By Topic

An SMDP-Based Service Model for Interdomain Resource Allocation in Mobile Cloud Networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
Hongbin Liang ; Sch. of Inf. Sci. & Technol., Southwest Jiaotong Univ., Chengdu, China ; Cai, L.X. ; Dijiang Huang ; Xuemin Shen
more authors

Mobile cloud computing is a promising technique that shifts the data and computing service modules from individual devices to a geographically distributed cloud service architecture. A general mobile cloud computing system is comprised of multiple cloud domains, and each domain manages a portion of the cloud system resources, such as the Central Processing Unit, memory and storage, etc. How to efficiently manage the cloud resources across multiple cloud domains is critical for providing continuous mobile cloud services. In this paper, we propose a service decision making system for interdomain service transfer to balance the computation loads among multiple cloud domains. Our system focuses on maximizing the rewards for both the cloud system and the users by minimizing the number of service rejections that degrade the user satisfaction level significantly. To this end, we formulate the service request decision making process as a semi-Markov decision process. The optimal service transfer decisions are obtained by jointly considering the system incomes and expenses. Extensive simulation results show that the proposed decision making system can significantly improve the system rewards and decrease service disruptions compared with the greedy approach.

Published in:

Vehicular Technology, IEEE Transactions on  (Volume:61 ,  Issue: 5 )