understanding video streaming algorithms in the wild
play

Understanding video streaming algorithms in the wild Maximilian - PowerPoint PPT Presentation

Aug 01, 2023 •773 likes •2.05k views

Understanding video streaming algorithms in the wild Maximilian Grner Photo: ETH Zrich / Gian Marco Castelberg Melissa Licciardello Ankit Singla Roadmap 3 Roadmap Introduction 3 Roadmap Introduction Setup 3 Roadmap

  1. Understanding video streaming algorithms in the wild Maximilian Grüner Photo: ETH Zürich / Gian Marco Castelberg

  2. Melissa Licciardello Ankit Singla

  3. Roadmap 3

  4. Roadmap •Introduction 3

  5. Roadmap •Introduction •Setup 3

  6. Roadmap •Introduction •Setup •Experiments 3

  7. Roadmap •Introduction •Setup •Experiments •Limitations and future work 3

  8. Roadmap •Introduction •Setup •Experiments •Limitations and future work •(Some) Takeaways 3

  9. Streaming in industry Share of global internet traffic % Categories [Sandvine 2019] 4

  10. Streaming in industry Share of global internet traffic % Categories [Sandvine 2019] 4

  11. Streaming in industry 23.8 % Various, 23.1 % Netflix, 12.7 % YouTube, 4.2 % Twitch… Share of global internet traffic % Categories [Sandvine 2019] 4

  12. Streaming in academia # Google Scholar citations Year 5

  13. Streaming in academia # Google Scholar citations Year 5

  14. 6

  15. 6

  16. 6

  17. ? 6

  18. ? Robust MPC [ From MPC Paper] 6

  19. Services of interest Provider Description Alexa Rank 7

  20. Services of interest Provider Description Alexa Rank YouTube Broad coverage 2, Global 7

  21. Services of interest Provider Description Alexa Rank YouTube Broad coverage 2, Global ZDF German Public Service 47, Germany 7

  22. Services of interest Provider Description Alexa Rank YouTube Broad coverage 2, Global ZDF German Public Service 47, Germany Pornhub Pornographic video sharing website 46, Global 7

  23. Services of interest Provider Description Alexa Rank Provider Description Alexa Rank YouTube Broad coverage 2, Global YouTube Broad coverage 2, Global ZDF German Public Service 47, Germany ZDF German Public Service 47, Germany Pornhub Pornographic video sharing website 46, Global Pornhub Pornographic video sharing website 46, Global Arte French-German,cultural 270,France Fandom Gaming, pop-culture 91, Global SRF Swiss Public Service 45, Switzerland TubiTV Movies and series of all genres 1330, USA Twitch Live and VoD streaming service, gaming 39, Global Vimeo Artistic content 188, Global XVideos Pornographic video sharing website 67, Global 7

  24. Providers X Net-traces X Videos X Length 8

  25. Providers X Net-traces X Videos X Length 9750 minutes ~ 7 days of streaming time 8

  26. Measurement setup 9

  27. Measurement setup Server Request/Response Browser 9

  28. Measurement setup Server Request/Response Request/Response Browser Proxy 9

  29. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy 9

  30. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy Client State (Buffer..) Stats from Request/Response Video Metadata Aggregator 9

  31. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy Client State (Buffer..) Stats from Request/Response Video Metadata Aggregator 9

  32. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy Client State (Buffer..) Stats from Request/Response Video Metadata Aggregator 9

  33. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy Client State (Buffer..) Stats from Request/Response Video Metadata Aggregator 9

  34. Looking at a measurement Mbps Time [s] 10

  35. Looking at a measurement Mbps Time [s] 10

  36. Looking at a measurement Twitch Mbps Time [s] 10

  37. Looking at a measurement 2.2 Mbps @ ~ 300s Twitch Mbps Time [s] 10

  38. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy Client State (Buffer..) Stats from Request/Response Video Metadata Aggregator 11

  39. Measurement setup Monitor Server Throughput Request/Response Request/Response Browser Proxy Client State (Buffer..) Stats from Request/Response Video Metadata Aggregator 11

  40. Is the measurement correct 12

  41. Is the measurement correct Stream A 12

  42. Is the measurement correct Stream A Stream B 12

  43. Is the measurement correct Stream A User Stream B 12

  44. Is the measurement correct Same ! Stream A User Stream B 12

  45. Is the measurement correct Same ! Stream A Different ! User Stream B 12

  46. Is the measurement correct Same ! Stream A Different ! Experience function [Formula from MPC Paper] Stream B 12

  47. Is the measurement correct QoE Linear Providers 13

  48. Is the measurement correct QoE Linear Providers 13

  49. Is the measurement correct QoE Linear Providers 13

  50. Is the measurement correct QoE Linear Providers 13

  51. Twitch Mbps Time [s] 14

  52. Startup Twitch Mbps Time [s] 14

  53. Startup Time [s] Provider 15

  54. Startup Time [s] Provider 15

  55. Startup Time [s] Provider 15

  56. Startup Time [s] Provider 15

  57. Twitch Mbps Time [s] 16

  58. Startup Twitch Mbps Time [s] 16

  59. Startup Converged Twitch Mbps Time [s] 16

  60. Convergence Mbps Switch % Played 17

  61. Convergence Mbps Switch % Played 17

  62. Convergence Startup Converged Mbps Switch % Played 17

  63. Convergence Mbps Switch % Played 17

  64. Twitch Twitch Mbps Buffer [s] Time [s] 18

  65. Twitch Twitch Mbps Buffer [s] Time [s] 18

  66. Buffer Twitch Twitch Mbps Buffer [s] Time [s] 18

  67. Buffer Twitch Twitch Mbps Buffer [s] Time [s] 18

  68. Buffer Twitch Twitch Mbps Buffer [s] Time [s] 18

  69. Risk tolerance Buffer [s] % Played 19

  70. Risk tolerance Buffer [s] % Played 19

  71. Risk tolerance Buffer [s] % Played 19

  72. Bandwidth Buffer State Playback 20

  73. Bandwidth Buffer State Playback 20

  74. Bandwidth Buffer State 240p 240p 240p 240p Playback 20

  75. Bandwidth Buffer State 240p 240p 240p 240p Playback 20

  76. Bandwidth Buffer State 240p 240p 240p 240p 240p 240p 240p 240p Playback 20

  77. Bandwidth Buffer State 240p 240p 240p 240p 720p 240p 240p 240p 240p Playback 20

  78. Bandwidth Buffer State 240p 240p 240p 240p 720p 720p 240p 240p 240p 240p Playback 20

  79. Bandwidth Normal Buffer State 240p 240p 240p 240p 720p 720p 240p 240p 240p 240p Playback 20

  80. Bandwidth Redownload Buffer State 240p 240p 240p 720p 240p 720p 240p 240p 240p 240p Playback 20

  81. Risk tolerance Buffer [s] % Played 21

  82. Bandwidth usage Played/ Downloaded Provider 22

  83. Bandwidth usage Played/ Downloaded Provider 22

  84. Bandwidth usage Played/ Downloaded Provider 22

  85. Bandwidth usage Played/ Downloaded Provider 22

  86. Bandwidth usage Played/ Downloaded Provider 22

  87. Twitch Mbps Time [s] 23

  88. Twitch Mbps Time [s] 23

  89. Twitch Mbps Time [s] 23

  90. Pre-spike Twitch Mbps Time [s] 23

  91. Pre-spike Post-spike Twitch Mbps Time [s] 23

  92. Reactivity Mbps before − Mbps after % Played # Downloads after change 24

  93. Reactivity Mbps before − Mbps after % Played # Downloads after change 24

  94. Reactivity Mbps before − Mbps after % Played # Downloads after change # Downloads after change 24

  95. Mbps Time [s] 25

  96. Available Mbps Time [s] 25

  97. Available Played Mbps Time [s] 25

  98. Bandwidth usage Downloaded/ Download-able Provider 26

  99. Bandwidth usage Downloaded/ Download-able Provider 26

  100. Bandwidth usage Downloaded/ Download-able Provider 26

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Streaming algorithms Jeremy Gibbons University of Oxford APPSEM II, April 2004 Streaming

Streaming algorithms Jeremy Gibbons University of Oxford APPSEM II, April 2004 Streaming

Streaming algorithms 1 Streaming algorithms Jeremy Gibbons University of Oxford APPSEM II, April 2004 Streaming algorithms 2 1. Origami programming In a compact category (where initial algebras and final coalgebras coincide), recursive

510 views • 21 slides
1 RealVideo Network Characteristics Outline RTSP Introduction Background

1 RealVideo Network Characteristics Outline RTSP Introduction Background

The Hungry Wolf - Bandwidth Measurement of the Congestion Requirements for Video Responsiveness of RealPlayer Streaming media growing Streaming Video Over UDP 350,000 hours of online video broadcast 01 Voice is 32-64 Kbps, but

349 views • 7 slides
Reconstructing proprietary video streaming algorithms Maximilian Grner , Melissa Licciardello,

Reconstructing proprietary video streaming algorithms Maximilian Grner , Melissa Licciardello,

Reconstructing proprietary video streaming algorithms Maximilian Grner , Melissa Licciardello, Ankit Singla Photo: ETH Zrich / Gian Marco Castelberg Roadmap 2 Roadmap Introduction 2 Roadmap Introduction Reconstruction 2

1.9k views • 141 slides
HLSaaS: High-Level Video Streaming as a Service Mohsen Amini-Salehi, Xiangbo Li High

HLSaaS: High-Level Video Streaming as a Service Mohsen Amini-Salehi, Xiangbo Li High

HLSaaS: High-Level Video Streaming as a Service Mohsen Amini-Salehi, Xiangbo Li High Performance and Cloud Computing (HPCC) Lab. University of Louisiana at Lafayette 1 Streaming Providers Video Streams Client Devices 2 Video streaming

404 views • 25 slides
Adaptive video streaming with Ice and GStreamer Using ICE middleware with GStreamer to implement

Adaptive video streaming with Ice and GStreamer Using ICE middleware with GStreamer to implement

Motivation Our Results Summary Adaptive video streaming with Ice and GStreamer Using ICE middleware with GStreamer to implement real-time QoS-aware video streaming for remotely controlled vehicle. Andrey Nechypurenko andreynech@gmail.com

653 views • 26 slides
Streaming Streaming Overview Our goal: Build a video sharing site Same idea as the

Streaming Streaming Overview Our goal: Build a video sharing site Same idea as the

Streaming Streaming Overview Our goal: Build a video sharing site Same idea as the image sharing site from HW4 Except: Videos can be very large When a user watches a video, we don't want to send the entire file in a single

343 views • 15 slides
FlexCast: Graceful Wireless Video Streaming S. Aditya & Sachin Katti Stanford University 1

FlexCast: Graceful Wireless Video Streaming S. Aditya & Sachin Katti Stanford University 1

FlexCast: Graceful Wireless Video Streaming S. Aditya & Sachin Katti Stanford University 1 Mobile Video Streaming User experience is poor/choppy Exponential Video Traffic Growth Constant buffering/stuttering, lost frames are quite

628 views • 28 slides
Trickle : Rate Limiting Video Streaming Monia Ghobadi <monia@cs.toronto.edu> Yuchung

Trickle : Rate Limiting Video Streaming Monia Ghobadi <monia@cs.toronto.edu> Yuchung

Trickle : Rate Limiting Video Streaming Monia Ghobadi <monia@cs.toronto.edu> Yuchung Cheng, Ankur Jain, Matt Mathis <ycheng, jankur, mattmathis@google.com> 1 Video Streaming TCP Just-in-time video delivery Ustreamer

511 views • 11 slides
Pitfalls of data-driven networking: A case study of latent causal confounders in video streaming

Pitfalls of data-driven networking: A case study of latent causal confounders in video streaming

Pitfalls of data-driven networking: A case study of latent causal confounders in video streaming P. C. Sruthi, Sanjay Rao, Bruno Ribeiro Say you want design a video streaming system... Say you want design a video streaming system... Video

690 views • 48 slides
Streaming HLS We've seen how to host and play HLS videos Now we'll convert a .mp4 video

Streaming HLS We've seen how to host and play HLS videos Now we'll convert a .mp4 video

Streaming HLS We've seen how to host and play HLS videos Now we'll convert a .mp4 video into and HLS video Using ff mpeg ffmpeg Software with many video processing features Needs to be installed on any machine running your

545 views • 11 slides
Parameterized Streaming Algorithms Graham Cormode Rajesh Chitnis Parameterized Streaming

Parameterized Streaming Algorithms Graham Cormode Rajesh Chitnis Parameterized Streaming

Towards a Theory ry of f Parameterized Streaming Algorithms Graham Cormode Rajesh Chitnis Parameterized Streaming Algorithms We increasingly have to deal with huge graphs Facebook graph Brain graph Google Maps in USA Web Graph 10

334 views • 16 slides
Mathematical Analysis of Scheduling Policies in Peer-to-Peer Video Streaming Networks Pablo

Mathematical Analysis of Scheduling Policies in Peer-to-Peer Video Streaming Networks Pablo

Motivation Contributions Video on-demand Live Streaming Conclusions Mathematical Analysis of Scheduling Policies in Peer-to-Peer Video Streaming Networks Pablo Romero Facultad de Ingeniera, Universidad de la Repblica. PEDECIBA

648 views • 50 slides
Learning Graph Representations for Video Understanding Xiaolong Wang Carnegie Mellon University

Learning Graph Representations for Video Understanding Xiaolong Wang Carnegie Mellon University

Learning Graph Representations for Video Understanding Xiaolong Wang Carnegie Mellon University Computer Vision Dog He et al. Mask R-CNN. ICCV 2017. Gler et al. DensePose: Dense Human Pose Estimation In The Wild. CVPR 2018. Deep Learning

941 views • 64 slides
Streaming Video Tuesday, February 2 Instructor: Jeremy Slayton Well cover: What is

Streaming Video Tuesday, February 2 Instructor: Jeremy Slayton Well cover: What is

Streaming Video Tuesday, February 2 Instructor: Jeremy Slayton Well cover: What is Streaming? Where to find information about EPLs eVideo collection Account creation Site navigation Hoopla Indieflix How

191 views • 15 slides
HTTP with Mininet Anatoliy Zabrovskiy Evgeny Kuzmin Petrozavodsk State University Video

HTTP with Mininet Anatoliy Zabrovskiy Evgeny Kuzmin Petrozavodsk State University Video

Emulation of Dynamic Adaptive Streaming over HTTP with Mininet Anatoliy Zabrovskiy Evgeny Kuzmin Petrozavodsk State University Video streaming Video streaming is becoming more and more popular technology for media content delivery over the

675 views • 20 slides
Introduction (1) Packet Loss Recovery for Streaming is growing Commercial streaming

Introduction (1) Packet Loss Recovery for Streaming is growing Commercial streaming

Introduction (1) Packet Loss Recovery for Streaming is growing Commercial streaming successful (ie Streaming Video RealPlayer and MediaPlayer) but proprietary and inflexible N. Feamster and H. Balakrishnan Use MPEG-4 since open

478 views • 6 slides
Daniel Farrington, Nicholas Muesch 1 Most online video content is A newer, less popular,

Daniel Farrington, Nicholas Muesch 1 Most online video content is A newer, less popular,

Daniel Farrington, Nicholas Muesch 1 Most online video content is A newer, less popular, growing readily available on demand service What is Live Streaming? What is Video-on-demand? User encodes and uploads Pre-Recorded

548 views • 18 slides
Computer Animation CPSC 453 Fall 2018 Sonny Chan Animation is the act, process, or result of

Computer Animation CPSC 453 Fall 2018 Sonny Chan Animation is the act, process, or result of

Computer Animation CPSC 453 Fall 2018 Sonny Chan Animation is the act, process, or result of imparting life, interest, spirit, motion, or activity. Michael Ashikhmin (Chapter 16) Principles Keyframes Procedural Outline for Today

864 views • 48 slides
Foot & Ankle Trauma Panel Discussion 22 yo man, motorcycle accident Andrew Haskell, MD

Foot & Ankle Trauma Panel Discussion 22 yo man, motorcycle accident Andrew Haskell, MD

5/8/2014 Case 1 Foot & Ankle Trauma Panel Discussion 22 yo man, motorcycle accident Andrew Haskell, MD Moderator Presents with deformed, swollen leg slight tingling in toes, otherwise DNVI Bob Anderson, MD Trauma workup

481 views • 13 slides
Image formation robotics, calibration, structure from motion graphics, text/natural

Image formation robotics, calibration, structure from motion graphics, text/natural

Administrivia and survey results Topics: deep learning, CNNs, machine learning, AI Applications: self driving cars, face detection/recognition, etc Image formation robotics, calibration, structure from motion graphics, text/natural

634 views • 21 slides
Us Usin ing g YouTuber ubers s an and d Twit witch h Str treamer eamers s for In

Us Usin ing g YouTuber ubers s an and d Twit witch h Str treamer eamers s for In

Us Usin ing g YouTuber ubers s an and d Twit witch h Str treamer eamers s for In Inspir spirati tion on Mark k Wilk lkinson inson Nottingha ingham m Trent nt Univ iver ersity sity Video eo Gam ames es?! Se Seth

881 views • 59 slides
Live Streaming: Measurement and Analysis Cong Zhang * , Jiangchuan Liu * , Haiyang Wang + * Simon

Live Streaming: Measurement and Analysis Cong Zhang * , Jiangchuan Liu * , Haiyang Wang + * Simon

Towards Hybrid Cloud-assisted Crowdsourced Live Streaming: Measurement and Analysis Cong Zhang * , Jiangchuan Liu * , Haiyang Wang + * Simon Fraser University, + University of Minesota Duluth May, 2016 Outline Background Data description

2.57k views • 33 slides
Watch me playing, I am a professional A first study on video game live streaming M. Kaytoue 1 , A.

Watch me playing, I am a professional A first study on video game live streaming M. Kaytoue 1 , A.

Watch me playing, I am a professional A first study on video game live streaming M. Kaytoue 1 , A. Silva 1 , L. Cerf 1 , W. Meira Jr. 1 , C. Ra ssi 2 1 2 Belo Horizonte Brazil Nancy France Mining Social Network Dynamics @ WWW 2012

594 views • 38 slides
Latest atest Gener eneration tion of f Onlin line e Gam ames? es? Andy Fawkes Di

Latest atest Gener eneration tion of f Onlin line e Gam ames? es? Andy Fawkes Di

ITEC Stockholm 14 May 2019 Lear earning ning fr from om th the e Latest atest Gener eneration tion of f Onlin line e Gam ames? es? Andy Fawkes Di Disruption sruption If you want something new, you have to stop doing

577 views • 38 slides

More recommend