HSM: A Hybrid Streaming Mechanism for Delay-Tolerant Multimedia Applications

HSM: A Hybrid Streaming Mechanism for Delay-Tolerant Multimedia Applications

Annanda Thavymony Rath (Institute of Technology of Cambodia, Cambodia), Saraswathi Krithivasan (India Institute of Technology, Bombay, India) and Sridhar Iyer (India Institute of Technology, Bombay, India)
Copyright: © 2009 |Pages: 17
DOI: 10.4018/978-1-59904-984-7.ch011
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Traditionally, Content Delivery Networks (CDNs) deploy proxy servers at strategic locations at the edge of the network to efficiently serve client requests. With the tremendous growth in multimedia applications and the number of clients accessing such applications, an edge proxy server may serve clients connected to it through a multihop network of heterogeneous links. Further, a special class of multimedia applications that can tolerate startup delays is emerging. In such applications, clients require a minimum acceptable quality (loss-free transmission at a minimum encoded rate ri) and the start of playback at a specific time (t + di) where t is the current time and di is the delay tolerance acceptable to client i. Our work deals with enhancing performance of such networks through a Hybrid Streaming Mechanism (HSM). In HSM, a client’s request triggers the selection of an intermediate node as a streaming point to which multimedia contents are dynamically transferred from the proxy/source, and this streaming point streams the contents to the client. Transferred contents are temporarily cached at the streaming point to service future requests for the same content. HSM helps a Content Service Provider’s objective of satisfying as many client requests as possible and providing enhanced quality to clients given their delay tolerance. Simulation results demonstrate that by leveraging the delay tolerance of clients and by combining the dynamic download and streaming mechanisms, HSM performs better than directly streaming from edge servers, serving on average 40% more client requests.

Complete Chapter List

Search this Book:
Reset