Matrix based proactive resource provisioning in mobile cloud environment

Sandeep K. Sood

doi:10.1016/j.simpat.2014.06.004

Return

Matrix based proactive resource provisioning in mobile cloud environment

2015-01-01

PRE

Sandeep K. Sood *

Rajinder Sandhu

DOI：10.1016/j.simpat.2014.06.004

Original

Original request for help

Save

Abstract

En 中文

Mobile cloud computing is a dynamic, virtually scalable and network based computing environment where mobile device acts as a thin client and applications run on remote cloud servers. Mobile cloud computing resources required by different users depend on their respective personalized applications. Therefore, efficient resource provisioning in mobile clouds is an important aspect that needs special attention in order to make the mobile cloud computing a highly optimized entity. This paper proposes an adaptive model for efficient resource provisioning in mobile clouds by predicting and storing resource usages in a two dimensional matrix termed as resource provisioning matrix. These resource provisioning matrices are further used by an independent authority to predict future required resources using artificial neural network. Independent authority also checks and verifies resource usage bill computed by cloud service provider using resource provisioning matrices. It provides cost computation reliability for mobile customers in mobile cloud environment. Proposed model is implemented on Hadoop using three different applications. Results indicate that proposed model provides better mobile cloud resources utilization as well as maintains quality of service for mobile customer. Proposed model increases battery life of mobile device and decreases data usage cost for mobile customer. (C) 2014 Elsevier B.V. All rights reserved.

Keywords:

Cloud computing

Mobile cloud

Resource provisioning

Resource provisioning matrix

Back propagation neural networks

Resource bill calculation

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.