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    
Performance Evaluation
Volume 63, Issues 9-10, October 2006, Pages 956-987
 
Font Size: Decrease Font Size  Increase Font Size
 Abstract - selected
Article
Purchase PDF (1429 K)

Article Toolbox
 
 
 
Related Articles in ScienceDirect
View More Related Articles
 
View Record in Scopus
 
doi:10.1016/j.peva.2005.10.003    
How to Cite or Link Using DOI (Opens New Window)

Copyright © 2005 Elsevier Ltd All rights reserved.

Tight end-to-end per-flow delay bounds in FIFO multiplexing sink-tree networksstar, open

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.

Luciano Lenzinia, E-mail The Corresponding Author, Linda Martorinia, E-mail The Corresponding Author, Enzo Mingozzia, E-mail The Corresponding Author and Giovanni SteaCorresponding Author Contact Information, a, E-mail The Corresponding Author

aDipartimento di Ingegneria dell’Informazione, University of Pisa, Via Diotisalvi 2, I-56122 Pisa, Italy


Received 13 September 2004; 
revised 24 October 2005. 
Available online 20 December 2005.

Abstract

Aggregate scheduling has been proposed as a solution for achieving scalability in large-size networks. However, in order to enable the provisioning of real-time services, such as video delivery or voice conversations, in aggregate scheduling networks, end-to-end delay bounds for single flows are required. In this paper, we derive per-flow end-to-end delay bounds in aggregate scheduling networks in which per-egress (or sink-tree) aggregation is in place, and flows traffic is aggregated according to a FIFO policy. The derivation process is based on Network Calculus, which is suitably extended to this purpose. We show that the bound is tight by deriving the scenario in which it is attained. A tight delay bound can be employed for a variety of purposes: for example, devising optimal aggregation criteria and rate provisioning policies based on pre-specified flow delay bounds.

Keywords: Delay bounds; Quality of Service; Sink-tree networks; Network Calculus; FIFO multiplexing

Article Outline

1. Introduction
2. Network Calculus background
3. System model
4. Analysis
4.1. End-to-end service curve for the tagged flow
4.2. Computation of the delay bound
4.2.1. Part 1 — V is an achievable delay
4.2.2. Part 2 — V is a delay bound
4.3. Analysis of the delay bound expression
4.4. Optimal end-to-end service curve for flow 1
4.5. Generalization to sink-tree networks of arbitrary topology
5. Numerical examples
5.1. Balanced tree topology
5.2. Comparison between aggregate scheduling and per-flow scheduling
5.2.1. Flows with the same relative burstiness
5.2.2. Flows with the same rate
5.3. Delay-constrained bandwidth provisioning
6. Related work
7. Conclusions and future work
Appendix A. Appendix
A.1. Proof of the properties of pseudoaffine curves
A.2. Proof of Property 4.9
A.3. Proof of Lemma A.1
A.4. Proof of Theorem 4.14
A.5. Table of symbols
References
Vitae















star, openThis work has been partially funded by the Italian Ministry for Education and Scientific Research (MIUR) through the FIRB-PERF and QUASAR probjects.


Corresponding Author Contact InformationCorresponding author. Tel.: +39 050 2217 653; fax: +39 050 2217 600.

Performance Evaluation
Volume 63, Issues 9-10, October 2006, Pages 956-987
 
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.