The Science Behind the Services

High quality and cost-effective video distribution over the Internet has long been an overarching vision and a grand challenge for the communication and media industry. Conviva brings together the disciplines of high-scale, parallel compute processing and real-time algorithmic inference with policy management to optimize both the quality and cost of online video. In addition, content owners have the instant audience insights they require for success.

For the last two decades, Conviva researchers have solved some of hardest technical problems, and pioneered key architectural innovations in fulfilling the promise of Internet video.


Viewer Experience Optimization

Service Disciplines For Integrated Services Packet-Switching Networks (13)

Developing a Predictive Model of Quality of Experience for Internet Video (14)

Improving Fairness, Efficiency, and Stability in HTTP-Based Adaptive Streaming with Festive (15)

Conviva Precision Video –
Policy based Multi-CDN Optimization
(white paper)

Impact of Delivery Eco-System Variability and Diversity on Internet Video Quality (16)

A Case for a Coordinated Internet-Scale Video Control Plane (18)

Understanding the Impact of Video Quality on User Engagement (18)

Conviva’s award-winning team of engineers and scientist prove the need for a preemptive viewer experience optimization tool and quantify and validate video quality’s impact on viewer engagement.


Scalable Management and Delivery Systems

The Feasibility of Supporting Large-Scale Live Streaming Applications with Dynamic Application End-Points (5)

Early Experience with an Internet Broadcast System Based on Overlay Multicast (6)

Chord: A Scalable Peer-to-peer Lookup Protocol for Internet Applications (9)

Stateless Core: A Scalable Approach for Quality of Service in the Internet (11)

The Impact of DHT Routing Geometry
on Resilience and Proximity
(7)

Dr. Zhang’s End System Multicast (ESM) research group at Carnegie Mellon pioneered the overlay multicast architecture and techniques to support scalable Internet video streaming. Jibin Zhan and Aditya Ganjam, two Conviva team members, led the development and deployment of the first Internet peer-to-peer live streaming system.

The award-winning Ph.D. dissertation of Dr. Ion Stoica, co-founder and chief technical officer, pioneered the first scalable architecture to manage QoS states in a distributed networking environment.

Big Data and Cloud Computing

A Common Substrate for Cluster Computing (1)

Improving MapReduce Performance
in Heterogeneous Environments
(2)

Shark: SQL and Rich Analytics at Scale. (21)

Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing. (22)

Dr. Stoica’s research group at the University of California at Berkeley has done pioneering research on building large scale, real-time cluster computing frameworks, and on enabling multiple frameworks, such as Hadoop and Hypertable, to seamlessly share the same cluster.


Software Defined Networks and Inteligent Network Control

A Clean Slate 4D Approach to Network Control and Management (4)

Tesseract: a 4D Network Control Plane (19)

Managing data transfers in computer clusters with orchestra (20)

The Feasibility of Supporting Large-Scale Live Streaming Applications with Dynamic Application End-Points (5)

A Case for End System Multicast (10)

Both Conviva co-founders have worked on new network architectures which enable direct control on routing data traffic, support network-level objectives, and provide network-wide visibility.


Secure Software and Network Diagnosis

The Design and Implementation of a Certifying Compiler (12)

CCured in the Real World (8)

Network Monitoring and Diagnosis Based on Available Bandwidth Measurements (3)

Dr. George Necula, a Conviva team member and a professor of Computer Science at the University of California at Berkeley, invented self-certifying code, a key capability of enabling practical secure software over the Internet.

Dr. Ningning Hu, a Conviva team member, developed the Internet’s most powerful performance and diagnosis software.

White Papers

  1. B. Hindman, A. Konwinski, M. Zaharia and I. Stoica, “A Common Substrate for Cluster Computing,” HotCloud 2009, June 2009.
  2. M. Zaharia, A. Konwinski, A. Joseph, R. Katz, and I. Stoica,“Improving MapReduce Performance in Heterogeneous Environments,” Proceedings of ACM OSDI’08, San Diego, Calif., December 2008.
  3. N. Hu, “Network Monitoring and Diagnosis Based on Available Bandwidth Measurements,”Ph.D. Dissertation, Carnegie Mellon, May 2006.
  4. A. Greenberg, G. Hjalmtysson, D. Maltz, A. Myers, J. Rexford, G. Xie, H. Yan, J. Zhan, H. Zhang, “A Clean Slate 4D Approach to Network Control and Management” ACM SIGCOMM Computer Communication Review. 35(5). October, 2005.
  5. K. Sripanidkulchai, A. Ganjam, B. Maggs, H. Zhang, “The Feasibility of Supporting Large-Scale Live Streaming Applications with Dynamic Application End-Points,”Proceedings of ACM SIGCOMM, Portland, OR, August, 2004.
  1. Y. Chu, A. Ganjam, T. Ng, S. Rao, K. Sripanidkulchai, J. Zhan, and H. Zhang , “Early Experience with an Internet Broadcast System Based on Overlay Multicast,” USENIX Annual Technical Conference, Boston, June, 2004.
  2. K. Gummadi, R. Gummadi, S. Gribble, S. Ratnasamy, S. Shenker, I. Stoica, “The Impact of DHT Routing Geometry on Resilience and Proximity,” In Proceedings of ACM SIGCOMM 2003, Karlsruhe, Germany, August 2003.
  3. J. Condit, M. Harren, S. McPeak, G. Necula, W. Weimer,“CCured in the Real World,”PLDI’03, June 2003.
  4. I. Stoica, R. Morris, D. Liben-Nowell, D. R. Karger, M. Frans Kaashoek, F. Dabek, H. Balakrishnan, “Chord: A Scalable Peer-to-peer Lookup Protocol for Internet Applications,” Proceedings of SIGCOMM’01, San Diego, August 2001.
  5. Y. Chu, S. Rao, and H. Zhang,“A Case for End System Multicast,” Proceedings of ACM SIGMETRICS, Santa Clara, Calif., June 2000.
  6. I. Stoica, “Stateless Core: A Scalable Approach for Quality of Service in the Internet,” Ph.D dissertation, Carnegie Mellon University, August 2000, (2001 ACM Best Dissertation Award)
  1. G. Necula, P. Lee. “The Design and Implementation of a Certifying Compiler,” PLDI’98, Montreal, 1998.
  2. H. Zhang, “Service Disciplines For Integrated Services Packet-Switching Networks,” Ph.D dissertation, UC Berkeley, November 1993.
  3. “Developing a Predictive Model of Quality of Experience for Internet Video” Athula Balachandran, Vyas Sekar, Aditya Akella, Srinivasan Seshan, Ion Stoica, and Hui Zhang, ACM SIGCOMM 2013, Hong Kong, China, August 2013
  4. “Improving Fairness, Efficiency, and Stability in HTTP-Based Adaptive Streaming with Festive”, Junchen Jiang, Vyas Sekar, Hui Zhang, CoNEXT 2012, Nice France, December 2013
  5. “Impact of Delivery Eco-System Variability and Diversity on Internet Video Quality”, Aditya Ganjam, Prashanth Pappu, Ion Stoica, Jibin Zhan, Hui Zhang, ICB 2013 (Best Paper Award)
  6. “A Case for a Coordinated Internet-Scale Video Control Plane”, Xi Liu, Florin Dobrian, Henry Milner, Junchen Jiang, Vyas Sekar, Ion Stoica, and Hui Zhang, ACM SIGCOMM 2012, Helsinki, Finland, August 2012
  1. “Understanding the Impact of Video Quality on User Engagement”, F. Dobrian, A. Awan, I. Stoica, V. Sekar, A. Ganjam, D. Joseph, J. Zhan and H. Zhang, SIGCOMM 2011, August 2011
  2. Tesseract: a 4D Network Control Plane, Hong Yan, David A. Maltz, T.S. Eugene Ng, Hemant Goineni, Hui Zhang, Zhen Cai, NSDI’07, Cambridge, MA, 2007
  3. Mosharaf Chowdhury, Matei Zaharia, Justin Ma, Michael I. Jordan, Ion Stoica: Managing data transfers in computer clusters with orchestra. SIGCOMM 2011, Toronto, Canada, 2011
  4. “Shark: SQL and Rich Analytics at Scale.” Reynold S Xin, Josh Rosen, Matei Zaharia, UC Berkeley; Michael J Franklin, Scott Shenker, Ion Stoica. SIGMOD 2013. June 2013
  5. “Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing.” Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, Ion Stoica. NSDI 2012. April 2012. (Best Paper Award and Honorable Mention for Community Award.)