Oscillation	
  Compensating
Dynamic	
  Adaptive	
  Streaming	
  over	
  HTTP
Christopher	
  Mueller,	
  Stefan	
  Lederer,	
  Reinhard Grandl,	
  and	
  Christian	
  Timmerer
Alpen-­‐Adria-­‐Universität Klagenfurt	
  (AAU)	
  w Faculty	
  of	
  Technical	
  Sciences	
  (TEWI) w Department	
  of	
  Information	
  
Technology	
  (ITEC)	
  w Multimedia	
  Communication	
   (MMC) w Sensory	
  Experience	
  Lab	
  (SELab)
http://blog.timmerer.com w http://selab.itec.aau.at/w http://dash.itec.aau.at w christian.timmerer@itec.aau.at
Chief	
  Innovation	
  Officer	
  (CIO)	
  at	
  bitmovin	
  GmbH
http://www.bitmovin.com w christian.timmerer@bitmovin.com
Slides:	
  http://www.slideshare.net/christian.timmerer
IEEE	
  ICME	
  2015,	
  June	
  29	
  – July	
  3,	
  2015
July	
  2,	
  2015 IEEE	
  ICME	
  2015 2
Submission	
   deadline:	
  November	
  27,	
  2015
http://www.mmsys.org/ |	
  http://mmsys2016.itec.aau.at/ |	
  @mmsys2015
Outline
• Introduction,	
  Motivation,	
  Problem	
  Statement
• Metrics	
  and	
  Tools
• Buffer-­‐based	
  Adaptation	
  Algorithm	
  with	
  
Oscillation	
  Detection	
  and	
  Compensation
• Experimental	
  Results
• Conclusions	
  and	
  Future	
  Work
July	
  2,	
  2015 IEEE	
  ICME	
  2015 3
Over-­‐The-­‐Top	
  – Adaptive	
  Media	
  Streaming
• In	
  a	
  Nutshell	
  …
Adaptation logic is within the
client, not normatively specified
by the standard,subject to
research and development
July	
  2,	
  2015 IEEE	
  ICME	
  2015 4
Why	
  do	
  we	
  do	
  that?
• HTTP-­‐based	
  multimedia	
  streaming	
  
is	
  being	
  massively	
  deployed
– Accounts	
  for	
  more	
  than	
  60%	
  of	
  
Internet	
  traffic in	
  peak	
  periods
• Client-­‐centric	
  approach
– Adaptation	
  algorithm/logic
– Client	
  behavior	
  subject	
  to	
  research
– Throughput-­‐basedvs.	
  buffer-­‐based
• What	
  happens	
  when	
  multiple	
  
clients	
  compete with	
  each	
  other?
July	
  2,	
  2015 IEEE	
  ICME	
  2015 5
Source:	
  Global	
   Internet	
   Phenomena	
   Report:	
  2H	
  2014	
  
What’s	
  the	
  problem?
• Big	
  Buck	
  Bunny	
  with	
  different	
  
representations
• Throughput-­‐based	
  adaptation
• Common	
  test	
  setup w/	
  two	
  
clients	
  and	
  varying	
  bandwidth
July	
  2,	
  2015 IEEE	
  ICME	
  2015 6
5HTXHVWHGq0HGLDq%LWUDWH
0ESV
3
4
f
S
c
5HTXHVWHGq0HGLDq%LWUDWH
%XIIHU
6HFRQGV
3
43
f3
S3
c3
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
%XIIHU
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
Without	
  cache
What’s	
  the	
  problem?
• Big	
  Buck	
  Bunny	
  with	
  different	
  
representations
• Throughput-­‐based	
  adaptation
• Common	
  test	
  setup w/	
  two	
  
clients	
  and	
  varying	
  bandwidth
July	
  2,	
  2015 IEEE	
  ICME	
  2015 7
5HTXHVWHGq0HGLDq%LWUDWH
0ESV
3
4
f
S
c
5HTXHVWHGq0HGLDq%LWUDWH
%XIIHU
6HFRQGV
3
43
f3
S3
c3
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
%XIIHU
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
With	
  cache
Our	
  metrics	
  and	
  tools!
• Adaptation-­‐specific
– Quality	
  switching	
  variance:	
  change	
  of	
  representation
– Oscillation	
  variance:	
  includes	
  direction	
  of	
  switching
• Buffer-­‐specific
– Buffer	
  model	
  restricting	
  available	
  quality	
  levels
• Based	
  on	
  buffer	
  fill	
  state
• Fitting	
  to	
  available	
  quality	
  levels	
  &	
  network	
  conditions
• Different	
  behavior:	
  linear,	
  exponential,	
  logarithmic
– Worst	
  case	
  buffer:	
  minimum	
  buffer	
  fill	
  state	
  in	
  seconds	
  that	
  shall	
  
be	
  available	
  prior	
  to	
  the	
  download	
  of	
  segment
July	
  2,	
  2015 IEEE	
  ICME	
  2015 8
Our	
  approach!	
  (1/2)
• Buffer-­‐based	
  adaptation	
  algorithm	
  
including:
– Oscillation	
  detection
– Oscillation	
  compensation
– Fully	
  client-­‐centric
• Oscillation	
  factor
– Depends	
  on	
  quality	
  switching	
  
variance and	
  oscillation	
  variance
– Increases	
  when	
  both	
  metrics	
  
become	
  different
July	
  2,	
  2015 IEEE	
  ICME	
  2015 9
Our	
  approach!	
  (2/2)
• Buffer-­‐based	
  adaptation
– c	
  …	
  min.	
  buffer	
  level	
  (aka	
  steady	
  state)
– b	
  …	
  fitting	
  based	
  on	
  a	
  given	
  c
– a	
  …	
  max.	
  representation	
  bitrate
• Compensation	
  algorithm
– Low	
  &	
  high comp.
July	
  2,	
  2015 IEEE	
  ICME	
  2015 10
/RJDULWKPLFg%LWUDWHg5HVWULFWLRQ
0D[LPXPgSYDLODEOHg%LWUDWH
0LQLPXPgSYDLODEOHg%LWUDWH
SOORZHGg0HGLDg%LWUDWHg>0ESV@
u
A
v
l
b
%XIIHUg)LOOg6WDWXVg>h@
u usv usb usd usp A
Our	
  results!	
  (1/2)
July	
  2,	
  2015 IEEE	
  ICME	
  2015 11
5HTXHVWHGq0HGLDq%LWUDWH
0ESV
3
4
f
S
c 5HTXHVWHGq0HGLDq%LWUDWH
%XIIHU
6HFRQGV
3
43
f3
S3
c3
%XIIHU
2VFLOODWLRQq)DFWRU
3
3pf
3pc
3pn
3pl
4
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
2VFLOODWLRQq)DFWRU
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
5HTXHVWHGq0HGLDq%LWUDWH
0ESV
3
4
f
S
c 5HTXHVWHGq0HGLDq%LWUDWH
%XIIHU
6HFRQGV
3
43
f3
S3
c3
%XIIHU
2VFLOODWLRQq)DFWRU
3
3pf
3pc
3pn
3pl
4
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
2VFLOODWLRQq)DFWRU
6HFRQGV
3 o3 433 4o3 f33 fo3 S33
W
i
t
h
o
u
t
c
a
c
h
e
W
i
t
h
c
a
c
h
e
Our	
  results!	
  (2/2)
July	
  2,	
  2015 IEEE	
  ICME	
  2015 12
/RJDULWKPLFg×XIIHUg0RGHOg3GDSWDWLRQ
7KURXJKSXWg0HDVXUHPHQWg3GDSWDWLRQ
4XDOLWg6ZLWFKLQJg9DULDQFHg>0ESVð@
pAy
TîpAy
7LPHg>6HFRQGV@
A QA pAA pQA nAA nQA TAA
Without	
  cache
/RJDULWKPLFg×XIIHUg0RGHOg3GDSWDWLRQ
7KURXJKSXWg0HDVXUHPHQWg3GDSWDWLRQ
4XDOLWg6ZLWFKLQJg9DULDQFHg>0ESVð@
pAy
TîpAy
7LPHg>6HFRQGV@
A QA pAA pQA nAA nQA TAA
With	
  cache
Our	
  conclusions!
• We	
  highlighted	
  some	
  issues
– Throughput-­‐based	
   adaptation	
  logics
– Clients	
  competing for	
  bandwidth
• In	
  this	
  paper
– Buffer-­‐based	
  adaptation	
  models
– Clients	
  metrics for	
  oscillation	
  detection
– Oscillation	
  compensation algorithm
– Increase	
  streaming	
  performance	
  – higher	
  throughput	
   &	
  less	
  quality	
  
switches
• Important:	
  client-­‐centric	
  approach
– Enables	
  scalability,	
  maintains	
  advantages of	
  DASH,	
  and	
  is	
  deployed!
• Future	
  work
– Large-­‐scale	
  evaluations
July	
  2,	
  2015 IEEE	
  ICME	
  2015 13
http://www.dash-­‐player.com/
Thank	
  you	
  for	
  your	
  attention
...	
  questions,	
  comments,	
  etc.	
  are	
  welcome	
  …
Priv.-­‐Doz.	
  Dipl.-­‐Ing.	
  Dr.	
  Christian	
  Timmerer
Associate	
  Professor
Alpen-­‐Adria-­‐Universität Klagenfurt,	
  Department	
  of	
  Information	
  Technology	
  (ITEC)
Universitätsstrasse 65-­‐67,	
  A-­‐9020	
  Klagenfurt,	
  AUSTRIA
christian.timmerer@itec.uni-­‐klu.ac.at
http://research.timmerer.com/
Tel:	
  +43/463/2700	
  3621	
  Fax:	
  +43/463/2700	
  3699
©	
  Copyright:	
  Christian	
  Timmerer
14July	
  2,	
  2015 IEEE	
  ICME	
  2015
July	
  2,	
  2015 IEEE	
  ICME	
  2015 15
Submission	
   deadline:	
  November	
  27,	
  2015
http://www.mmsys.org/ |	
  http://mmsys2016.itec.aau.at/ |	
  @mmsys2015

More Related Content

PDF
Quality of Experience for Inter-Destination Media Synchronization
PPTX
An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments
PPTX
Dynamic Adaptive Streaming over HTTP (DASH)
PPTX
Ultra-High-Definition Quality of Experience with MPEG-DASH
PPTX
A Seamless Web Integration of Adaptive HTTP Streaming
PPTX
MPEG-DASH Reference Software and Conformance
PDF
Mobile Movies with HTTP Live Streaming (CocoaConf DC, March 2013)
PPTX
HTTP Streaming of MPEG Media
Quality of Experience for Inter-Destination Media Synchronization
An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments
Dynamic Adaptive Streaming over HTTP (DASH)
Ultra-High-Definition Quality of Experience with MPEG-DASH
A Seamless Web Integration of Adaptive HTTP Streaming
MPEG-DASH Reference Software and Conformance
Mobile Movies with HTTP Live Streaming (CocoaConf DC, March 2013)
HTTP Streaming of MPEG Media

What's hot (14)

PPTX
Adaptive Media Streaming over Emerging Protocols
PPTX
Dynamic Adaptive Streaming over HTTP Dataset
PPTX
PPTX
Distributed DASH Dataset
PPTX
Adaptive Video over ICN @ IETF'87
PDF
Tile-based Streaming of 8K Omnidirectional Video: Subjective and Objective Qo...
PDF
AVSTP2P: Welcome Message from the Chairs
PPT
MPEG-DASH Conformance and Reference Software
PPTX
DASH at the ACM Multimedia 2011
PPTX
libdash 2.0
PPTX
Using SVC for DASH in Mobile Environments
PPTX
MPEG-DASH open source tools and cloud services
PPTX
CAdViSE or how to find the Sweet Spots of ABR Systems
PDF
Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks
Adaptive Media Streaming over Emerging Protocols
Dynamic Adaptive Streaming over HTTP Dataset
Distributed DASH Dataset
Adaptive Video over ICN @ IETF'87
Tile-based Streaming of 8K Omnidirectional Video: Subjective and Objective Qo...
AVSTP2P: Welcome Message from the Chairs
MPEG-DASH Conformance and Reference Software
DASH at the ACM Multimedia 2011
libdash 2.0
Using SVC for DASH in Mobile Environments
MPEG-DASH open source tools and cloud services
CAdViSE or how to find the Sweet Spots of ABR Systems
Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks
Ad

Similar to Oscillation Compensating Dynamic Adaptive Streaming over HTTP (20)

PDF
Monitoring of Transmission and Distribution Grids using PMUs
PDF
On the representativeness of measurements
PDF
An Introduction to ATM Networks 1st Edition Harry G. Perros
PDF
RuleML2015: Compact representation of conditional probability for rule-based...
PDF
Kikusui general catalogue 2021 part 1
PDF
IRJET- Automated Water Conservation and Theft Detection using IOT
PDF
IRJET-E-Blood Bank Application using Cloud Computing
PDF
Industry outlook_ ABB.pdf
PDF
November 2024: Top 10 Read Article in Computer Science, Engineering and Appli...
PDF
Poka yoke implimentation on punching machine a case study
PDF
Bovini (CATTLE) And Dairy Farm Management
PDF
CAdViSE or how to find the sweet spots of ABR systems
PDF
IRJET-Smart System for Food Industries and Bakeries
PDF
minor project report
PDF
Internet of Things and Energy at SAP for Utilities
DOCX
ECET 365 Success Begins /newtonhelp.com 
PDF
April 2025: Top 10 Read Article in Computer Science, Engineering and Applicat...
PPTX
Variogram-derived measures for QC purposes
PDF
An Introduction To Packet Microwave Systems And Technologies Paolo Volpato
PDF
Master slave autonomous surveillance bot for military applications
Monitoring of Transmission and Distribution Grids using PMUs
On the representativeness of measurements
An Introduction to ATM Networks 1st Edition Harry G. Perros
RuleML2015: Compact representation of conditional probability for rule-based...
Kikusui general catalogue 2021 part 1
IRJET- Automated Water Conservation and Theft Detection using IOT
IRJET-E-Blood Bank Application using Cloud Computing
Industry outlook_ ABB.pdf
November 2024: Top 10 Read Article in Computer Science, Engineering and Appli...
Poka yoke implimentation on punching machine a case study
Bovini (CATTLE) And Dairy Farm Management
CAdViSE or how to find the sweet spots of ABR systems
IRJET-Smart System for Food Industries and Bakeries
minor project report
Internet of Things and Energy at SAP for Utilities
ECET 365 Success Begins /newtonhelp.com 
April 2025: Top 10 Read Article in Computer Science, Engineering and Applicat...
Variogram-derived measures for QC purposes
An Introduction To Packet Microwave Systems And Technologies Paolo Volpato
Master slave autonomous surveillance bot for military applications
Ad

More from Alpen-Adria-Universität (20)

PDF
Energy-Quality-aware Variable Framerate Pareto-Front for Adaptive Video Strea...
PPTX
End-to-end Quality of Experience Evaluation for HTTP Adaptive Streaming
PDF
HTTP Adaptive Streaming – Quo Vadis (2024)
PDF
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
PDF
Video Streaming: Then, Now, and in the Future
PDF
VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
PDF
GREEM: An Open-Source Energy Measurement Tool for Video Processing
PDF
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
PDF
VEEP: Video Encoding Energy and CO₂ Emission Prediction
PDF
Content-adaptive Video Coding for HTTP Adaptive Streaming
PPTX
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
PPTX
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Vid...
PPTX
Optimizing Video Streaming for Sustainability and Quality: The Role of Prese...
PDF
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
PPTX
Machine Learning Based Resource Utilization Prediction in the Computing Conti...
PDF
Evaluation of Quality of Experience of ABR Schemes in Gaming Stream
PDF
Network-Assisted Delivery of Adaptive Video Streaming Services through CDN, S...
PDF
Multi-access Edge Computing for Adaptive Video Streaming
PPTX
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
PDF
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
Energy-Quality-aware Variable Framerate Pareto-Front for Adaptive Video Strea...
End-to-end Quality of Experience Evaluation for HTTP Adaptive Streaming
HTTP Adaptive Streaming – Quo Vadis (2024)
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Video Streaming: Then, Now, and in the Future
VEED: Video Encoding Energy and CO2 Emissions Dataset for AWS EC2 instances
GREEM: An Open-Source Energy Measurement Tool for Video Processing
Optimal Quality and Efficiency in Adaptive Live Streaming with JND-Aware Low ...
VEEP: Video Encoding Energy and CO₂ Emission Prediction
Content-adaptive Video Coding for HTTP Adaptive Streaming
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Video...
Empowerment of Atypical Viewers via Low-Effort Personalized Modeling of Vid...
Optimizing Video Streaming for Sustainability and Quality: The Role of Prese...
Energy-Efficient Multi-Codec Bitrate-Ladder Estimation for Adaptive Video Str...
Machine Learning Based Resource Utilization Prediction in the Computing Conti...
Evaluation of Quality of Experience of ABR Schemes in Gaming Stream
Network-Assisted Delivery of Adaptive Video Streaming Services through CDN, S...
Multi-access Edge Computing for Adaptive Video Streaming
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...

Recently uploaded (20)

PDF
The influence of sentiment analysis in enhancing early warning system model f...
PPTX
MicrosoftCybserSecurityReferenceArchitecture-April-2025.pptx
PDF
How ambidextrous entrepreneurial leaders react to the artificial intelligence...
PDF
1 - Historical Antecedents, Social Consideration.pdf
PPT
Module 1.ppt Iot fundamentals and Architecture
PPTX
AI IN MARKETING- PRESENTED BY ANWAR KABIR 1st June 2025.pptx
PDF
A contest of sentiment analysis: k-nearest neighbor versus neural network
PPTX
Benefits of Physical activity for teenagers.pptx
PPT
What is a Computer? Input Devices /output devices
PPT
Galois Field Theory of Risk: A Perspective, Protocol, and Mathematical Backgr...
PDF
Two-dimensional Klein-Gordon and Sine-Gordon numerical solutions based on dee...
PDF
Getting started with AI Agents and Multi-Agent Systems
PDF
Produktkatalog für HOBO Datenlogger, Wetterstationen, Sensoren, Software und ...
PDF
Five Habits of High-Impact Board Members
PDF
Abstractive summarization using multilingual text-to-text transfer transforme...
PDF
ENT215_Completing-a-large-scale-migration-and-modernization-with-AWS.pdf
PDF
A Late Bloomer's Guide to GenAI: Ethics, Bias, and Effective Prompting - Boha...
PDF
A proposed approach for plagiarism detection in Myanmar Unicode text
PDF
OpenACC and Open Hackathons Monthly Highlights July 2025
PDF
sbt 2.0: go big (Scala Days 2025 edition)
The influence of sentiment analysis in enhancing early warning system model f...
MicrosoftCybserSecurityReferenceArchitecture-April-2025.pptx
How ambidextrous entrepreneurial leaders react to the artificial intelligence...
1 - Historical Antecedents, Social Consideration.pdf
Module 1.ppt Iot fundamentals and Architecture
AI IN MARKETING- PRESENTED BY ANWAR KABIR 1st June 2025.pptx
A contest of sentiment analysis: k-nearest neighbor versus neural network
Benefits of Physical activity for teenagers.pptx
What is a Computer? Input Devices /output devices
Galois Field Theory of Risk: A Perspective, Protocol, and Mathematical Backgr...
Two-dimensional Klein-Gordon and Sine-Gordon numerical solutions based on dee...
Getting started with AI Agents and Multi-Agent Systems
Produktkatalog für HOBO Datenlogger, Wetterstationen, Sensoren, Software und ...
Five Habits of High-Impact Board Members
Abstractive summarization using multilingual text-to-text transfer transforme...
ENT215_Completing-a-large-scale-migration-and-modernization-with-AWS.pdf
A Late Bloomer's Guide to GenAI: Ethics, Bias, and Effective Prompting - Boha...
A proposed approach for plagiarism detection in Myanmar Unicode text
OpenACC and Open Hackathons Monthly Highlights July 2025
sbt 2.0: go big (Scala Days 2025 edition)

Oscillation Compensating Dynamic Adaptive Streaming over HTTP

  • 1. Oscillation  Compensating Dynamic  Adaptive  Streaming  over  HTTP Christopher  Mueller,  Stefan  Lederer,  Reinhard Grandl,  and  Christian  Timmerer Alpen-­‐Adria-­‐Universität Klagenfurt  (AAU)  w Faculty  of  Technical  Sciences  (TEWI) w Department  of  Information   Technology  (ITEC)  w Multimedia  Communication   (MMC) w Sensory  Experience  Lab  (SELab) http://blog.timmerer.com w http://selab.itec.aau.at/w http://dash.itec.aau.at w christian.timmerer@itec.aau.at Chief  Innovation  Officer  (CIO)  at  bitmovin  GmbH http://www.bitmovin.com w christian.timmerer@bitmovin.com Slides:  http://www.slideshare.net/christian.timmerer IEEE  ICME  2015,  June  29  – July  3,  2015
  • 2. July  2,  2015 IEEE  ICME  2015 2 Submission   deadline:  November  27,  2015 http://www.mmsys.org/ |  http://mmsys2016.itec.aau.at/ |  @mmsys2015
  • 3. Outline • Introduction,  Motivation,  Problem  Statement • Metrics  and  Tools • Buffer-­‐based  Adaptation  Algorithm  with   Oscillation  Detection  and  Compensation • Experimental  Results • Conclusions  and  Future  Work July  2,  2015 IEEE  ICME  2015 3
  • 4. Over-­‐The-­‐Top  – Adaptive  Media  Streaming • In  a  Nutshell  … Adaptation logic is within the client, not normatively specified by the standard,subject to research and development July  2,  2015 IEEE  ICME  2015 4
  • 5. Why  do  we  do  that? • HTTP-­‐based  multimedia  streaming   is  being  massively  deployed – Accounts  for  more  than  60%  of   Internet  traffic in  peak  periods • Client-­‐centric  approach – Adaptation  algorithm/logic – Client  behavior  subject  to  research – Throughput-­‐basedvs.  buffer-­‐based • What  happens  when  multiple   clients  compete with  each  other? July  2,  2015 IEEE  ICME  2015 5 Source:  Global   Internet   Phenomena   Report:  2H  2014  
  • 6. What’s  the  problem? • Big  Buck  Bunny  with  different   representations • Throughput-­‐based  adaptation • Common  test  setup w/  two   clients  and  varying  bandwidth July  2,  2015 IEEE  ICME  2015 6 5HTXHVWHGq0HGLDq%LWUDWH 0ESV 3 4 f S c 5HTXHVWHGq0HGLDq%LWUDWH %XIIHU 6HFRQGV 3 43 f3 S3 c3 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 %XIIHU 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 Without  cache
  • 7. What’s  the  problem? • Big  Buck  Bunny  with  different   representations • Throughput-­‐based  adaptation • Common  test  setup w/  two   clients  and  varying  bandwidth July  2,  2015 IEEE  ICME  2015 7 5HTXHVWHGq0HGLDq%LWUDWH 0ESV 3 4 f S c 5HTXHVWHGq0HGLDq%LWUDWH %XIIHU 6HFRQGV 3 43 f3 S3 c3 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 %XIIHU 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 With  cache
  • 8. Our  metrics  and  tools! • Adaptation-­‐specific – Quality  switching  variance:  change  of  representation – Oscillation  variance:  includes  direction  of  switching • Buffer-­‐specific – Buffer  model  restricting  available  quality  levels • Based  on  buffer  fill  state • Fitting  to  available  quality  levels  &  network  conditions • Different  behavior:  linear,  exponential,  logarithmic – Worst  case  buffer:  minimum  buffer  fill  state  in  seconds  that  shall   be  available  prior  to  the  download  of  segment July  2,  2015 IEEE  ICME  2015 8
  • 9. Our  approach!  (1/2) • Buffer-­‐based  adaptation  algorithm   including: – Oscillation  detection – Oscillation  compensation – Fully  client-­‐centric • Oscillation  factor – Depends  on  quality  switching   variance and  oscillation  variance – Increases  when  both  metrics   become  different July  2,  2015 IEEE  ICME  2015 9
  • 10. Our  approach!  (2/2) • Buffer-­‐based  adaptation – c  …  min.  buffer  level  (aka  steady  state) – b  …  fitting  based  on  a  given  c – a  …  max.  representation  bitrate • Compensation  algorithm – Low  &  high comp. July  2,  2015 IEEE  ICME  2015 10 /RJDULWKPLFg%LWUDWHg5HVWULFWLRQ 0D[LPXPgSYDLODEOHg%LWUDWH 0LQLPXPgSYDLODEOHg%LWUDWH SOORZHGg0HGLDg%LWUDWHg>0ESV@ u A v l b %XIIHUg)LOOg6WDWXVg>h@ u usv usb usd usp A
  • 11. Our  results!  (1/2) July  2,  2015 IEEE  ICME  2015 11 5HTXHVWHGq0HGLDq%LWUDWH 0ESV 3 4 f S c 5HTXHVWHGq0HGLDq%LWUDWH %XIIHU 6HFRQGV 3 43 f3 S3 c3 %XIIHU 2VFLOODWLRQq)DFWRU 3 3pf 3pc 3pn 3pl 4 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 2VFLOODWLRQq)DFWRU 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 5HTXHVWHGq0HGLDq%LWUDWH 0ESV 3 4 f S c 5HTXHVWHGq0HGLDq%LWUDWH %XIIHU 6HFRQGV 3 43 f3 S3 c3 %XIIHU 2VFLOODWLRQq)DFWRU 3 3pf 3pc 3pn 3pl 4 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 2VFLOODWLRQq)DFWRU 6HFRQGV 3 o3 433 4o3 f33 fo3 S33 W i t h o u t c a c h e W i t h c a c h e
  • 12. Our  results!  (2/2) July  2,  2015 IEEE  ICME  2015 12 /RJDULWKPLFg×XIIHUg0RGHOg3GDSWDWLRQ 7KURXJKSXWg0HDVXUHPHQWg3GDSWDWLRQ 4XDOLWg6ZLWFKLQJg9DULDQFHg>0ESVð@ pAy TîpAy 7LPHg>6HFRQGV@ A QA pAA pQA nAA nQA TAA Without  cache /RJDULWKPLFg×XIIHUg0RGHOg3GDSWDWLRQ 7KURXJKSXWg0HDVXUHPHQWg3GDSWDWLRQ 4XDOLWg6ZLWFKLQJg9DULDQFHg>0ESVð@ pAy TîpAy 7LPHg>6HFRQGV@ A QA pAA pQA nAA nQA TAA With  cache
  • 13. Our  conclusions! • We  highlighted  some  issues – Throughput-­‐based   adaptation  logics – Clients  competing for  bandwidth • In  this  paper – Buffer-­‐based  adaptation  models – Clients  metrics for  oscillation  detection – Oscillation  compensation algorithm – Increase  streaming  performance  – higher  throughput   &  less  quality   switches • Important:  client-­‐centric  approach – Enables  scalability,  maintains  advantages of  DASH,  and  is  deployed! • Future  work – Large-­‐scale  evaluations July  2,  2015 IEEE  ICME  2015 13 http://www.dash-­‐player.com/
  • 14. Thank  you  for  your  attention ...  questions,  comments,  etc.  are  welcome  … Priv.-­‐Doz.  Dipl.-­‐Ing.  Dr.  Christian  Timmerer Associate  Professor Alpen-­‐Adria-­‐Universität Klagenfurt,  Department  of  Information  Technology  (ITEC) Universitätsstrasse 65-­‐67,  A-­‐9020  Klagenfurt,  AUSTRIA christian.timmerer@itec.uni-­‐klu.ac.at http://research.timmerer.com/ Tel:  +43/463/2700  3621  Fax:  +43/463/2700  3699 ©  Copyright:  Christian  Timmerer 14July  2,  2015 IEEE  ICME  2015
  • 15. July  2,  2015 IEEE  ICME  2015 15 Submission   deadline:  November  27,  2015 http://www.mmsys.org/ |  http://mmsys2016.itec.aau.at/ |  @mmsys2015