Paper: | MSP-L1.2 | ||
Session: | Multimedia Communication, Networking and Security I | ||
Time: | Thursday, May 20, 13:20 - 13:40 | ||
Presentation: | Lecture | ||
Topic: | Multimedia Signal Processing: Multimedia Applications | ||
Title: | ONLINE BANDWIDTH-EFFICIENT SCHEDULING FOR VIDEO-ON-DEMAND WITH RECURSIVE PATCHING | ||
Authors: | Yinqing Zhao; University of Southern California | ||
Zhi Shi; University of Southern California | |||
C.-C. Jay Kuo; University of Southern California | |||
Abstract: | The service bandwidth optimization problem for multicast video-on-demand systems with early service merging is investigated, and a series of on-line algorithms based on recursive patching are proposed in this research. We adopt a simple fixed-threshold starting rule and introduce a control window to regulate the degree of service merging. Our resultsindicate that the cost-aware recursive patching (CARP) with a carefully chosen control window can significantly reduce the service bandwidth consumption. We also study the promoting rule and the limited client buffer effect for practical recursive patching algorithms. Experimental result shows that the proposed recursive patching schemes outperform graceful patching with a wide margin even with a very small client buffer size. | ||
Back |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops