SlideShare uma empresa Scribd logo
1 de 25
Baixar para ler offline
Days of Future Past: An Optimization-based
Adaptive Bitrate Algorithm over HTTP/3
EPIQ’21 (ACM CoNEXT 2021)
07.-10.12.2021 | Munich, Germany
Daniele Lorenzi, Minh Nguyen, Farzad Tashtarian, Christian Timmerer, Hermann Hellwagner, Simone Milani
Christian Doppler laboratory ATHENA | Alpen-Adria University | Austria
daniele.lorenzi@aau.at | https://athena.itec.aau.at/
1
● Introduction
● Motivation
● Proposed method
● Experimental setup
● Results and analysis
● Conclusion
Agenda
2
3
Introduction
Introduction: HAS Schema
4
Video
segmentation
Video encoding
...
...
...
Server Client
Adaptive BitRate
(ABR) algorithm
Throughput
estimation
Playout buffer
Video decoding
...
HTTP GET requests
Version 3
Version 2
Version 1
Throughput
Time
Introduction: HTTP/3 & QUIC
5
Stream
Multiplexing
0-RTT Connection
Establishment
Stream Termination
HTTP/3 & QUIC
X
X
6
Motivation
Motivation
7
8
Proposed Method
DoFP: An Optimization-based ABR algorithm
9
● Mixed Integer Linear Programming (MILP) model that selects:
○ Bitrate for the next segments;
○ Which segments from the buffer need to be upgraded;
○ Bitrate for these segments.
Par.
Desc.
Set of
indexes of
k buffered
segments
+ next one
Quality
level of
ith
segment
Binary
variable:
1 → (re-)
download ith
segment at
quality level j;
Deadline
to (re-)
download
ith
segment
Current
buffer
level
(Max.)
Buffer
size
Size of ith
segment
with quality
level 𝑗
(kbits)
Assigned
throughput
to (re-)
download
ith
segment
Available
throughput
between
player and
server
DoFP: An Optimization-based ABR algorithm
10
● 1st constraint expresses the univocity of the pair (index, quality):
Max. quality level
DoFP: An Optimization-based ABR algorithm
11
● Define the deadlines for each segment (where , ):
● 2nd constraint ensure that the download time is lower than the deadline:
Not valid for j=qi
Seg. length
Safety par.
DoFP: An Optimization-based ABR algorithm
12
● 3rd constraint checks the sum of the assigned throughputs to be at
most the total available one:
No Multiplexing With Multiplexing
DoFP: An Optimization-based ABR algorithm
13
● The MILP model is finally introduced as follows:
Objective
Function
Constraints
Variables
14
Experimental setup
Experimental setup
15
● HAS + LSQUIC [1] testbed
● 5-min test sequence (Tears of Steel - begin)
● Bitrate ladder: {107, 240, 346, 715, 1347, 2426, 4121} kbps [2]
● Resolution: {144, 240, 360, 480, 720, 1080, 1440} p [2]
● Codec: H.264
● Linux tc (bash script)
○ 4G Network trace
○ RTT: 40 ms
● 𝛕 = 4s, Bmax
= 20s
● 𝛍 = 0.1, 𝛂 = 0.25, 𝛃 = 0.5, 𝛄 = 0.75
[1] https://github.com/litespeedtech/lsquic
[2] T. Karagkioules, et al.: A Public Dataset for YouTube’s Mobile Streaming Client.
16
Results and analysis
Results and analysis
17
● Metrics considered:
○ Average quality: average quality level of the played segments
○ Video instability: average quality fluctuation among adjacent segments
○ Number of switches: number of segments whose quality is lower than their
previous one
○ Number of stalls: number of buffer underruns
○ Stall duration: total video freeze time
○ QoE score: computed via ITU-T P.1203 mode 0 and its extension [3]
[3] https://github.com/Telecommunication-Telemedia-Assessment/itu-p1203-codecextension
Results and analysis
18
● Results: Comparison among different DoFP versions:
○ DoFP/B: next segment, then retransmitted ones seq. in order as in the buffer
○ DoFP/M: with stream multiplexing feature and concurrent requests
○ DoFP/C: with stream cancellation feature
○ DoFP/MC: with both stream multiplexing and stream cancellation
Avg.
quality
Video inst. N. switches N. stalls Stall dur. (s) QoE
DoFP/B 6.12 0.53 8.2 1.8 6.7 3.15
DoFP/M 6.14 0.47 7.8 1.8 6.7 3.25
DoFP/C 6.11 0.48 7.8 0.6 1.7 3.36
DoFP/MC 6.02 0.54 10.6 0.0 0.0 3.38
Multiplexing and cancellation features enhance DoFP results
Results and analysis
19
● Results: Comparison with state-of-the-art approaches
○ SARA → DoFP/MC: highest % of quality 7 seg. (74% → 64%) and avg. quality
(6.12 → 6.02)
○ DoFP/MC → others: lowest % of quality 1 seg. (3.2% → > 6.1%)
Percentage of quality levels and average quality
Results and analysis
20
● Results: Comparison with state-of-the-art approaches
○ BBA-0: lowest video instability (0.53); DoFP/MC: second lowest (0.54)
○ DoFP/MC: high # of switches (10.6) → upgrade quality, not eliminate gaps
Number of switches and video Instability
Results and analysis
21
● Results: Comparison with state-of-the-art approaches
○ DoFP/MC: 0.0 stalls and 0.0s stall duration
○ AGG (0.4 - 1.47s), BOLA (1 - 3.88s) → SARA (2.8 - 9.71s), BBA-0 (4 - 14.41s)
Number of stalls and stall duration
Results and analysis
22
● Results: Comparison with state-of-the-art approaches
○ DoFP/MC: best QoE score (3.38)
○ Up to 33.9% increment w.r.t the other approaches
QoE scores
23
Conclusions
Conclusions
24
● DoFP(/MC): a MILP model to provide high QoE (and low stall-probability)
through HTTP/3 and QUIC features
● Taking into account throughput, buffer, and quality of each buffered
segment
● The model chooses the bitrates for the next segment and (if needed) for the
buffered segments to be re-transmitted
● DoFP/MC: outperforms the other approaches with the highest QoE score
● Multiplexing and cancellation features enhance DoFP results
● In the future, investigate the stream priority feature, the impact of DoFP’s
parameters and different streaming (video sequence, bitrate ladder, segment
duration) and network scenarios (bandwidth traces)
Thank you
25

Mais conteúdo relacionado

Mais procurados

On the Impact of Viewing Distance on Perceived Video Quality
On the Impact of Viewing Distance on Perceived Video QualityOn the Impact of Viewing Distance on Perceived Video Quality
On the Impact of Viewing Distance on Perceived Video Quality
Alpen-Adria-Universität
 
Quality impact of scalable video coding tunneling for media aware content del...
Quality impact of scalable video coding tunneling for media aware content del...Quality impact of scalable video coding tunneling for media aware content del...
Quality impact of scalable video coding tunneling for media aware content del...
Alpen-Adria-Universität
 
CAdViSE or how to find the Sweet Spots of ABR Systems
CAdViSE or how to find the Sweet Spots of ABR SystemsCAdViSE or how to find the Sweet Spots of ABR Systems
CAdViSE or how to find the Sweet Spots of ABR Systems
Alpen-Adria-Universität
 
HTTP Adaptive Streaming – Quo Vadis?
HTTP Adaptive Streaming – Quo Vadis?HTTP Adaptive Streaming – Quo Vadis?
HTTP Adaptive Streaming – Quo Vadis?
Alpen-Adria-Universität
 

Mais procurados (20)

On the Impact of Viewing Distance on Perceived Video Quality
On the Impact of Viewing Distance on Perceived Video QualityOn the Impact of Viewing Distance on Perceived Video Quality
On the Impact of Viewing Distance on Perceived Video Quality
 
Understanding Quality of Experience of Heuristic-based HTTP Adaptive Bitrate ...
Understanding Quality of Experience of Heuristic-based HTTP Adaptive Bitrate ...Understanding Quality of Experience of Heuristic-based HTTP Adaptive Bitrate ...
Understanding Quality of Experience of Heuristic-based HTTP Adaptive Bitrate ...
 
Policy-driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-driven Dynamic HTTP Adaptive Streaming Player Environment
 
H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive...
H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive...H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive...
H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive...
 
Machine Learning Based Video Coding Enhancements for HTTP Adaptive Streaming
Machine Learning Based Video Coding Enhancements for HTTP Adaptive StreamingMachine Learning Based Video Coding Enhancements for HTTP Adaptive Streaming
Machine Learning Based Video Coding Enhancements for HTTP Adaptive Streaming
 
Quality impact of scalable video coding tunneling for media aware content del...
Quality impact of scalable video coding tunneling for media aware content del...Quality impact of scalable video coding tunneling for media aware content del...
Quality impact of scalable video coding tunneling for media aware content del...
 
LwTE: Light-weight Transcoding at the Edge
LwTE: Light-weight Transcoding at the EdgeLwTE: Light-weight Transcoding at the Edge
LwTE: Light-weight Transcoding at the Edge
 
20 Years of Streaming in 20 Minutes
20 Years of Streaming in 20 Minutes20 Years of Streaming in 20 Minutes
20 Years of Streaming in 20 Minutes
 
Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks
 Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks
Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks
 
SLFC: Scalable Light Field Coding
SLFC: Scalable Light Field CodingSLFC: Scalable Light Field Coding
SLFC: Scalable Light Field Coding
 
Quality Optimization of Live Streaming Services over HTTP with Reinforcement ...
Quality Optimization of Live Streaming Services over HTTP with Reinforcement ...Quality Optimization of Live Streaming Services over HTTP with Reinforcement ...
Quality Optimization of Live Streaming Services over HTTP with Reinforcement ...
 
EADAS: Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming
EADAS: Edge Assisted Adaptation Scheme for HTTP Adaptive StreamingEADAS: Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming
EADAS: Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming
 
INCEPT: Intra CU Depth Prediction for HEVC
INCEPT: Intra CU Depth Prediction for HEVCINCEPT: Intra CU Depth Prediction for HEVC
INCEPT: Intra CU Depth Prediction for HEVC
 
CAdViSE or how to find the Sweet Spots of ABR Systems
CAdViSE or how to find the Sweet Spots of ABR SystemsCAdViSE or how to find the Sweet Spots of ABR Systems
CAdViSE or how to find the Sweet Spots of ABR Systems
 
A Distributed Approach for Bitrate Selection in HTTP Adaptive Streaming
A Distributed Approach for Bitrate Selection in HTTP Adaptive StreamingA Distributed Approach for Bitrate Selection in HTTP Adaptive Streaming
A Distributed Approach for Bitrate Selection in HTTP Adaptive Streaming
 
HTTP Adaptive Streaming – Quo Vadis?
HTTP Adaptive Streaming – Quo Vadis?HTTP Adaptive Streaming – Quo Vadis?
HTTP Adaptive Streaming – Quo Vadis?
 
A Channel Allocation Algorithm for Cognitive Radio Users Based on Channel Sta...
A Channel Allocation Algorithm for Cognitive Radio Users Based on Channel Sta...A Channel Allocation Algorithm for Cognitive Radio Users Based on Channel Sta...
A Channel Allocation Algorithm for Cognitive Radio Users Based on Channel Sta...
 
Labmeeting - 20150831 - Overhead and Performance of Low Latency Live Streamin...
Labmeeting - 20150831 - Overhead and Performance of Low Latency Live Streamin...Labmeeting - 20150831 - Overhead and Performance of Low Latency Live Streamin...
Labmeeting - 20150831 - Overhead and Performance of Low Latency Live Streamin...
 
Bandwidth Prediction in Low-Latency Chunked Streaming
Bandwidth Prediction in Low-Latency Chunked StreamingBandwidth Prediction in Low-Latency Chunked Streaming
Bandwidth Prediction in Low-Latency Chunked Streaming
 
Press Release of 131st WG11 (MPEG) Meeting
Press Release of 131st WG11 (MPEG) MeetingPress Release of 131st WG11 (MPEG) Meeting
Press Release of 131st WG11 (MPEG) Meeting
 

Semelhante a EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorithm over HTTP/3

Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Alpen-Adria-Universität
 
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Minh Nguyen
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
Videoguy
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
Videoguy
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
Videoguy
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
Videoguy
 
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming ApplicationsSARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
Alpen-Adria-Universität
 
CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...
CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...
CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...
Reza Farahani
 
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
Alpen-Adria-Universität
 
Paper id 2120148
Paper id 2120148Paper id 2120148
Paper id 2120148
IJRAT
 

Semelhante a EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorithm over HTTP/3 (20)

Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
 
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-Driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-Driven Dynamic HTTP Adaptive Streaming Player Environment
 
IEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdfIEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdf
 
Midtem_19082004
Midtem_19082004Midtem_19082004
Midtem_19082004
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
 
Video coding technology proposal by
Video coding technology proposal by Video coding technology proposal by
Video coding technology proposal by
 
ACM NOSSDAV'21-ES-HAS_ An Edge- and SDN-Assisted Framework for HTTP Adaptive ...
ACM NOSSDAV'21-ES-HAS_ An Edge- and SDN-Assisted Framework for HTTP Adaptive ...ACM NOSSDAV'21-ES-HAS_ An Edge- and SDN-Assisted Framework for HTTP Adaptive ...
ACM NOSSDAV'21-ES-HAS_ An Edge- and SDN-Assisted Framework for HTTP Adaptive ...
 
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming ApplicationsSARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
 
FaME-ML: Fast Multirate Encoding for HTTP Adaptive Streaming Using Machine Le...
FaME-ML: Fast Multirate Encoding for HTTP Adaptive Streaming Using Machine Le...FaME-ML: Fast Multirate Encoding for HTTP Adaptive Streaming Using Machine Le...
FaME-ML: Fast Multirate Encoding for HTTP Adaptive Streaming Using Machine Le...
 
CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...
CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...
CSDN_ CDN-Aware QoE Optimization inSDN-Assisted HTTP Adaptive Video Streaming...
 
IEEE_ICC'23_SARENA.pdf
IEEE_ICC'23_SARENA.pdfIEEE_ICC'23_SARENA.pdf
IEEE_ICC'23_SARENA.pdf
 
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation...
 
HDMI Troubleshooting & System Design
HDMI Troubleshooting & System DesignHDMI Troubleshooting & System Design
HDMI Troubleshooting & System Design
 
Paper id 2120148
Paper id 2120148Paper id 2120148
Paper id 2120148
 
IEEE ICC'22_ LEADER_ A Collaborative Edge- and SDN-Assisted Framework for HTT...
IEEE ICC'22_ LEADER_ A Collaborative Edge- and SDN-Assisted Framework for HTT...IEEE ICC'22_ LEADER_ A Collaborative Edge- and SDN-Assisted Framework for HTT...
IEEE ICC'22_ LEADER_ A Collaborative Edge- and SDN-Assisted Framework for HTT...
 
C08 – Updated planning and commissioning guidelines for Profinet - Xaver Sch...
C08 – Updated planning and commissioning guidelines for Profinet -  Xaver Sch...C08 – Updated planning and commissioning guidelines for Profinet -  Xaver Sch...
C08 – Updated planning and commissioning guidelines for Profinet - Xaver Sch...
 
Aruna Ravi - M.S Thesis
Aruna Ravi - M.S ThesisAruna Ravi - M.S Thesis
Aruna Ravi - M.S Thesis
 
Optimizing QoE and Latency of Live Video Streaming Using Edge Computing a...
Optimizing  QoE and Latency of  Live Video Streaming Using  Edge Computing  a...Optimizing  QoE and Latency of  Live Video Streaming Using  Edge Computing  a...
Optimizing QoE and Latency of Live Video Streaming Using Edge Computing a...
 

Mais de Minh Nguyen

CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming
CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive StreamingCADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming
CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming
Minh Nguyen
 
CAdViSE or how to find the sweet spots of ABR systems
CAdViSE or how to find the sweet spots of ABR systemsCAdViSE or how to find the sweet spots of ABR systems
CAdViSE or how to find the sweet spots of ABR systems
Minh Nguyen
 

Mais de Minh Nguyen (7)

CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming
CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive StreamingCADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming
CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming
 
CAdViSE or how to find the sweet spots of ABR systems
CAdViSE or how to find the sweet spots of ABR systemsCAdViSE or how to find the sweet spots of ABR systems
CAdViSE or how to find the sweet spots of ABR systems
 
Video streaming using light-weight transcoding and in-network intelligence
Video streaming using light-weight transcoding and in-network intelligenceVideo streaming using light-weight transcoding and in-network intelligence
Video streaming using light-weight transcoding and in-network intelligence
 
Efficient bitrate ladder construction for live video streaming
Efficient bitrate ladder construction for live video streamingEfficient bitrate ladder construction for live video streaming
Efficient bitrate ladder construction for live video streaming
 
RICHTER: hybrid P2P-CDN architecture for low latency live video streaming
RICHTER: hybrid P2P-CDN architecture for low latency live video streamingRICHTER: hybrid P2P-CDN architecture for low latency live video streaming
RICHTER: hybrid P2P-CDN architecture for low latency live video streaming
 
MHV'22 - Super-resolution Based Bitrate Adaptation for HTTP Adaptive Streamin...
MHV'22 - Super-resolution Based Bitrate Adaptation for HTTP Adaptive Streamin...MHV'22 - Super-resolution Based Bitrate Adaptation for HTTP Adaptive Streamin...
MHV'22 - Super-resolution Based Bitrate Adaptation for HTTP Adaptive Streamin...
 
MHV'22 - Take the Red Pill for H3 and See How Deep the Rabbit Hole Goes
MHV'22 - Take the Red Pill for H3 and See How Deep the Rabbit Hole GoesMHV'22 - Take the Red Pill for H3 and See How Deep the Rabbit Hole Goes
MHV'22 - Take the Red Pill for H3 and See How Deep the Rabbit Hole Goes
 

Último

Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Victor Rentea
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 

Último (20)

Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Spring Boot vs Quarkus the ultimate battle - DevoxxUK
Spring Boot vs Quarkus the ultimate battle - DevoxxUKSpring Boot vs Quarkus the ultimate battle - DevoxxUK
Spring Boot vs Quarkus the ultimate battle - DevoxxUK
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 

EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorithm over HTTP/3

  • 1. Days of Future Past: An Optimization-based Adaptive Bitrate Algorithm over HTTP/3 EPIQ’21 (ACM CoNEXT 2021) 07.-10.12.2021 | Munich, Germany Daniele Lorenzi, Minh Nguyen, Farzad Tashtarian, Christian Timmerer, Hermann Hellwagner, Simone Milani Christian Doppler laboratory ATHENA | Alpen-Adria University | Austria daniele.lorenzi@aau.at | https://athena.itec.aau.at/ 1
  • 2. ● Introduction ● Motivation ● Proposed method ● Experimental setup ● Results and analysis ● Conclusion Agenda 2
  • 4. Introduction: HAS Schema 4 Video segmentation Video encoding ... ... ... Server Client Adaptive BitRate (ABR) algorithm Throughput estimation Playout buffer Video decoding ... HTTP GET requests Version 3 Version 2 Version 1 Throughput Time
  • 5. Introduction: HTTP/3 & QUIC 5 Stream Multiplexing 0-RTT Connection Establishment Stream Termination HTTP/3 & QUIC X X
  • 9. DoFP: An Optimization-based ABR algorithm 9 ● Mixed Integer Linear Programming (MILP) model that selects: ○ Bitrate for the next segments; ○ Which segments from the buffer need to be upgraded; ○ Bitrate for these segments. Par. Desc. Set of indexes of k buffered segments + next one Quality level of ith segment Binary variable: 1 → (re-) download ith segment at quality level j; Deadline to (re-) download ith segment Current buffer level (Max.) Buffer size Size of ith segment with quality level 𝑗 (kbits) Assigned throughput to (re-) download ith segment Available throughput between player and server
  • 10. DoFP: An Optimization-based ABR algorithm 10 ● 1st constraint expresses the univocity of the pair (index, quality): Max. quality level
  • 11. DoFP: An Optimization-based ABR algorithm 11 ● Define the deadlines for each segment (where , ): ● 2nd constraint ensure that the download time is lower than the deadline: Not valid for j=qi Seg. length Safety par.
  • 12. DoFP: An Optimization-based ABR algorithm 12 ● 3rd constraint checks the sum of the assigned throughputs to be at most the total available one: No Multiplexing With Multiplexing
  • 13. DoFP: An Optimization-based ABR algorithm 13 ● The MILP model is finally introduced as follows: Objective Function Constraints Variables
  • 15. Experimental setup 15 ● HAS + LSQUIC [1] testbed ● 5-min test sequence (Tears of Steel - begin) ● Bitrate ladder: {107, 240, 346, 715, 1347, 2426, 4121} kbps [2] ● Resolution: {144, 240, 360, 480, 720, 1080, 1440} p [2] ● Codec: H.264 ● Linux tc (bash script) ○ 4G Network trace ○ RTT: 40 ms ● 𝛕 = 4s, Bmax = 20s ● 𝛍 = 0.1, 𝛂 = 0.25, 𝛃 = 0.5, 𝛄 = 0.75 [1] https://github.com/litespeedtech/lsquic [2] T. Karagkioules, et al.: A Public Dataset for YouTube’s Mobile Streaming Client.
  • 17. Results and analysis 17 ● Metrics considered: ○ Average quality: average quality level of the played segments ○ Video instability: average quality fluctuation among adjacent segments ○ Number of switches: number of segments whose quality is lower than their previous one ○ Number of stalls: number of buffer underruns ○ Stall duration: total video freeze time ○ QoE score: computed via ITU-T P.1203 mode 0 and its extension [3] [3] https://github.com/Telecommunication-Telemedia-Assessment/itu-p1203-codecextension
  • 18. Results and analysis 18 ● Results: Comparison among different DoFP versions: ○ DoFP/B: next segment, then retransmitted ones seq. in order as in the buffer ○ DoFP/M: with stream multiplexing feature and concurrent requests ○ DoFP/C: with stream cancellation feature ○ DoFP/MC: with both stream multiplexing and stream cancellation Avg. quality Video inst. N. switches N. stalls Stall dur. (s) QoE DoFP/B 6.12 0.53 8.2 1.8 6.7 3.15 DoFP/M 6.14 0.47 7.8 1.8 6.7 3.25 DoFP/C 6.11 0.48 7.8 0.6 1.7 3.36 DoFP/MC 6.02 0.54 10.6 0.0 0.0 3.38 Multiplexing and cancellation features enhance DoFP results
  • 19. Results and analysis 19 ● Results: Comparison with state-of-the-art approaches ○ SARA → DoFP/MC: highest % of quality 7 seg. (74% → 64%) and avg. quality (6.12 → 6.02) ○ DoFP/MC → others: lowest % of quality 1 seg. (3.2% → > 6.1%) Percentage of quality levels and average quality
  • 20. Results and analysis 20 ● Results: Comparison with state-of-the-art approaches ○ BBA-0: lowest video instability (0.53); DoFP/MC: second lowest (0.54) ○ DoFP/MC: high # of switches (10.6) → upgrade quality, not eliminate gaps Number of switches and video Instability
  • 21. Results and analysis 21 ● Results: Comparison with state-of-the-art approaches ○ DoFP/MC: 0.0 stalls and 0.0s stall duration ○ AGG (0.4 - 1.47s), BOLA (1 - 3.88s) → SARA (2.8 - 9.71s), BBA-0 (4 - 14.41s) Number of stalls and stall duration
  • 22. Results and analysis 22 ● Results: Comparison with state-of-the-art approaches ○ DoFP/MC: best QoE score (3.38) ○ Up to 33.9% increment w.r.t the other approaches QoE scores
  • 24. Conclusions 24 ● DoFP(/MC): a MILP model to provide high QoE (and low stall-probability) through HTTP/3 and QUIC features ● Taking into account throughput, buffer, and quality of each buffered segment ● The model chooses the bitrates for the next segment and (if needed) for the buffered segments to be re-transmitted ● DoFP/MC: outperforms the other approaches with the highest QoE score ● Multiplexing and cancellation features enhance DoFP results ● In the future, investigate the stream priority feature, the impact of DoFP’s parameters and different streaming (video sequence, bitrate ladder, segment duration) and network scenarios (bandwidth traces)