SlideShare a Scribd company logo
Towards the Application of WebRTC Peer-to-Peer to
Scale LiveVideo Streaming over the Internet
Flávio Ribeiro Nogueira Barbosa
Luiz Fernando Gomes Soares
Workshop de Redes P2P, Dinâmicas, Sociais e Orientadas a Conteúdo (Wp2p+)
Simpósio Brasileiro de Redes de Computadores (SBRC)
Maio, 2014
Monday, May 5, 14
Towards the Application of WebRTC Peer-to-Peer to
Scale LiveVideo Streaming over the Internet
Flávio Ribeiro Nogueira Barbosa
Luiz Fernando Gomes Soares
Workshop de Redes P2P, Dinâmicas, Sociais e Orientadas a Conteúdo (Wp2p+)
Simpósio Brasileiro de Redes de Computadores (SBRC)
Maio, 2014
Monday, May 5, 14
‣ Motivation
‣ Background
‣ Proposed Solution
‣ Conclusion & Future Work
‣ References
Schedule
Monday, May 5, 14
Motivation
Monday, May 5, 14
‣ Audience growth on the Internet & preference for multimedia
content consumption
Motivation
‣ Red Bull Stratos 2012
‣ 8 million concurrent users [Katz 2012]
Monday, May 5, 14
‣ Audience growth on the Internet & preference for multimedia
content consumption
Motivation
‣ Red Bull Stratos 2012
‣ 8 million concurrent users [Katz 2012]
‣ FIFA Confederations Cup 2013 to Brazilian residents
‣ Almost half a million concurrent users
Monday, May 5, 14
‣ OnlineVideo Production Quality
Motivation
Monday, May 5, 14
‣ OnlineVideo Production Quality
‣ Netflix is expecting to deliver 4K videos in 2014/2015 [Sandoval 2013]
Motivation
Monday, May 5, 14
‣ OnlineVideo Production Quality
‣ Netflix is expecting to deliver 4K videos in 2014/2015 [Sandoval 2013]
‣ Prediction of transmission quality of FIFA’s next World Cup in
Brazil
Motivation
700#
1200#
3500#
0#
1000#
2000#
3000#
4000#
2006#FIFA#World#Cup## 2010#FIFA#World#Cup## 2014#FIFA#World#Cup#
Maximum'Delivered'Bitrate'
Bitrate#in#Kbps#
Monday, May 5, 14
‣ The use of Content Delivery Networks (CDN)
Motivation
Monday, May 5, 14
‣ The use of Content Delivery Networks (CDN)
‣ Scalability: CDNs scales through the addition of point-of-
presence (PoP’s)
Motivation
Monday, May 5, 14
‣ The use of Content Delivery Networks (CDN)
‣ Scalability: CDNs scales through the addition of point-of-
presence (PoP’s)
‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009]
Motivation
Monday, May 5, 14
‣ The use of Content Delivery Networks (CDN)
‣ Scalability: CDNs scales through the addition of point-of-
presence (PoP’s)
‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009]
‣ Users’ Quality of Experience
Motivation
Monday, May 5, 14
‣ The use of Content Delivery Networks (CDN)
‣ Scalability: CDNs scales through the addition of point-of-
presence (PoP’s)
‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009]
‣ Users’ Quality of Experience
Motivation
http://goo.gl/zixUr7
Monday, May 5, 14
‣ The use of Content Delivery Networks (CDN)
‣ Scalability: CDNs scales through the addition of point-of-
presence (PoP’s)
‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009]
‣ Users’ Quality of Experience
Motivation
http://goo.gl/sTNb7d
Monday, May 5, 14
Motivation
Rebuffers by Region and Telecom Carrier at Brazil. Globo.com, 2013.
Monday, May 5, 14
Background
Monday, May 5, 14
‣ CurrentVideo DistributionTechniques
Background
RTP/RTSP/RTMP HTTP-Based
Mostly on top of UDP On top of HTTP
Specialized Media Servers
Segmenter + Ordinary
Web Servers
Low Delay High Delay
Monday, May 5, 14
‣ HTTP-Based Streaming Protocols
‣ HTTP Dynamic Streaming (HDS) by Adobe
‣ HTTP Live Streaming (HLS) by Apple
‣ Smooth Streaming by Microsoft
‣ DASH by MPEG
Background
Monday, May 5, 14
‣ HTTP-Based
‣ HTTP Dynamic Streaming (HDS) by Adobe
‣ HTTP Live Streaming (HLS) by Apple
‣ Smooth Streaming by Microsoft
‣ DASH by MPEG
Background
Monday, May 5, 14
‣ WebRTC
‣ Real-Time Communications,Working Draft
‣ Capability of share video, audio and data between browsers
Background
Monday, May 5, 14
Proposed Solution
Monday, May 5, 14
‣ Hybrid Peer-to-Peer/CDN to assist video chunks delivery
Proposed Solution
Monday, May 5, 14
‣ Hybrid Peer-to-Peer/CDN to assist video chunks delivery
‣ P2P Networks usually improves as network size increases
[Rossoupolous et al 2010]
‣ Peer-assisted data sharing can decrease CDN requests to
about 96% [Cho et al 2010]
Proposed Solution
The implementation is available at: http://github.com/flavioribeiro/bemtv
Monday, May 5, 14
‣ Hybrid Peer-to-Peer/CDN to assist video chunks delivery
‣ P2P Networks usually improves as network size increases
[Rossoupolous et al 2010]
‣ Peer-assisted data sharing can decrease CDN requests to
about 96% [Cho et al 2010]
‣ Decreases the cost of transmission
‣ Reduces networks bottlenecks
‣ Improves audience’s experience
Proposed Solution
The implementation is available at: http://github.com/flavioribeiro/bemtv
Monday, May 5, 14
‣ Peer Entrance and Signaling
‣ ISP-Location & Geolocation Awareness [Kovacevic 2009]
Proposed Solution
Monday, May 5, 14
‣ Peer Entrance and Signaling
‣ ISP-Location & Geolocation Awareness [Kovacevic 2009]
1. Node A hits a “swarm name discoverer” URL *
2. Node A asks Central Server to publish himself on the swarm
3. Other nodes acknowledge new user entrance
4. Node A establish a P2P connection with each node on the same swarm (using STUN)
Proposed Solution
* http://server.bem.tv/room
Monday, May 5, 14
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
A needs chunk bbb_3.ts
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
checking if have bbb_3.ts
<A> DESIRE:bbb_3.ts
checking if have bbb_3.ts
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
have bbb_3.ts!
have bbb_3.ts!
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
choosing the best peer
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
C is the best!
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
<A-C> REQ:bbb_3.ts
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
<A-C> REQ:bbb_3.ts
<C-A> OFFER:bbb_3.ts:<blob>
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
<A-C> REQ:bbb_3.ts
<C-A> OFFER:bbb_3.ts:<blob>
A have chunk bbb_3.ts!
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
A
B
C
<A> DESIRE:bbb_3.ts
<B-A> DESACK:bbb_3.ts
<C-A> DESACK:bbb_3.ts
<A-C> REQ:bbb_3.ts
<C-A> OFFER:bbb_3.ts:<blob>
timeout? go to CDN
CDN
‣ Video Chunks Exchange Protocol
Proposed Solution
Monday, May 5, 14
‣ Early Experiments
Proposed Solution
Monday, May 5, 14
‣ Early Experiments
‣ 10 Apple MacBooks White (2GB SDRAM)
‣ Mozila Firefox 27.1 (WebRTC compatible)
‣ Same Wireless hotspot (10/100Mbps)
‣ Video Streaming
‣ Chunks with 5 seconds of duration
‣ 600 Kbps of bitrate quality
‣ CDN + Room Discoverer + P2P Signaling Server
‣ 1 server with 512MB of SDRAM in NewYork
Proposed Solution
Monday, May 5, 14
‣ Early Experiments
Proposed Solution
Monday, May 5, 14
‣ Early Experiments
Proposed Solution
Monday, May 5, 14
‣ Results
Proposed Solution
0"
20"
40"
60"
80"
100"
120"
140"
1" 3" 5" 7" 9" 11" 13" 15" 17" 19" 21" 23" 25" 27" 29" 31" 33" 35" 37" 39" 41" 43" 45" 47" 49" 51" 53" 55" 57" 59"
Requests'
Minute'
CDN.only'x'CDN.P2P'Requests'per'minute'
CDN/only" CDN/P2P"
Monday, May 5, 14
‣ Results
‣ CDN-only: 7457 requests to CDN
‣ CDN-P2P: 4482 requests to CDN
Proposed Solution
Monday, May 5, 14
‣ Results
‣ CDN-only: 7457 requests to CDN
‣ CDN-P2P: 4482 requests to CDN
‣ Reduction of 39.89%
Proposed Solution
Monday, May 5, 14
Conclusion & Future Work
Monday, May 5, 14
‣ Our approach is promising!
Conclusion & Future Work
Monday, May 5, 14
‣ Our approach is promising!
‣ Improvements:
‣ Peers Convergence and Over Swarming
‣ Reputation [Xiong and Liu 2004], Partnership [Li et al 2010], Leader Election
[Kutten 2013]
‣ Video Chunks Exchange Protocol
‣ Content Security[Medina-López et al 2013]
‣ Poisoned Chunks
‣ DoS Starvation
Conclusion & Future Work
Monday, May 5, 14
Towards the Application of WebRTC Peer-to-Peer to
Scale LiveVideo Streaming over the Internet
Flávio Ribeiro Nogueira Barbosa
Luiz Fernando Gomes Soares
Workshop de Redes P2P, Dinâmicas, Sociais e Orientadas a Conteúdo (Wp2p+)
Simpósio Brasileiro de Redes de Computadores (SBRC)
Maio, 2014
Monday, May 5, 14
References
•Berkvist,A., Burnett, D., Jennings, C. Narayanan,A. (2011) “WebRTC 1.0: Real-Time Communication Between Browsers”.Working Draft.
•Bronzino, F. Gaeta, R. Grangetto, M. Pau, G. (2012) “An Adaptive Hybrid CDN/P2P Solution for Content Delivery Networks”.VCIP, page 1-6, IEEE.
•Cho, S., Cho, J., Shin, S. (2010) “Playback Latency Reduction for Internet LiveVideo Services in CDN-P2P Hybrid Architecture”. 2013 IEEE International
Conference on Communications.
•Huang, C.,Wang,A., Li, J., Ross, K. (2008) “Understanding hybrid CDN-P2P: why limelight needs its own Red Swoosh”. Proceedings of the 18th International
Workshop on Network and Operating Systems Support for Digital Audio andVideo.
•Katz,T. (2012) “Mission Complete: Red Bull Stratos lands safely back on Earth”. http://goo.gl/bX31hl, accessed in March 2014.
•Kovacevic,A., Graffi, K., Pussep, K., Steinmetz, R. (2009) “Underlay awareness in P2P systems:Techniques and challenges”. IEEE Symposium on Parallel &
Distributed Processing.
•Kutten, S., Panduragan, G., Peleg, D., Robinson, P.,Trehan,A. (2013) “On the complexity of universal leader election”. Proceedings of the ACM symposium on
Principles of distributed computing.
•Li, B., Xie, S., Qu,Y., Keung, G.Y. (2008) “Inside the New CoolStreaming: Principles, Measurements and Performance Implications”. IEEE 27th Conference on
Computer Communications.
•Medina-López, C., Naranjo, J.A.M., García-Ortiz, J. P., Casado, L. G., González-Ruiz,V. (2013) “Execution of the P2PSP protocol in parallel environments”. XXIV
Jornadas de Paralelismo. Madrid, Spain.
•Naylor,A. (2013) “WebRTC is almost here, and it will change the web”. http://goo.gl/IgxF33, accessed in March 2014.
•Nordyke, K, (2014) “HBO Go Crashes During ‘True Detective’ Finale”. http://goo.gl/zixUr7, accessed in March 2014.
•Parmar, H. andThornburg, M. (2012) “Adobe’s RealTime Messaging Protocol”. http://goo.gl/cGMWPI, accessed in March 2014.
•Rosenberg. J, Mahy, R., Matthews, P.Wing, D. (2008) “SessionTraversal Utilities for NAT (STUN)”. IEFT Proposed Standard.
•Roussopolous, M., Baker, M., Rosenthal D. S. H., GiuliT. J., Maniatis, P., Mogul, P. (2004) “2 P2P or Not 2 P2P?”.Third International Workshop, IPTPS 2004.
•Sandoval, G. (2013) “. Netflix Chief Product Officer: expect 4k Streaming within a year or two”. http://goo.gl/F4S133, accessed in March 2014.
•Spangler,T. (2009) “YouTube May Lose $470 Million in 2009:Analysts”. http://goo.gl/oNgAzY, accessed in March 2014.
•Xiong, L. and Liu, L. (2004) “PeerTrust: Supporting Reputation-BasedTrust for Peer-to-Peer Electronic Communities”. IEEETransactions on Knowledge and
Data Engineering.
•Yuste, L. and Melvin, H. (2012) “A Protocol Review for IPTV and WebTV Multimedia Delivery Systems”. Scientific Letters of the University of Zilina, vol 14.
•Zimmerman,A., (2014) “ABC Promised to Livestream the Oscars andTotally Failed”. http://goo.gl/sTNb7d, accessed in March 2014.
Monday, May 5, 14

More Related Content

Similar to Towards the Application of WebRTC Peer-to-Peer to Scale Live Video Streaming Over the Internet

IE9 the story so far
IE9 the story so farIE9 the story so far
IE9 the story so far
thebeebs
 
WordPress Portsmouth meetup 20 dec 2018 v0.0.2
WordPress Portsmouth meetup 20 dec 2018 v0.0.2WordPress Portsmouth meetup 20 dec 2018 v0.0.2
WordPress Portsmouth meetup 20 dec 2018 v0.0.2
Herb Miller
 
Portfolio : Freddy Atton
Portfolio : Freddy Atton Portfolio : Freddy Atton
Portfolio : Freddy Atton
Freddy Atton
 
How to Implement Accessible Lecture Capture
How to Implement Accessible Lecture CaptureHow to Implement Accessible Lecture Capture
How to Implement Accessible Lecture Capture
3Play Media
 
Modern Software Practices - by Damon Poole
Modern Software Practices - by Damon PooleModern Software Practices - by Damon Poole
Modern Software Practices - by Damon Poole
Synerzip
 
360_tr.pdf
360_tr.pdf360_tr.pdf
360_tr.pdf
ssuser50a5ec
 
Quick Start to Captioning
Quick Start to CaptioningQuick Start to Captioning
Quick Start to Captioning
3Play Media
 
Quick Start to Captioning
Quick Start to CaptioningQuick Start to Captioning
Quick Start to Captioning
3Play Media
 
Quick Start to Captioning 05-07-2015
Quick Start to Captioning 05-07-2015Quick Start to Captioning 05-07-2015
Quick Start to Captioning 05-07-2015
3Play Media
 
Improving frontend performance
Improving frontend performanceImproving frontend performance
Improving frontend performance
Sagar Desarda
 
GFAR webinar: "The art and science of webcasting and webstreaming"
GFAR webinar: "The art and science of webcasting and webstreaming"GFAR webinar: "The art and science of webcasting and webstreaming"
GFAR webinar: "The art and science of webcasting and webstreaming"
GCARD Conferences
 
Section 508 and 504 Video Captioning Requirements, Workflows, and Best Practices
Section 508 and 504 Video Captioning Requirements, Workflows, and Best PracticesSection 508 and 504 Video Captioning Requirements, Workflows, and Best Practices
Section 508 and 504 Video Captioning Requirements, Workflows, and Best Practices
3Play Media
 
Making Video Communications and Training Searchable and Accessible
Making Video Communications and Training Searchable and AccessibleMaking Video Communications and Training Searchable and Accessible
Making Video Communications and Training Searchable and Accessible
3Play Media
 
Closed Captioning Online Video Clips for FCC Compliance
Closed Captioning Online Video Clips for FCC ComplianceClosed Captioning Online Video Clips for FCC Compliance
Closed Captioning Online Video Clips for FCC Compliance
3Play Media
 
Portogdg video
Portogdg videoPortogdg video
Portogdg video
Doug Sillars
 
Metrics & Challenges for Testing Streaming Applications in 2019
Metrics & Challenges for Testing Streaming Applications in 2019Metrics & Challenges for Testing Streaming Applications in 2019
Metrics & Challenges for Testing Streaming Applications in 2019
Sarah Elson
 
Corkgdg video
Corkgdg videoCorkgdg video
Corkgdg video
Doug Sillars
 
Video performance snowcamp
Video performance snowcampVideo performance snowcamp
Video performance snowcamp
Doug Sillars
 
How to Transform Data between AutoCAD and GIS
How to Transform Data between AutoCAD and GISHow to Transform Data between AutoCAD and GIS
How to Transform Data between AutoCAD and GIS
Safe Software
 
Google PageSpeed: 5 Steps to 100% (Mobile) Success
Google PageSpeed: 5 Steps to 100% (Mobile) SuccessGoogle PageSpeed: 5 Steps to 100% (Mobile) Success
Google PageSpeed: 5 Steps to 100% (Mobile) Success
Joe Williams
 

Similar to Towards the Application of WebRTC Peer-to-Peer to Scale Live Video Streaming Over the Internet (20)

IE9 the story so far
IE9 the story so farIE9 the story so far
IE9 the story so far
 
WordPress Portsmouth meetup 20 dec 2018 v0.0.2
WordPress Portsmouth meetup 20 dec 2018 v0.0.2WordPress Portsmouth meetup 20 dec 2018 v0.0.2
WordPress Portsmouth meetup 20 dec 2018 v0.0.2
 
Portfolio : Freddy Atton
Portfolio : Freddy Atton Portfolio : Freddy Atton
Portfolio : Freddy Atton
 
How to Implement Accessible Lecture Capture
How to Implement Accessible Lecture CaptureHow to Implement Accessible Lecture Capture
How to Implement Accessible Lecture Capture
 
Modern Software Practices - by Damon Poole
Modern Software Practices - by Damon PooleModern Software Practices - by Damon Poole
Modern Software Practices - by Damon Poole
 
360_tr.pdf
360_tr.pdf360_tr.pdf
360_tr.pdf
 
Quick Start to Captioning
Quick Start to CaptioningQuick Start to Captioning
Quick Start to Captioning
 
Quick Start to Captioning
Quick Start to CaptioningQuick Start to Captioning
Quick Start to Captioning
 
Quick Start to Captioning 05-07-2015
Quick Start to Captioning 05-07-2015Quick Start to Captioning 05-07-2015
Quick Start to Captioning 05-07-2015
 
Improving frontend performance
Improving frontend performanceImproving frontend performance
Improving frontend performance
 
GFAR webinar: "The art and science of webcasting and webstreaming"
GFAR webinar: "The art and science of webcasting and webstreaming"GFAR webinar: "The art and science of webcasting and webstreaming"
GFAR webinar: "The art and science of webcasting and webstreaming"
 
Section 508 and 504 Video Captioning Requirements, Workflows, and Best Practices
Section 508 and 504 Video Captioning Requirements, Workflows, and Best PracticesSection 508 and 504 Video Captioning Requirements, Workflows, and Best Practices
Section 508 and 504 Video Captioning Requirements, Workflows, and Best Practices
 
Making Video Communications and Training Searchable and Accessible
Making Video Communications and Training Searchable and AccessibleMaking Video Communications and Training Searchable and Accessible
Making Video Communications and Training Searchable and Accessible
 
Closed Captioning Online Video Clips for FCC Compliance
Closed Captioning Online Video Clips for FCC ComplianceClosed Captioning Online Video Clips for FCC Compliance
Closed Captioning Online Video Clips for FCC Compliance
 
Portogdg video
Portogdg videoPortogdg video
Portogdg video
 
Metrics & Challenges for Testing Streaming Applications in 2019
Metrics & Challenges for Testing Streaming Applications in 2019Metrics & Challenges for Testing Streaming Applications in 2019
Metrics & Challenges for Testing Streaming Applications in 2019
 
Corkgdg video
Corkgdg videoCorkgdg video
Corkgdg video
 
Video performance snowcamp
Video performance snowcampVideo performance snowcamp
Video performance snowcamp
 
How to Transform Data between AutoCAD and GIS
How to Transform Data between AutoCAD and GISHow to Transform Data between AutoCAD and GIS
How to Transform Data between AutoCAD and GIS
 
Google PageSpeed: 5 Steps to 100% (Mobile) Success
Google PageSpeed: 5 Steps to 100% (Mobile) SuccessGoogle PageSpeed: 5 Steps to 100% (Mobile) Success
Google PageSpeed: 5 Steps to 100% (Mobile) Success
 

More from Flávio Ribeiro

Implementação de Aplicações Móveis e Jogos com Python - Aula 3
Implementação de Aplicações Móveis e Jogos com Python - Aula 3Implementação de Aplicações Móveis e Jogos com Python - Aula 3
Implementação de Aplicações Móveis e Jogos com Python - Aula 3
Flávio Ribeiro
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 5
Implementação de Aplicações Móveis e Jogos com Python - Aula 5Implementação de Aplicações Móveis e Jogos com Python - Aula 5
Implementação de Aplicações Móveis e Jogos com Python - Aula 5
Flávio Ribeiro
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 6
Implementação de Aplicações Móveis e Jogos com Python - Aula 6Implementação de Aplicações Móveis e Jogos com Python - Aula 6
Implementação de Aplicações Móveis e Jogos com Python - Aula 6
Flávio Ribeiro
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 4
Implementação de Aplicações Móveis e Jogos com Python - Aula 4Implementação de Aplicações Móveis e Jogos com Python - Aula 4
Implementação de Aplicações Móveis e Jogos com Python - Aula 4
Flávio Ribeiro
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 2
Implementação de Aplicações Móveis e Jogos com Python - Aula 2Implementação de Aplicações Móveis e Jogos com Python - Aula 2
Implementação de Aplicações Móveis e Jogos com Python - Aula 2
Flávio Ribeiro
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 1
Implementação de Aplicações Móveis e Jogos com Python - Aula 1Implementação de Aplicações Móveis e Jogos com Python - Aula 1
Implementação de Aplicações Móveis e Jogos com Python - Aula 1
Flávio Ribeiro
 
BemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-Peer
BemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-PeerBemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-Peer
BemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-Peer
Flávio Ribeiro
 
Desenvolvimento Mobile & Embedded com Arduino, Python, ARM e Linux
Desenvolvimento Mobile & Embedded com Arduino, Python, ARM e LinuxDesenvolvimento Mobile & Embedded com Arduino, Python, ARM e Linux
Desenvolvimento Mobile & Embedded com Arduino, Python, ARM e Linux
Flávio Ribeiro
 
stewie: Machine Learning para detecção não supervisionada de anomalias
stewie: Machine Learning para detecção não supervisionada de anomaliasstewie: Machine Learning para detecção não supervisionada de anomalias
stewie: Machine Learning para detecção não supervisionada de anomalias
Flávio Ribeiro
 
Test Driven Development - Trabalhe tranquilo e maximize sua produtividade
Test Driven Development - Trabalhe tranquilo e maximize sua produtividadeTest Driven Development - Trabalhe tranquilo e maximize sua produtividade
Test Driven Development - Trabalhe tranquilo e maximize sua produtividadeFlávio Ribeiro
 
Desenvolvimento de aplicações embarcadas utilizando Python
Desenvolvimento de aplicações embarcadas utilizando PythonDesenvolvimento de aplicações embarcadas utilizando Python
Desenvolvimento de aplicações embarcadas utilizando Python
Flávio Ribeiro
 
Introdução a Linguagem de Programação Python
Introdução a Linguagem de Programação PythonIntrodução a Linguagem de Programação Python
Introdução a Linguagem de Programação Python
Flávio Ribeiro
 
Linux em Sistemas Embarcados
Linux em Sistemas EmbarcadosLinux em Sistemas Embarcados
Linux em Sistemas Embarcados
Flávio Ribeiro
 

More from Flávio Ribeiro (13)

Implementação de Aplicações Móveis e Jogos com Python - Aula 3
Implementação de Aplicações Móveis e Jogos com Python - Aula 3Implementação de Aplicações Móveis e Jogos com Python - Aula 3
Implementação de Aplicações Móveis e Jogos com Python - Aula 3
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 5
Implementação de Aplicações Móveis e Jogos com Python - Aula 5Implementação de Aplicações Móveis e Jogos com Python - Aula 5
Implementação de Aplicações Móveis e Jogos com Python - Aula 5
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 6
Implementação de Aplicações Móveis e Jogos com Python - Aula 6Implementação de Aplicações Móveis e Jogos com Python - Aula 6
Implementação de Aplicações Móveis e Jogos com Python - Aula 6
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 4
Implementação de Aplicações Móveis e Jogos com Python - Aula 4Implementação de Aplicações Móveis e Jogos com Python - Aula 4
Implementação de Aplicações Móveis e Jogos com Python - Aula 4
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 2
Implementação de Aplicações Móveis e Jogos com Python - Aula 2Implementação de Aplicações Móveis e Jogos com Python - Aula 2
Implementação de Aplicações Móveis e Jogos com Python - Aula 2
 
Implementação de Aplicações Móveis e Jogos com Python - Aula 1
Implementação de Aplicações Móveis e Jogos com Python - Aula 1Implementação de Aplicações Móveis e Jogos com Python - Aula 1
Implementação de Aplicações Móveis e Jogos com Python - Aula 1
 
BemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-Peer
BemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-PeerBemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-Peer
BemTV: Modelo Híbrido para Transmissão de Vídeos ao Vivo utilizando Peer-to-Peer
 
Desenvolvimento Mobile & Embedded com Arduino, Python, ARM e Linux
Desenvolvimento Mobile & Embedded com Arduino, Python, ARM e LinuxDesenvolvimento Mobile & Embedded com Arduino, Python, ARM e Linux
Desenvolvimento Mobile & Embedded com Arduino, Python, ARM e Linux
 
stewie: Machine Learning para detecção não supervisionada de anomalias
stewie: Machine Learning para detecção não supervisionada de anomaliasstewie: Machine Learning para detecção não supervisionada de anomalias
stewie: Machine Learning para detecção não supervisionada de anomalias
 
Test Driven Development - Trabalhe tranquilo e maximize sua produtividade
Test Driven Development - Trabalhe tranquilo e maximize sua produtividadeTest Driven Development - Trabalhe tranquilo e maximize sua produtividade
Test Driven Development - Trabalhe tranquilo e maximize sua produtividade
 
Desenvolvimento de aplicações embarcadas utilizando Python
Desenvolvimento de aplicações embarcadas utilizando PythonDesenvolvimento de aplicações embarcadas utilizando Python
Desenvolvimento de aplicações embarcadas utilizando Python
 
Introdução a Linguagem de Programação Python
Introdução a Linguagem de Programação PythonIntrodução a Linguagem de Programação Python
Introdução a Linguagem de Programação Python
 
Linux em Sistemas Embarcados
Linux em Sistemas EmbarcadosLinux em Sistemas Embarcados
Linux em Sistemas Embarcados
 

Recently uploaded

原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
obonagu
 
sieving analysis and results interpretation
sieving analysis and results interpretationsieving analysis and results interpretation
sieving analysis and results interpretation
ssuser36d3051
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
JoytuBarua2
 
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
ihlasbinance2003
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
gestioneergodomus
 
14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application
SyedAbiiAzazi1
 
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
ydteq
 
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
awadeshbabu
 
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTSHeap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Soumen Santra
 
digital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdfdigital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdf
drwaing
 
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.pptPROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
bhadouriyakaku
 
Low power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniquesLow power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniques
nooriasukmaningtyas
 
Understanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine LearningUnderstanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine Learning
SUTEJAS
 
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
zwunae
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
Rahul
 
Literature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptxLiterature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptx
Dr Ramhari Poudyal
 
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdfBPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
MIGUELANGEL966976
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
zwunae
 
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
Mukeshwaran Balu
 
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTCHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
jpsjournal1
 

Recently uploaded (20)

原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
 
sieving analysis and results interpretation
sieving analysis and results interpretationsieving analysis and results interpretation
sieving analysis and results interpretation
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
 
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
5214-1693458878915-Unit 6 2023 to 2024 academic year assignment (AutoRecovere...
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
 
14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application
 
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
一比一原版(UofT毕业证)多伦多大学毕业证成绩单如何办理
 
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
 
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTSHeap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
 
digital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdfdigital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdf
 
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.pptPROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
 
Low power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniquesLow power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniques
 
Understanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine LearningUnderstanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine Learning
 
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
一比一原版(UMich毕业证)密歇根大学|安娜堡分校毕业证成绩单专业办理
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
 
Literature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptxLiterature Review Basics and Understanding Reference Management.pptx
Literature Review Basics and Understanding Reference Management.pptx
 
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdfBPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
BPV-GUI-01-Guide-for-ASME-Review-Teams-(General)-10-10-2023.pdf
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
 
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
 
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTCHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECT
 

Towards the Application of WebRTC Peer-to-Peer to Scale Live Video Streaming Over the Internet

  • 1. Towards the Application of WebRTC Peer-to-Peer to Scale LiveVideo Streaming over the Internet Flávio Ribeiro Nogueira Barbosa Luiz Fernando Gomes Soares Workshop de Redes P2P, Dinâmicas, Sociais e Orientadas a Conteúdo (Wp2p+) Simpósio Brasileiro de Redes de Computadores (SBRC) Maio, 2014 Monday, May 5, 14
  • 2. Towards the Application of WebRTC Peer-to-Peer to Scale LiveVideo Streaming over the Internet Flávio Ribeiro Nogueira Barbosa Luiz Fernando Gomes Soares Workshop de Redes P2P, Dinâmicas, Sociais e Orientadas a Conteúdo (Wp2p+) Simpósio Brasileiro de Redes de Computadores (SBRC) Maio, 2014 Monday, May 5, 14
  • 3. ‣ Motivation ‣ Background ‣ Proposed Solution ‣ Conclusion & Future Work ‣ References Schedule Monday, May 5, 14
  • 5. ‣ Audience growth on the Internet & preference for multimedia content consumption Motivation ‣ Red Bull Stratos 2012 ‣ 8 million concurrent users [Katz 2012] Monday, May 5, 14
  • 6. ‣ Audience growth on the Internet & preference for multimedia content consumption Motivation ‣ Red Bull Stratos 2012 ‣ 8 million concurrent users [Katz 2012] ‣ FIFA Confederations Cup 2013 to Brazilian residents ‣ Almost half a million concurrent users Monday, May 5, 14
  • 7. ‣ OnlineVideo Production Quality Motivation Monday, May 5, 14
  • 8. ‣ OnlineVideo Production Quality ‣ Netflix is expecting to deliver 4K videos in 2014/2015 [Sandoval 2013] Motivation Monday, May 5, 14
  • 9. ‣ OnlineVideo Production Quality ‣ Netflix is expecting to deliver 4K videos in 2014/2015 [Sandoval 2013] ‣ Prediction of transmission quality of FIFA’s next World Cup in Brazil Motivation 700# 1200# 3500# 0# 1000# 2000# 3000# 4000# 2006#FIFA#World#Cup## 2010#FIFA#World#Cup## 2014#FIFA#World#Cup# Maximum'Delivered'Bitrate' Bitrate#in#Kbps# Monday, May 5, 14
  • 10. ‣ The use of Content Delivery Networks (CDN) Motivation Monday, May 5, 14
  • 11. ‣ The use of Content Delivery Networks (CDN) ‣ Scalability: CDNs scales through the addition of point-of- presence (PoP’s) Motivation Monday, May 5, 14
  • 12. ‣ The use of Content Delivery Networks (CDN) ‣ Scalability: CDNs scales through the addition of point-of- presence (PoP’s) ‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009] Motivation Monday, May 5, 14
  • 13. ‣ The use of Content Delivery Networks (CDN) ‣ Scalability: CDNs scales through the addition of point-of- presence (PoP’s) ‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009] ‣ Users’ Quality of Experience Motivation Monday, May 5, 14
  • 14. ‣ The use of Content Delivery Networks (CDN) ‣ Scalability: CDNs scales through the addition of point-of- presence (PoP’s) ‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009] ‣ Users’ Quality of Experience Motivation http://goo.gl/zixUr7 Monday, May 5, 14
  • 15. ‣ The use of Content Delivery Networks (CDN) ‣ Scalability: CDNs scales through the addition of point-of- presence (PoP’s) ‣ Cost: GoogleYouTube spend 1 million dollars per day [Spangler 2009] ‣ Users’ Quality of Experience Motivation http://goo.gl/sTNb7d Monday, May 5, 14
  • 16. Motivation Rebuffers by Region and Telecom Carrier at Brazil. Globo.com, 2013. Monday, May 5, 14
  • 18. ‣ CurrentVideo DistributionTechniques Background RTP/RTSP/RTMP HTTP-Based Mostly on top of UDP On top of HTTP Specialized Media Servers Segmenter + Ordinary Web Servers Low Delay High Delay Monday, May 5, 14
  • 19. ‣ HTTP-Based Streaming Protocols ‣ HTTP Dynamic Streaming (HDS) by Adobe ‣ HTTP Live Streaming (HLS) by Apple ‣ Smooth Streaming by Microsoft ‣ DASH by MPEG Background Monday, May 5, 14
  • 20. ‣ HTTP-Based ‣ HTTP Dynamic Streaming (HDS) by Adobe ‣ HTTP Live Streaming (HLS) by Apple ‣ Smooth Streaming by Microsoft ‣ DASH by MPEG Background Monday, May 5, 14
  • 21. ‣ WebRTC ‣ Real-Time Communications,Working Draft ‣ Capability of share video, audio and data between browsers Background Monday, May 5, 14
  • 23. ‣ Hybrid Peer-to-Peer/CDN to assist video chunks delivery Proposed Solution Monday, May 5, 14
  • 24. ‣ Hybrid Peer-to-Peer/CDN to assist video chunks delivery ‣ P2P Networks usually improves as network size increases [Rossoupolous et al 2010] ‣ Peer-assisted data sharing can decrease CDN requests to about 96% [Cho et al 2010] Proposed Solution The implementation is available at: http://github.com/flavioribeiro/bemtv Monday, May 5, 14
  • 25. ‣ Hybrid Peer-to-Peer/CDN to assist video chunks delivery ‣ P2P Networks usually improves as network size increases [Rossoupolous et al 2010] ‣ Peer-assisted data sharing can decrease CDN requests to about 96% [Cho et al 2010] ‣ Decreases the cost of transmission ‣ Reduces networks bottlenecks ‣ Improves audience’s experience Proposed Solution The implementation is available at: http://github.com/flavioribeiro/bemtv Monday, May 5, 14
  • 26. ‣ Peer Entrance and Signaling ‣ ISP-Location & Geolocation Awareness [Kovacevic 2009] Proposed Solution Monday, May 5, 14
  • 27. ‣ Peer Entrance and Signaling ‣ ISP-Location & Geolocation Awareness [Kovacevic 2009] 1. Node A hits a “swarm name discoverer” URL * 2. Node A asks Central Server to publish himself on the swarm 3. Other nodes acknowledge new user entrance 4. Node A establish a P2P connection with each node on the same swarm (using STUN) Proposed Solution * http://server.bem.tv/room Monday, May 5, 14
  • 28. ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 29. ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 30. A B C ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 31. A B C A needs chunk bbb_3.ts ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 32. A B C <A> DESIRE:bbb_3.ts ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 33. A B C checking if have bbb_3.ts <A> DESIRE:bbb_3.ts checking if have bbb_3.ts ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 34. A B C <A> DESIRE:bbb_3.ts have bbb_3.ts! have bbb_3.ts! ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 35. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 36. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts choosing the best peer ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 37. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts C is the best! ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 38. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts <A-C> REQ:bbb_3.ts ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 39. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts <A-C> REQ:bbb_3.ts <C-A> OFFER:bbb_3.ts:<blob> ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 40. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts <A-C> REQ:bbb_3.ts <C-A> OFFER:bbb_3.ts:<blob> A have chunk bbb_3.ts! ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 41. A B C <A> DESIRE:bbb_3.ts <B-A> DESACK:bbb_3.ts <C-A> DESACK:bbb_3.ts <A-C> REQ:bbb_3.ts <C-A> OFFER:bbb_3.ts:<blob> timeout? go to CDN CDN ‣ Video Chunks Exchange Protocol Proposed Solution Monday, May 5, 14
  • 42. ‣ Early Experiments Proposed Solution Monday, May 5, 14
  • 43. ‣ Early Experiments ‣ 10 Apple MacBooks White (2GB SDRAM) ‣ Mozila Firefox 27.1 (WebRTC compatible) ‣ Same Wireless hotspot (10/100Mbps) ‣ Video Streaming ‣ Chunks with 5 seconds of duration ‣ 600 Kbps of bitrate quality ‣ CDN + Room Discoverer + P2P Signaling Server ‣ 1 server with 512MB of SDRAM in NewYork Proposed Solution Monday, May 5, 14
  • 44. ‣ Early Experiments Proposed Solution Monday, May 5, 14
  • 45. ‣ Early Experiments Proposed Solution Monday, May 5, 14
  • 46. ‣ Results Proposed Solution 0" 20" 40" 60" 80" 100" 120" 140" 1" 3" 5" 7" 9" 11" 13" 15" 17" 19" 21" 23" 25" 27" 29" 31" 33" 35" 37" 39" 41" 43" 45" 47" 49" 51" 53" 55" 57" 59" Requests' Minute' CDN.only'x'CDN.P2P'Requests'per'minute' CDN/only" CDN/P2P" Monday, May 5, 14
  • 47. ‣ Results ‣ CDN-only: 7457 requests to CDN ‣ CDN-P2P: 4482 requests to CDN Proposed Solution Monday, May 5, 14
  • 48. ‣ Results ‣ CDN-only: 7457 requests to CDN ‣ CDN-P2P: 4482 requests to CDN ‣ Reduction of 39.89% Proposed Solution Monday, May 5, 14
  • 49. Conclusion & Future Work Monday, May 5, 14
  • 50. ‣ Our approach is promising! Conclusion & Future Work Monday, May 5, 14
  • 51. ‣ Our approach is promising! ‣ Improvements: ‣ Peers Convergence and Over Swarming ‣ Reputation [Xiong and Liu 2004], Partnership [Li et al 2010], Leader Election [Kutten 2013] ‣ Video Chunks Exchange Protocol ‣ Content Security[Medina-López et al 2013] ‣ Poisoned Chunks ‣ DoS Starvation Conclusion & Future Work Monday, May 5, 14
  • 52. Towards the Application of WebRTC Peer-to-Peer to Scale LiveVideo Streaming over the Internet Flávio Ribeiro Nogueira Barbosa Luiz Fernando Gomes Soares Workshop de Redes P2P, Dinâmicas, Sociais e Orientadas a Conteúdo (Wp2p+) Simpósio Brasileiro de Redes de Computadores (SBRC) Maio, 2014 Monday, May 5, 14
  • 53. References •Berkvist,A., Burnett, D., Jennings, C. Narayanan,A. (2011) “WebRTC 1.0: Real-Time Communication Between Browsers”.Working Draft. •Bronzino, F. Gaeta, R. Grangetto, M. Pau, G. (2012) “An Adaptive Hybrid CDN/P2P Solution for Content Delivery Networks”.VCIP, page 1-6, IEEE. •Cho, S., Cho, J., Shin, S. (2010) “Playback Latency Reduction for Internet LiveVideo Services in CDN-P2P Hybrid Architecture”. 2013 IEEE International Conference on Communications. •Huang, C.,Wang,A., Li, J., Ross, K. (2008) “Understanding hybrid CDN-P2P: why limelight needs its own Red Swoosh”. Proceedings of the 18th International Workshop on Network and Operating Systems Support for Digital Audio andVideo. •Katz,T. (2012) “Mission Complete: Red Bull Stratos lands safely back on Earth”. http://goo.gl/bX31hl, accessed in March 2014. •Kovacevic,A., Graffi, K., Pussep, K., Steinmetz, R. (2009) “Underlay awareness in P2P systems:Techniques and challenges”. IEEE Symposium on Parallel & Distributed Processing. •Kutten, S., Panduragan, G., Peleg, D., Robinson, P.,Trehan,A. (2013) “On the complexity of universal leader election”. Proceedings of the ACM symposium on Principles of distributed computing. •Li, B., Xie, S., Qu,Y., Keung, G.Y. (2008) “Inside the New CoolStreaming: Principles, Measurements and Performance Implications”. IEEE 27th Conference on Computer Communications. •Medina-López, C., Naranjo, J.A.M., García-Ortiz, J. P., Casado, L. G., González-Ruiz,V. (2013) “Execution of the P2PSP protocol in parallel environments”. XXIV Jornadas de Paralelismo. Madrid, Spain. •Naylor,A. (2013) “WebRTC is almost here, and it will change the web”. http://goo.gl/IgxF33, accessed in March 2014. •Nordyke, K, (2014) “HBO Go Crashes During ‘True Detective’ Finale”. http://goo.gl/zixUr7, accessed in March 2014. •Parmar, H. andThornburg, M. (2012) “Adobe’s RealTime Messaging Protocol”. http://goo.gl/cGMWPI, accessed in March 2014. •Rosenberg. J, Mahy, R., Matthews, P.Wing, D. (2008) “SessionTraversal Utilities for NAT (STUN)”. IEFT Proposed Standard. •Roussopolous, M., Baker, M., Rosenthal D. S. H., GiuliT. J., Maniatis, P., Mogul, P. (2004) “2 P2P or Not 2 P2P?”.Third International Workshop, IPTPS 2004. •Sandoval, G. (2013) “. Netflix Chief Product Officer: expect 4k Streaming within a year or two”. http://goo.gl/F4S133, accessed in March 2014. •Spangler,T. (2009) “YouTube May Lose $470 Million in 2009:Analysts”. http://goo.gl/oNgAzY, accessed in March 2014. •Xiong, L. and Liu, L. (2004) “PeerTrust: Supporting Reputation-BasedTrust for Peer-to-Peer Electronic Communities”. IEEETransactions on Knowledge and Data Engineering. •Yuste, L. and Melvin, H. (2012) “A Protocol Review for IPTV and WebTV Multimedia Delivery Systems”. Scientific Letters of the University of Zilina, vol 14. •Zimmerman,A., (2014) “ABC Promised to Livestream the Oscars andTotally Failed”. http://goo.gl/sTNb7d, accessed in March 2014. Monday, May 5, 14