Share Email Print

Proceedings Paper

Comparison of stream merging algorithms for media-on-demand
Author(s): Amotz Bar-Noy; Justin Goshi; Richard E. Ladner; Kenneth Tam
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Stream merging is a technique for efficiently delivering popular media-on-demand using multicast and client buffers. The basic idea is that clients may simultaneously receive more data than they need for playback and store parts of the transmission in their buffers to be played back later. It was shown that with these additional capabilities, the bandwidth requirements for servers are dramatically reduced compared with traditional unicast systems and multicast systems that use only batching. Recently, several algorithms for stream merging have been proposed, and we perform a comprehensive comparison in this paper. We present the differences in philosophy and mechanics among the various algorithms, and illustrate the trade-offs between their system complexity and performance. We measure performance in average, maximum, and time-varying server bandwidth usage under different assumptions for the client request patterns. The result of this study is a deeper understanding of the system complexity and performance trade-offs for the various algorithms.

Paper Details

Date Published: 10 December 2001
PDF: 15 pages
Proc. SPIE 4673, Multimedia Computing and Networking 2002, (10 December 2001); doi: 10.1117/12.449974
Show Author Affiliations
Amotz Bar-Noy, AT&T Research (United States)
Justin Goshi, Univ. of Washington (United States)
Richard E. Ladner, Univ. of Washington (United States)
Kenneth Tam, Univ. of Washington (United States)

Published in SPIE Proceedings Vol. 4673:
Multimedia Computing and Networking 2002
Martin G. Kienzle; Prashant J. Shenoy, Editor(s)

© SPIE. Terms of Use
Back to Top