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    
Computer Communications
Volume 25, Issue 17, 1 November 2002, Pages 1596-1605
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Article
Purchase PDF (258 K)

Article Toolbox
 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
View Record in Scopus
 
doi:10.1016/S0140-3664(02)00059-2    
How to Cite or Link Using DOI (Opens New Window)

Copyright © 2002 Elsevier Science B.V. All rights reserved.

An efficient bandwidth management scheme for real-time Internet applications

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.

Fugui Wanga, Prasant MohapatraCorresponding Author Contact Information, E-mail The Corresponding Author, b, Sarit Mukherjeec and Dennis Bushmitchc

a Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, USA

b Department of Computer Science, University of California, Davis, CA 95616, USA

c Panasonic Information and Networking Technologies Laboratory, Two Research Way, Princeton, NJ 08540, USA


Received 20 February 2001; 
revised 9 January 2002; 
accepted 29 January 2002. 
Available online 7 March 2002.

Abstract

Differentiated services (DiffServ) was recently proposed by the IETF as a scalable solution for the Internet QoS. Within the DiffServ architecture, premium services is a service class which is proposed for interactive real-time applications like Internet telephony or video conference. In order to ensure the service quality of premium services, each DiffServ domain needs to appropriately negotiate a service level agreement (SLA) with its customers and neighboring domains. Because the resources for premium service is usually a small part of the total network band-width, dynamic SLA negotiation is preferred to maximize the resource utilization. However, a completely dynamic SLA negotiation scheme introduces scalability problem for the bandwidth broker (BB). In this paper, we introduce the concept of ‘pipe’ as a viable solution for this scalability problem. We propose a simple threshold-based updating scheme for the pipe which incurs an acceptable updating overhead for the BB while maintaining a high utilization of the pipe. We study the performance of the threshold-based updating scheme and compare it with an ideal updating scheme. The ideal scheme is theoretically optimal as it uses future knowledge for periodically updating the pipe capacity. The performance of the threshold-based updating scheme is very close to the ideal updating scheme.

Author Keywords: Differentiated services; End-to-end guarantee; Expedited forwarding; Internet; Pipe; Premium services; Quality of service

Article Outline

1. Introduction
2. Concept of pipe
2.1. Definition of a pipe
2.2. Relationship between pipe and SLA
2.3. Establishments of pipes
2.4. Using pipes to construct an end-to-end Qos guaranteed connection
3. Implementation of pipe
4. Improving pipe utilization through updating
4.1. Traffic model
4.2. Prediction model
4.2.1. Ideal prediction
4.2.2. Threshold-based prediction
5. Concluding remarks
References











Corresponding Author Contact Information Corresponding author; email: prasant@cs.ucdavis.edu


Computer Communications
Volume 25, Issue 17, 1 November 2002, Pages 1596-1605
 
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.