Adaptive chaining scheme for distributed VOD applications

In distributed video on demand (VOD) applications, a client station buffers a shifting window of its displaying video so that the video stream can be chained from the client to another one arriving within the window, instead of consuming a server stream for each new request. This scheme is called vi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on broadcasting 1999-06, Vol.45 (2), p.215-224
Main Authors: Jen-Kai Chen, Wu, J.-L.C.
Format: Article
Language:English
Subjects:
Applied sciences
Bandwidth
Bridges
Broadcasting. Videocommunications. Audiovisual
Buffers
Chaining
Chains
Costs
Exact sciences and technology
Mathematical analysis
Memory management
Multicast
Network servers
Resumes
Servers
Space stations
Streaming media
Streams
Telecommunications
Telecommunications and information theory
Television
Tiles
Video on demand
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:In distributed video on demand (VOD) applications, a client station buffers a shifting window of its displaying video so that the video stream can be chained from the client to another one arriving within the window, instead of consuming a server stream for each new request. This scheme is called video chaining that can reduce the load of video servers significantly. In this paper, we propose a novel adaptive chaining scheme that extends the basic chaining scheme with two new techniques: two-way bridging and multicast chaining. The two-way bridging method employs video buffers as forward and/or backward bridges to extend each video chain as long as possible. It provides nearly twice the performance gain than basic chaining in terms of server I/O load reduction. Mathematical analyses for both schemes are also given. The multicast chaining method maximizes the multicast degree of each video chain so that lower data delivery cost per video session can be achieved. Our scheme maintains the video chains optimally to shift the load to active clients so that the I/O bottleneck of video servers is released.
ISSN:0018-9316
1557-9611
DOI:10.1109/11.796263