response to their service demands adaptively. We demonstrate that our proposed schemes are able to reduce the resource use cost significantly while maintaining the acceptable Quality of Service(QoS) of cloud service users through the evaluation results.

Statistics
Cite this article