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    
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Article
Purchase PDF (306 K)

Article Toolbox
 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
View Record in Scopus
 
doi:10.1016/j.peva.2005.03.003    
How to Cite or Link Using DOI (Opens New Window)

Copyright © 2006 Elsevier B.V. All rights reserved.

Quantitative performance comparison of different content distribution modes

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.

Samuli Aaltoa, E-mail The Corresponding Author, Janne Aaltonenb, E-mail The Corresponding Author and Jouni Karvoa, Corresponding Author Contact Information, E-mail The Corresponding Author

aHelsinki University of Technology (TKK), Networking Laboratory, P.O. Box 3000, FIN-02015 TKK, Finland

bNokia Corporation, P.O. Box 4, FIN-20521 TURKU, Finland


Received 11 December 2003; 
revised 1 December 2004. 
Available online 11 May 2005.

Abstract

We develop methods for quantifying the gain of using multicast or a combination of broadcast and unicast for transmitting popular content in telecommunication networks. The gain is evaluated in a single link, such as the radio interface of a cellular network. Two approaches to define such a gain are presented: one based on the average link occupancy, and another based on the blocking probability. The developed methods enable determining how popular the most popular contents should be in order to justify the use of multicast or a combination of broadcast and unicast from a performance point of view.

Keywords: Multicast; Broadcast; Content distribution; Performance comparison; Zipf-like distributions

Article Outline

1. Introduction
2. Comparison method based on average link occupancy
2.1. System and user models
2.2. Unconstrained capacity
2.3. Comparison method
3. Comparison method based on blocking probability
3.1. Loss system model
3.2. Unicast mode
3.3. Multicast mode
3.4. Broadcast-unicast mode
3.5. Comparison method
4. Comparison method for large systems
4.1. Asymptotic loss system model
4.2. Bahadur–Rao approximation
4.3. Comparison method
5. Numerical results
5.1. Comparison based on average link occupancy
5.2. Comparison based on average content-wise call blocking probability
5.3. Comparison based on worst content-wise call blocking probability
5.4. Comparison based on time blocking probability in large systems
5.5. Summary
6. Conclusions
Acknowledgements
Appendix A. Monte Carlo simulation for the multicast mode
Appendix B. Gain for α=0 and I<∞
Appendix C. Gain in the limit α→1 for I=∞
Appendix D. Gain in the limit I→∞ for 0≤α≤1
References







Corresponding Author Contact InformationCorresponding author.

 
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.