Clockwise from top. (a) The SONET Monitor. Components are being monitored in real-time in action in a quasi active subnet. (b) At run time SONET dynamically analyzes the network resource condition to determine  locations, composition, computations and quality. (c) The real-time display and monitoring of frame processing rate– its going up as SONET garners more nodes.

SONET: Self-Organizing Nomadic Transcoding Stream

In this active application demonstration project we aimed to show a technology for seamless assured information delivery on extreme network irrespective of the network resource asymmetry. The goal is that information must flow while the format is negotiated based on the resource adaptation. 

 

 

We demonstrate a novel MPEG-2 transcoding/computing system SONET with novel adaptation and architectural self-organization abilities:

 

It adapts with respect to the transport network resources—bandwidth and the processing resource at the junction nodes.

 

It can squeeze the amount of computation and data generation rate and in extreme cases it can also migrate and diffuse itself in a network to garner computation and bandwidth using active network technology.

 

 

As opposed to classical server-client model, an MPEG-2 transcoder has been designed which launches itself into an Active Network in three parts—server, transcoder and the client. The middle component is launched as active capsules in a suitable active junction point which has the capability to transcode the MPEG-2 stream and process it for rate downscaling if needed.

>> WIC: S. S. Yang & Javed I. Khan, Delay and Jitter Minimization in Active Diffusion Computing, The 3^rd IEEE International Symposium on Applications and the Internet, Orlando, SAINT 2003, Florida, January 2003, pp.292-300, [YaKh03]

 

>> NET: Javed I. Khan & S. S. Yang, Resource Adaptive Nomadic Transcoding on Active Network, International Conference of Applied Informatics, AI 2001, February 19-22, 2001, Insbruck, Austria, ISBN:0-88986-280-X (307), pp262-267. [PDF]

 

>> MMN: Javed I. Khan, Patrick Mail and Seung S. Yang, Flow Assignment in A Self-Organizing Video Stream that Auto Morphs Itself while in Transit via a Quasi-Active Network, 5th IEEE International Conf. on High Speed Networking and Multimedia Communications, HSNMC2002, Jeju, Korea, July 2002. [KhMY02]

 

 

>> MMN: Javed I. Khan, Seung Su Yang, Darsan Patel, Oleg Komogortsev, Wansik Oh, and Zhong Guo, Q. Gu, P. Mail, Resource Adaptive Netcentric Systems on Active Network: a Self-Organizing Video Stream that Automorphs itself while in Transit Via a Quasi-Active Network, Proceedings of the Active Networks Conference and Exposition DANCE ’2002, San Jose, CA May 21-24, 2002, IEEE Computer Society Press, pp.409-426. [KYPK02]

 

>> MMN: Javed I. Khan, Q. Gu, Network Aware Symbiotic Video Transcoding for Instream Rate Adaptation on Interactive Transport Control, IEEE International Symposium on Network Computing and Applications, IEEE NCA’ 2001, October 8-10, 2001, Cambridge, MA, pp.201-213. (GS(1)). [PDF]

 

 

>> MMN: Javed I. Khan, Seung Su Yang, Qiong Gu, Darsan Patel, Patrick Mail, Oleg Komogortsev, Wansik Oh, and Zhong Guo Resource Adaptive Netcentric Systems: A case Study with SONET- a Self-Organizing Network Embedded Transcoder, Proceedings of the ACM Multimedia 2001, October 2001, Ottawa, Canada, pp617-620. [PDF]

 

Selected Publications

More Publications >>

In the first level of adaptation, the transcoder senses local asymmetry in link capacities at various junction points (such as at nodes splicing a fiber and a wireless) of a network and is capable of dynamically downscaling the video stream rate. In the second level to cope with the more severe resource constraint at junction computation powers it can also diffuse and migrate computations in multiple active nodes or other routes. We call it nomadic and self-organizing applications.

 

As a result the passing video stream appears as a self-organizing stream, which automatically senses the network asymmetry and adapts itself as the packets diffuse via the active subnet. As a platform the stream uses the computing power of a quasi-active network.

 

This implementation SONET (Self-Organizing Network Embedded Transcoder) has been developed and as an application of the DARPA ANI project and has been demonstrated in DARPA Expo 2002 and ACM Multimedia 2001. It has also received a Ohio Board of Regents Research Challenge Grant for digital divide research.

Publications

Distributions

Demo

Technical Reports

All Projects

 

 

 

Page last updated February, 2008, Medianet Laboratories.