Table of Contents Author Guidelines Submit a Manuscript
Scientific Programming
Volume 2016 (2016), Article ID 5635673, 9 pages
http://dx.doi.org/10.1155/2016/5635673
Research Article

RVLBPNN: A Workload Forecasting Model for Smart Cloud Computing

1School of Computer Science and Telecommunication Engineering Jiangsu University, Jiangsu, China
2Department of Computing and Mathematics, University of Derby, Derby, UK
3Department of Computer Science, Boise State University, Boise, USA

Received 28 July 2016; Accepted 19 September 2016

Academic Editor: Wenbing Zhao

Copyright © 2016 Yao Lu et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Given the increasing deployments of Cloud datacentres and the excessive usage of server resources, their associated energy and environmental implications are also increasing at an alarming rate. Cloud service providers are under immense pressure to significantly reduce both such implications for promoting green computing. Maintaining the desired level of Quality of Service (QoS) without violating the Service Level Agreement (SLA), whilst attempting to reduce the usage of the datacentre resources is an obvious challenge for the Cloud service providers. Scaling the level of active server resources in accordance with the predicted incoming workloads is one possible way of reducing the undesirable energy consumption of the active resources without affecting the performance quality. To this end, this paper analyzes the dynamic characteristics of the Cloud workloads and defines a hierarchy for the latency sensitivity levels of the Cloud workloads. Further, a novel workload prediction model for energy efficient Cloud Computing is proposed, named RVLBPNN (Rand Variable Learning Rate Backpropagation Neural Network) based on BPNN (Backpropagation Neural Network) algorithm. Experiments evaluating the prediction accuracy of the proposed prediction model demonstrate that RVLBPNN achieves an improved prediction accuracy compared to the HMM and Naïve Bayes Classifier models by a considerable margin.