Traffic Smoothing and Bandwidth Allocation for VBR MPEG-2 Video Connections in ATM Networks

Authors:
Affiliations:
Venue:
ICCCN '95 Proceedings of the 4th International Conference on Computer Communications and Networks
Year:
1995

Citing 6
Cited 0

Effective bandwidths for the multi-type UAS channel

Queueing Systems: Theory and Applications
The Asynchronous Transfer Mode: a tutorial

Computer Networks and ISDN Systems - Special issue on the ATM—asynchronous transfer mode
Effective bandwidth of general Markovian traffic sources and admission control of high speed networks

IEEE/ACM Transactions on Networking (TON)
Effective bandwidths for multiclass Markov fluids and other ATM sources

IEEE/ACM Transactions on Networking (TON)
Asynchronous Transfer Mode Networks: Performance Issues

Asynchronous Transfer Mode Networks: Performance Issues
Statistical characteristics and multiplexing of MPEG streams

INFOCOM '95 Proceedings of the Fourteenth Annual Joint Conference of the IEEE Computer and Communication Societies (Vol. 2)-Volume - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we studied the traffic smoothing and bandwidth allocation issues for VBR MPEG-2 video connections in ATM networks. First of all, the statistical characteristics of VBR MPEG-2 video sequences were examined by real observation. The obtained results showed that it would be very difficult to efficiently allocate an appropriate amount of bandwidth if such traffic were straightforwardly feed into the network. We therefore introduced a so called macro-frame (M-frame) smoothing scheme. It was found that the smoothed traffic not only possesses relatively simple characteristics but also makes the bandwidth allocation more efficient. In consideration of that there is not yet a proper bandwidth allocation algorithm for VBR MPEG-2 connections, we examined and compared the simple peak rate allocation and Gaussian approximation. It was found that 1) peak rate allocation is far more inefficient than the actual need and 2) Gaussian approximation is surprisingly accurate and efficient in estimating the bandwidth, especially in smoothed traffic case.