Hybrid Broadcast for the Video-on-Demand Service

Multicast offers an efficient means of distributing video contents/programs to multiple clients by batching their requests and then having them share a server‘s video stream.Batching customers‘ requests is either client-initiated or server-initiated.Most anvanced client-initiated video multicasts are implemented by patching.Periodic broadcast,a typical server-initiated approach,can be entirety-based or segment-based.This paper focuses on the performance of the VoD service for popular videos.First,we analyze the limitation of conventional patching when the customer request rate is high.Then,By combining the advantages of each of the two broadcast schemes,we propose a hybrid broadcast scheme for popular videos ,which not only lowers the serviec latency but also improves clients‘ interactivity by using an active buffering technique ,This is shown to be a good compromise for both lowering service latency and improving the VCR-like interactivity.

Hybrid broadcast for the video-on-demand service

Multicast offers an efficient means of distributing video contents/programs to multiple clients by batching their requests and then having them share a server’s video stream. Batching customers’ requests is either client-initiated or server-initiated. Most advanced client-initiated video multicasts are implemented by patching. Periodic broadcast, a typical server-initiated approach, can be entirety-based or segment-based. This paper focuses on the performance of the VoD service for popular videos. First, we analyze the limitation of conventional patching when the customer request rate is high. Then, by combining the advantages of each of the two broadcast schemes, we propose a hybrid broadcast scheme for popular videos, which not only lowers the service latency but also improves clients’ interactivity by using an active buffering technique. This is shown to be a good compromise for both lowering service latency and improving the VCR-like interactivity. This paper was partly done when Ma Huadong visited the University of Michigan. The work reported in this paper is supported by the NSF of USA under Grant EIA-9806280, the National Natural Science Foundation of China under Grant No. 69873006, and a grant for Excellent Young Teachers by the MOE of China. MA Huadong is a professor of the College of Computer Science and Technology, Beijing University of Posts and Telecommunications, China. He received his Ph.D. degree in computer science from the Institute of Computing Technology, Chinese Academy of Sciences in 1995, M.S. degree in computer science from Shenyang Institute of Computing Technology, the Chinese Academy of Sciences in 1990 and B.S. degree in mathematics from Henan Normal University in 1984. His research interests are multimedia, computer animation and networking software, and he has published over 40 papers and 2 books in these fields. Kang G. Shin is a professor and Director of the Real-Time Computing Laboratory, Department of Electrical Engineering and Computer Science, The University of Michigan, USA. He has supervised the completion of 40 Ph.D. theses, and authored/coauthored over 600 technical papers and numerous book chapters in the areas of distributed real-time computing and control, computer networking, fault-tolerant computing, and intelligent manufacturing. His current research focuses on QoS sensitive computing and networking with emphases on timeliness and dependability. He received the B.S. degree in electronics engineering from Seoul National University, Seoul, Korea in 1970, and both the M.S. and Ph.D. degrees in electrical engineering from Cornell University, Ithaca, New York in 1976 and 1978, respectively. He is an IEEE fellow, ACM fellow and member of the Korean Academy of Engineering.