Loading…

Performance evaluation of transmission schemes for real-time traffic in a high-speed timed-token MAC network

The fast development of high-speed networks makes many real-time multimedia applications possible. These applications usually involve the transmission of massive amounts of digital video data, which requires the application of video image compression technology, under a stringent timing constraint....

Full description

Saved in:
Bibliographic Details
Published in:The Journal of systems and software 2000-09, Vol.54 (1), p.41-60
Main Authors: Ng, Joseph Kee-Yin, Lee, Victor Chung-sing
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The fast development of high-speed networks makes many real-time multimedia applications possible. These applications usually involve the transmission of massive amounts of digital video data, which requires the application of video image compression technology, under a stringent timing constraint. As a result, the transmission of the variable bit rate (VBR) traffic generated by the compression algorithms plays a very important role in meeting the real-time requirement of the applications. In this paper, we analyze the characteristics of the real-time traffic generated by Moving Pictures Experts Group (MPEG), which is one of the most notable video image compression standards, and evaluate four different transmission schemes for the real-time VBR traffic. In order to have a deterministic behavior and bounded message delays, we choose the timed token medium access control (MAC) protocol for the evaluation of our transmission schemes. Judging from our maximum bandwidth demand analysis, and after a series of intensive simulation experiments, the results reveal that in our best scenario, the performance improvement (PI) can be as high as 422% over the original default transmission scheme in terms of the number of video streams that can be supported in the network.
ISSN:0164-1212
1873-1228
DOI:10.1016/S0164-1212(00)00025-X