Asee peer logo

Development of a Multi-Platform High Performance Computing Streaming Video Distribution Cluster

Download Paper |

Conference

2013 ASEE Annual Conference & Exposition

Location

Atlanta, Georgia

Publication Date

June 23, 2013

Start Date

June 23, 2013

End Date

June 26, 2013

ISSN

2153-5965

Conference Session

Emerging Computing and Information Technologies

Tagged Division

Computing & Information Technology

Page Count

6

Page Numbers

23.420.1 - 23.420.6

Permanent URL

https://peer.asee.org/19434

Download Count

32

Request a correction

Paper Authors

author page

Carlos R Morales Purdue University, West Lafayette

author page

Perry Lucas Cox

author page

Matthew John Farrenkopf

biography

Robert Eric Knorr Purdue University

visit author page

I studied at Purdue University to receive a Bachelor's of Science in Computer Graphic Technology. I specialized in production and practiced in production management.

visit author page

author page

Erick Morales

author page

Christopher Gaeta

author page

Martin Jerome Durchholz

Download Paper |

Abstract

Development of a Multi‐Platform High Performance Computing Streaming Video Distribution Cluster Abstract The _______________ developed a multiplatform (PC, iPhone, Android) streaming video platform to distribute distance‐learning content using a variety of HPC techniques. The developed system is capable of dynamically scaling and transcoding content based on server demand, available bandwidth, format of source material, and client format restrictions.  The ______ needed a mechanism for distributing distance‐learning content to off‐site students. The group evaluated a wide range of commercial and open‐source streaming platforms using a robust set of objective criteria. The most important criteria were identified as: (1) ability to stream content to any common client (PCs/Macs, Tablets, mobile phones), (2) ability to encode / transcode content into any necessary format in real‐time or faster, (3) ability to adequately handle adverse conditions such as network congestion, and (4) ability to handle a large number of simultaneous client requests.  To accomplish encoding, the team erected a computing farm with a cluster of nodes dedicated to real‐time video encoding. At the core of the encoding process were dedicated hardware h.264 encoders that accepted our videos as 1080p via HDMI and/or SDI and output h.264 files ranging in data‐rate from 2 to 20 Mbps. Lower bitrate files were created with off‐the‐shelf encoding software capable of utilizing NVidia Quadro and Tesla GPUs on the servers.  A customized deployment of Wowza and JWplayer running on multiple servers stream content to the clients via HTTP pseudostreaming or RTMP based on the clients’ requirements. JWplayer identifies the client and routes calls to the appropriate streaming points on the Wowza server. Wowza gauges stream requirements and serves the content appropriately.   In the end, the created solution meets all of the project’s goals of delivering any of the videos to any of the common platforms in a very robust and scalable manner.   

Morales, C. R., & Cox, P. L., & Farrenkopf, M. J., & Knorr, R. E., & Morales, E., & Gaeta, C., & Durchholz, M. J. (2013, June), Development of a Multi-Platform High Performance Computing Streaming Video Distribution Cluster Paper presented at 2013 ASEE Annual Conference & Exposition, Atlanta, Georgia. https://peer.asee.org/19434

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2013 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015