Catching and selective catching
Published 30 October 1999Open access
Lixin Gao, Zhi-Li Zhang, Don Towsley
Citations76
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A novel video streaming technique called catching for on-demand delivery of “hot” (i.e., frequently accessed) video objects to a large number of clients is presented and an efficient video delivery scheme referred to as selective catching is designed.
Abstract
We present a novel video streaming technique called catching for on-demand delivery of "hot" (i.e., frequently accessed) video objects to a large number of clients. This technique not only significantly reduces the server and network resource requirements but also is capable of providing near-instantaneous service to a large number of clients. By combining this technique for delivery of "hot" video objects with controlled multicast [4] for delivery of "cold" video objects, we design an efficient video delivery scheme referred to as selective catching. Through empirical studies, we demonstrate the efficacy of the proposed video delivery schemes.
Keywords
Computer Science
Scheduling policies for an on-demand video server with batching
610 Citations1994A. Dan, Dinkar Sitaram +1 more
It is shown that an FCFS policy that schedules the movie with the longest outstanding request can perform better than the MQL policy that chooses the film with the maximum number of outstanding requests.
<i>Patching</i>
597 Citations1998Kien A. Hua, Ying Cai +1 more
This paper is able to tiate the service latency and improve the efficiency of mtiticast at the same time, and indicates convincingly that Patching offers .wbstanti~y better perforrnace.
Proxy prefix caching for multimedia streams
512 Citations1999Subhabrata Sen, Jennifer Rexford +1 more
This work proposes a prefix caching technique whereby a proxy stores the initial frames of popular clips, and describes how to construct a smooth transmission schedule, based on the size of the prefix, smoothing, and playback buffers, without increasing client playback delay.
Skyscraper broadcasting
508 Citations1997Kien A. Hua, Simon Sheu
This study investigates a novel multicast technique, called Skyscraper Broadcasting (SB), for video-on-demand applications, and is able to achieve the low latency of PB while using only 20% of the buffer space required by PPB.
Multimedia SystemsMetropolitan area video-on-demand service using pyramid broadcasting
434 Citations1996S. Viswanathan, Tomasz Imieliński
This paper provides analytical and experimental evaluations of pyramid broadcasting based on its implementation on an Ethernet LAN, gaining a radical improvement in access time and bandwidth use by using storage at the receiving end.
On optimal batching policies for video-on-demand storage servers
244 Citations2002Charų C. Aggarwal, Joel L. Wolf +1 more
This study proposes a batching policy that schedules the video with the maximum factored queue length and shows that MFQ yields excellent empirical results in terms of standard performance measures such as average latency time, defection rates and fairness.
A permutation-based pyramid broadcasting scheme for video-on-demand systems
243 Citations2002Charų C. Aggarwal, Joel L. Wolf +1 more
This work presents a permutation based pyramid scheme in which the storage requirements and disk transfer rates are greatly reduced, and yet the viewer latency is smaller as well.
Multimedia SystemsEfficient schemes for broadcasting popular videos
190 Citations2002Lixin Gao, Jim Kurose +1 more
This work provides a formal framework for studying broadcasting schemes and designs a family of schemes for broadcasting popular videos, the greedy disk-conserving broadcasting (GDB) family, and shows that with small client I/O bandwidth, the resource requirements of GDB are close to the minimum achievable by any disk-Conserving broadcasting scheme.
Supplying instantaneous video-on-demand services using controlled multicast
182 Citations2003Lixin Gao, Don Towsley
This work proposes and evaluates the performance of a multicast technique, called controlled CIWP, for supplying video-on-demand services and derives the optimal threshold that maximizes the number of server channels required.
A network-conscious approach to end-to-end video delivery over wide area networks using proxy servers
136 Citations2002Yuewei Wang, Zhi-Li Zhang +2 more
The results demonstrate that the proposed proxy-server-based, network-conscious approach provides an effective and scalable solution to the problem of the end-to-end video delivery over wide-area networks.
Lecture notes in computer scienceDynamic Skyscraper Broadcasts for Video-on-Demand
101 Citations1998Derek L. Eager, Mary K. Vernon
Preliminary simulation results show that the proposed dynamic scheme for dynamically scheduling the objects that are broadcast on the skyscraper channels outperforms the static system with respect to variability in client waiting time, and delivers reasonable service to clients with inexpensive settops while providing clients that have more expensive settops with a high level of service that is relatively isolated from detrimental performance impact from the diskless clients.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Optimized regional caching for on-demand data delivery</title>
80 Citations1998Derek L. Eager, Michael C. Ferris +1 more
It is often cost-effective to cache the initial segments of many data objects rather than the complete data for fewer objects, and the partitioned delivery architecture and caching partial objects can each greatly reduce delivery cost.
The split and merge (SAM) protocol for interactive video-on-demand systems
31 Citations2002Wanjium Liao, V.O.K. Li
An innovative way to merge an interactive user from the batch and to serve him with a dedicated video stream is developed, which significantly improves the system resource utilization and the number of simultaneous users, and more importantly, allows true VOD services.