ScienceDirect® Home Skip Main Navigation Links
You have guest access to ScienceDirect. Find out more.
 
Home
Browse
My Settings
Alerts
Help
 Quick Search
 Search tips (Opens new window)
    Clear all fields    
advertisementadvertisement
Data & Knowledge Engineering
Volume 63, Issue 3, December 2007, Pages 894-918
25th International Conference on Conceptual Modeling (ER 2006) - ’Four of the best papers presented
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Article
Purchase PDF (656 K)

 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
doi:10.1016/j.datak.2007.05.004    How to Cite or Link Using DOI (Opens New Window)
Copyright © 2007 Elsevier B.V. All rights reserved.

Adaptive searching and replication of images in mobile hierarchical peer-to-peer networks

Kumar Abhinay Rathorea, Sanjay K. Madriaa, Corresponding Author Contact Information, E-mail The Corresponding Author and Takahiro Harab, E-mail The Corresponding Author

aDepartment of Computer Science, University of Missouri-Rolla, 1870, Miner Circle Drive, Rolla, MO 65409, United States bDepartment of Multimedia Engineering, Osaka University, Japan

Received 30 January 2007; 
revised 26 April 2007; 
accepted 18 May 2007. 
Available online 9 June 2007.

Purchase the full-text article



References and further reading may be available for this article. To view references and further reading you must purchase this article.

Abstract

Due to the limitation of resources in mobile handheld devices and bandwidth constraints in wireless networks, it is important to efficiently manage image content and traffic to improve network throughput and response time. The efficient distribution of images in wireless networks is based on many parameters like the quality of service requirement, available bandwidth, restricted memory and diverse user profiles. We consider digital images as data objects accessed in a hierarchical mobile ad-hoc peer-to-peer network, referred as M-P2P. Our objective is to optimize the number of replicas of images in such a network architecture based on the resource limitations of the requesting peers equipped with miniature mobile devices as well as of wireless constraints in mobile ad-hoc networks (MANET). While replicating images, fragments of different resolution and their residues are used to optimize the traffic in the network and to decrease the search turnaround time. We call this replication algorithm as Ada-Rep. Performance evaluation is done by simulating Ada-Rep, base replication and uniform replication methods to evaluate parameters such as response time, failure rate, memory usage, traffic etc. Our results prove the efficiency and better performance of Ada-Rep.

Keywords: Adaptive; Mobile peer-to-peer; Searching; Replication

Article Outline

1. Introduction
2. Related work
3. System model
4. Image re-sampling
5. Ada-Rep algorithm
5.1. Costs involved
5.1.1. Transcoding cost (Cs)
5.1.2. Transmission cost (Ct)
5.2. Replication decision
5.3. Replication factor
5.4. Trust values
5.5. Ada-Rep using flooding
5.6. Ada-Rep using multicast
5.7. Application example
5.8. Replication factor calculations
6. Simulation
6.1. Simulation environment
6.2. Simulation results
6.2.1. Flooding and multicast comparison
6.2.1.1. Flooding and multicast average response time
6.2.1.2. Flooding and multicast network traffic
6.2.2. Ada-Rep and base replication scheme comparison
6.2.2.1. Ada-Rep and base replication replica count
6.2.2.2. Ada-Rep and base replication average response time
6.2.2.3. Ada-Rep and base replication memory usage
6.2.2.4. Ada-Rep and base replication hop count
6.2.2.5. Ada-Rep and base replication failure rate
7. Conclusions and future work
References
Vitae





















Data & Knowledge Engineering
Volume 63, Issue 3, December 2007, Pages 894-918
25th International Conference on Conceptual Modeling (ER 2006) - ’Four of the best papers presented
 
Home
Browse
My Settings
Alerts
Help
Elsevier.com (Opens new window)
About ScienceDirect  |  Contact Us  |  Information for Advertisers  |  Terms & Conditions  |  Privacy Policy
Copyright © 2008 Elsevier B.V. All rights reserved. ScienceDirect® is a registered trademark of Elsevier B.V.