LwTE-Live: Light-weight Transcoding at the Edge for Live Streaming

Alpen-Adria-Universität
Alpen-Adria-UniversitätAssociate Professor at Alpen-Adria-Universität
All rights reserved. ©2020
1
LwTE-Live: Light-weight Transcoding at the Edge
for Live Streaming
ViSNext’21: 1st ACM CoNEXT Workshop on Design, Deployment,
and Evaluation of Network-assisted Video Streaming)
December 7th 2021
Alireza Erfanian, Hadi Amirpour, Farzad Tashtarian, Christian Timmerer, and Hermann Hellwagner
Christian Doppler laboratory ATHENA | Klagenfurt University | Austria
alireza.erfanian@aau.at | https://athena.itec.aau.at/
All rights reserved. ©2020
● Introduction
● Proposed approach
● Results
● Conclusion and future work
● Q&A
All rights reserved. ©2020
TABLE OF CONTENTS
All rights reserved. ©2020
3
Live video streaming
Live streaming: a specific type of streaming that
media broadcasts in real-time (it can be pre-recorded
or simultaneously recorded) such as:
● News, concerts, sports or awards shows
● Conferences
● Educational events
● Gaming
3/17
Source: http://statista.com/
All rights reserved. ©2020
4
Live streaming: main challenges
1. End-to-end (E2E) latency is a critical QoE
parameter, conflicting with other QoE
parameters such as video quality, low
rebuffering rate, and few quality
switches.
2. Scalability: a huge number of requests
especially for popular events leads to
congestion in the network and undesirable
performance at the origin server.
4/17
Throughput
All rights reserved. ©2020
5
HAS Player
Distribution
Internet
Ingest
CDN Server
CDN Server
CDN Server
Origin Server
ABR
Encoder
Live
Source
HAS Player
HAS Player
Delivery
CDN-enable live streaming workflow
Introduces high
bandwidth utilization in
the network backhaul,
especially between CDN
servers and HAS players
5/17
All rights reserved. ©2020
6
HAS Player
Distribution
Ingest
CDN Server
CDN Server
Origin Server
ABR
Encoder
Live
Source
HAS Player
HAS Player
Edge Server
Edge Server
Edge Server
Delivery
Internet
Edge-enable live streaming workflow
Decrease the backhaul
network utilization
Introduce higher E2E
latency due to requests
aggregation at the edge
6/17
All rights reserved. ©2020
7
HAS Player
Distribution
Ingest
CDN Server
CDN Server
Origin Server
ABR
Encoder
Live
Source
HAS Player
HAS Player Edge Server
Edge Server
Edge Server
Delivery
Internet
Edge-transcoding enable live streaming workflow
7/17
Decrease the backhaul network utilization
Higher E2E latency while transcoding is
the compute-intensive and
time-consuming process
All rights reserved. ©2020
8
LwTE: Light-weight Transcoding at the Edge [1]
● In our previous work [1], we propose a new lightweight transcoding method at the edge named
LwTE that reduces the transcoding time up to 80% compared with the conventional
transcoding method.
● The main idea of LwTE is to extract some features as metadata during the encoding process in
the origin server and reuse them in the transcoding process to reduce the transcoding time
and computational costs.
[1] A. Erfanian, H. Amirpour, F. Tashtarian, C. Timmerer and H. Hellwagner, "LwTE: Light-Weight Transcoding at the Edge," in IEEE Access, vol. 9,
pp. 112276-112289, 2021
8/17
All rights reserved. ©2020
Motivating example
99/17
How to decrease the live streaming cost including the computation
and bandwidth costs while increase scalability by saving network
backhaul bandwidth considering the following constraints:
1. Bandwidth limitation between edge and CDN/origin server
2. Available computation resource at the edge
3. E2E latency
All rights reserved. ©2020
Proposed Mixed-Binary Linear Programming (MBLP) model
1
Bandwidth
cost
Computation
cost
Required computation
resources for
transcoding
Total amount of data
fetched from CDN/origin
server
10/17
Serving policy constraints that
select an optimal policy,
including transcoding at the
edge server or fetching from
the origin/CDN server
● Select a policy for each request
● Selects an instance for request 𝑟 if the
transcoding policy has been chosen for 𝑟
● Guarantees that at least one
representation with higher bitrate than 𝑟
must be downloaded from the
origin/CDN server
All rights reserved. ©2020
Proposed Mixed-Binary Linear Programming (MBLP) model
1
11/17
Serving time constraints that
guarantee to meet the given
deadline for serving all requests
● Determines the total transcoding
time by considering the available
computation resources
● Determines the total fetching time
by taking into account the available
bandwidth between edge and the
origin/CDN server
● Guarantees that total transcoding
time + total fetch time be less than
the given deadline
Computation resource constraints
that determine the required
computation resources for
transcoding operations at the edge
server
● Determines the required computation
resources for transcoding operations at
the edge server
● Guarantees that the largest selected
instance does not exceed the available
computation resources at the edge
server
● Guarantees to provide the required
computation resources during the
transcoding time
All rights reserved. ©2020
1
Performance Evaluation
● Ten minutes live streaming session
● Transcoding is performed on Amazon EC2 instances with various resource profiles
● Default values for segment length = 2 sec, available computation resources = 16 CPU cores,
and bandwidth between edge and origin/CDN server = 100𝑀𝑏𝑝𝑠
● Compare with the following state-of-the-art approaches
○ OSCAR [1]: determines the optimal policy, including fetching and transcoding, from a
higher representation through the conventional transcoding approach, for serving the
incoming request at the edge server.
○ FetchAll: does not perform any transcoding, and the clients’ requested segments are
fetched from the origin/CDN server after aggregation at the edge sever.
[1] A.Erfanian, F.Tashtarian, A.Zabrovskiy, C.Timmerer, and H.Hellwagner. 2021. “OSCAR: On Optimizing Resource Utilization in Live Video
Streaming.” IEEE Transactions on Network and Service Management 18, 1 (2021), 552–569
12/17
All rights reserved. ©2020
1
Evaluation results: LwTE’s performance in terms of (a) Transcoding time saving of the
proposed method (with metadata) compared to the conventional method (without metadata), (b)
relative bitrates of metadata to its corresponding representations
13/17
All rights reserved. ©2020
1
Evaluation results: Performance of the proposed model and compare it with state-of-the-art
approaches’ in terms of (c) bandwidth utilization, (d) normalized cost
14/17
All rights reserved. ©2020
1
Evaluation results: Performance comparison of LwTE-Live with state-of-the-art approaches
in terms of (a) normalized cost, (b) bandwidth utilization, (c) CPU utilization, and (d) number of
transcoded representations for various bandwidth profiles (60, 100, 150, and 200 Mbps)
15/17
All rights reserved. ©2020
1
Evaluation results: Performance comparison of LwTE-Live with state-of-the-art approaches
in terms of (a) normalized cost, (b) bandwidth utilization, (c) CPU utilization, and (d) number of
transcoded representations for various segment lengths (1sec, 2sec, 4sec)
16/17
All rights reserved. ©2020
Conclusion and Future Work
● Investigate the cost efficiency of LwTE for live streaming applications.
● Formulate the problem of minimizing live streaming cost by selecting the
optimal policy, including fetching and transcoding, for serving incoming
requests to the edge server as a MBLP model.
● Compare the proposed method with state-of-the-art approaches in terms of live
streaming cost and backhaul network utilization.
● Show that our proposed method saves the cost and backhaul bandwidth
utilization up to 34% and 45%, respectively.
● Extending LwTE-live to support multiple video channels and relaxing
assumptions is subject to future work direction.
1
17/17
1 of 17

Recommended

LwTE: Light-weight Transcoding at the Edge by
LwTE: Light-weight Transcoding at the EdgeLwTE: Light-weight Transcoding at the Edge
LwTE: Light-weight Transcoding at the EdgeAlpen-Adria-Universität
567 views54 slides
20 Years of Streaming in 20 Minutes by
20 Years of Streaming in 20 Minutes20 Years of Streaming in 20 Minutes
20 Years of Streaming in 20 MinutesAlpen-Adria-Universität
1.9K views25 slides
WISH: User-centric Bitrate Adaptation for HTTP Adaptive Streaming on Mobile D... by
WISH: User-centric Bitrate Adaptation for HTTP Adaptive Streaming on Mobile D...WISH: User-centric Bitrate Adaptation for HTTP Adaptive Streaming on Mobile D...
WISH: User-centric Bitrate Adaptation for HTTP Adaptive Streaming on Mobile D...Minh Nguyen
720 views22 slides
Labmeeting - 20150831 - Overhead and Performance of Low Latency Live Streamin... by
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...Syuan Wang
713 views12 slides
On Optimizing Resource Utilization in AVC-based Real-time Video Streaming by
On Optimizing Resource Utilization in AVC-based Real-time Video StreamingOn Optimizing Resource Utilization in AVC-based Real-time Video Streaming
On Optimizing Resource Utilization in AVC-based Real-time Video StreamingAlpen-Adria-Universität
849 views21 slides
Where to Encode: A Performance Analysis of Intel x86 and Arm-based Amazon EC2... by
Where to Encode: A Performance Analysis of Intel x86 and Arm-based Amazon EC2...Where to Encode: A Performance Analysis of Intel x86 and Arm-based Amazon EC2...
Where to Encode: A Performance Analysis of Intel x86 and Arm-based Amazon EC2...Alpen-Adria-Universität
208 views23 slides

More Related Content

What's hot

Policy-driven Dynamic HTTP Adaptive Streaming Player Environment by
Policy-driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-driven Dynamic HTTP Adaptive Streaming Player EnvironmentMinh Nguyen
32 views20 slides
SLFC: Scalable Light Field Coding by
SLFC: Scalable Light Field CodingSLFC: Scalable Light Field Coding
SLFC: Scalable Light Field CodingAlpen-Adria-Universität
842 views40 slides
Quality Optimization of Live Streaming Services over HTTP with Reinforcement ... by
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 ...Alpen-Adria-Universität
705 views28 slides
MiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming by
MiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive StreamingMiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming
MiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive StreamingAlpen-Adria-Universität
1.1K views25 slides
ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming by
ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video StreamingES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming
ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video StreamingAlpen-Adria-Universität
1.1K views29 slides
EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith... by
EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith...EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith...
EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith...Minh Nguyen
848 views25 slides

What's hot(20)

Policy-driven Dynamic HTTP Adaptive Streaming Player Environment by Minh Nguyen
Policy-driven Dynamic HTTP Adaptive Streaming Player EnvironmentPolicy-driven Dynamic HTTP Adaptive Streaming Player Environment
Policy-driven Dynamic HTTP Adaptive Streaming Player Environment
Minh Nguyen32 views
Quality Optimization of Live Streaming Services over HTTP with Reinforcement ... by Alpen-Adria-Universität
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 ...
MiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming by Alpen-Adria-Universität
MiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive StreamingMiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming
MiPSO: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming
ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming by Alpen-Adria-Universität
ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video StreamingES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming
ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming
EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith... by Minh Nguyen
EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith...EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith...
EPIQ'21: Days of Future Past: An Optimization-based Adaptive Bitrate Algorith...
Minh Nguyen848 views
Machine Learning Based Video Coding Enhancements for HTTP Adaptive Streaming by Alpen-Adria-Universität
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
Docker-Based Evaluation Framework for Video Streaming QoE in Broadband Networks by Alpen-Adria-Universität
 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
ComplexCTTP: Complexity Class Based Transcoding Time Prediction for Video Seq... by Alpen-Adria-Universität
ComplexCTTP: Complexity Class Based Transcoding Time Prediction for Video Seq...ComplexCTTP: Complexity Class Based Transcoding Time Prediction for Video Seq...
ComplexCTTP: Complexity Class Based Transcoding Time Prediction for Video Seq...
H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive... by Alpen-Adria-Universität
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...
CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming by Alpen-Adria-Universität
CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video StreamingCSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming
CSDN: CDN-Aware QoE Optimization in SDN-Assisted HTTP Adaptive Video Streaming
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin... by Alpen-Adria-Universität
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
CAdViSE: Cloud based Adaptive Video Streaming Evaluation Framework for the Au... by Alpen-Adria-Universität
CAdViSE: Cloud based Adaptive Video Streaming Evaluation Framework for the Au...CAdViSE: Cloud based Adaptive Video Streaming Evaluation Framework for the Au...
CAdViSE: Cloud based Adaptive Video Streaming Evaluation Framework for the Au...
Scalable Video Coding Guidelines and Performance Evaluations for Adaptive Me... by mgrafl
Scalable Video Coding Guidelines and Performance Evaluations for Adaptive Me...Scalable Video Coding Guidelines and Performance Evaluations for Adaptive Me...
Scalable Video Coding Guidelines and Performance Evaluations for Adaptive Me...
mgrafl1.8K views
Quality impact of scalable video coding tunneling for media aware content del... by 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...
Scalable High Efficiency Video Coding based HTTP Adaptive Streaming over QUIC... by Alpen-Adria-Universität
Scalable High Efficiency Video Coding based HTTP Adaptive Streaming over QUIC...Scalable High Efficiency Video Coding based HTTP Adaptive Streaming over QUIC...
Scalable High Efficiency Video Coding based HTTP Adaptive Streaming over QUIC...

Similar to LwTE-Live: Light-weight Transcoding at the Edge for Live Streaming

QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming by
QoE- and Energy-aware Content Consumption for HTTP Adaptive StreamingQoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
QoE- and Energy-aware Content Consumption for HTTP Adaptive StreamingDanieleLorenzi6
15 views22 slides
MMSys'21 - Multi-access edge computing for adaptive bitrate video streaming by
MMSys'21 - Multi-access edge computing for adaptive bitrate video streamingMMSys'21 - Multi-access edge computing for adaptive bitrate video streaming
MMSys'21 - Multi-access edge computing for adaptive bitrate video streamingJesus Aguilar
53 views13 slides
IEEE ICC'22_ LEADER_ A Collaborative Edge- and SDN-Assisted Framework for HTT... by
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...Reza Farahani
480 views30 slides
IEEEGlobecom'22-OL-RICHTER.pdf by
IEEEGlobecom'22-OL-RICHTER.pdfIEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdfReza Farahani
13 views28 slides
CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming by
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 StreamingMinh Nguyen
190 views22 slides
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch by
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchDPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchJim St. Leger
6K views35 slides

Similar to LwTE-Live: Light-weight Transcoding at the Edge for Live Streaming(20)

QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming by DanieleLorenzi6
QoE- and Energy-aware Content Consumption for HTTP Adaptive StreamingQoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
QoE- and Energy-aware Content Consumption for HTTP Adaptive Streaming
DanieleLorenzi615 views
MMSys'21 - Multi-access edge computing for adaptive bitrate video streaming by Jesus Aguilar
MMSys'21 - Multi-access edge computing for adaptive bitrate video streamingMMSys'21 - Multi-access edge computing for adaptive bitrate video streaming
MMSys'21 - Multi-access edge computing for adaptive bitrate video streaming
Jesus Aguilar53 views
IEEE ICC'22_ LEADER_ A Collaborative Edge- and SDN-Assisted Framework for HTT... by Reza Farahani
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...
Reza Farahani480 views
IEEEGlobecom'22-OL-RICHTER.pdf by Reza Farahani
IEEEGlobecom'22-OL-RICHTER.pdfIEEEGlobecom'22-OL-RICHTER.pdf
IEEEGlobecom'22-OL-RICHTER.pdf
Reza Farahani13 views
CADLAD: Device-aware Bitrate Ladder Construction for HTTP Adaptive Streaming by Minh Nguyen
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 Nguyen190 views
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch by Jim St. Leger
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitchDPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
DPDK Summit - 08 Sept 2014 - NTT - High Performance vSwitch
Jim St. Leger6K views
How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions by Alpen-Adria-Universität
How to Optimize Dynamic Adaptive Video Streaming? Challenges and SolutionsHow to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
How to Optimize Dynamic Adaptive Video Streaming? Challenges and Solutions
Design and implementation of DADCT by Satish Kumar
Design and implementation of DADCTDesign and implementation of DADCT
Design and implementation of DADCT
Satish Kumar1.2K views
Sync on TAP - Syncing infrastructure with software by ADVA
Sync on TAP - Syncing infrastructure with softwareSync on TAP - Syncing infrastructure with software
Sync on TAP - Syncing infrastructure with software
ADVA85 views
Optimizing User QoE through Overlay Routing, Bandwidth ... by Videoguy
Optimizing User QoE through Overlay Routing, Bandwidth ...Optimizing User QoE through Overlay Routing, Bandwidth ...
Optimizing User QoE through Overlay Routing, Bandwidth ...
Videoguy422 views
ACM NOSSDAV'21-ES-HAS_ An Edge- and SDN-Assisted Framework for HTTP Adaptive ... by Reza Farahani
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 ...
Reza Farahani9 views
Motion Vector Recovery for Real-time H.264 Video Streams by IDES Editor
Motion Vector Recovery for Real-time H.264 Video StreamsMotion Vector Recovery for Real-time H.264 Video Streams
Motion Vector Recovery for Real-time H.264 Video Streams
IDES Editor477 views
Online Video and Next-gen Storage by Jim Kaskade
Online Video and Next-gen StorageOnline Video and Next-gen Storage
Online Video and Next-gen Storage
Jim Kaskade918 views
An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments by Alpen-Adria-Universität
An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular EnvironmentsAn Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments
An Evaluation of Dynamic Adaptive Streaming over HTTP in Vehicular Environments
An Overview on Multimedia Transcoding Techniques on Streaming Digital Contents by idescitation
An Overview on Multimedia Transcoding Techniques on Streaming Digital ContentsAn Overview on Multimedia Transcoding Techniques on Streaming Digital Contents
An Overview on Multimedia Transcoding Techniques on Streaming Digital Contents
idescitation444 views

More from Alpen-Adria-Universität

Evaluation of Quality of Experience of ABR Schemes in Gaming Stream by
Evaluation of Quality of Experience of ABR Schemes in Gaming StreamEvaluation of Quality of Experience of ABR Schemes in Gaming Stream
Evaluation of Quality of Experience of ABR Schemes in Gaming StreamAlpen-Adria-Universität
28 views34 slides
Multi-access Edge Computing for Adaptive Video Streaming by
Multi-access Edge Computing for Adaptive Video StreamingMulti-access Edge Computing for Adaptive Video Streaming
Multi-access Edge Computing for Adaptive Video StreamingAlpen-Adria-Universität
509 views36 slides
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In... by
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...Alpen-Adria-Universität
183 views17 slides
Energy Consumption in Video Streaming: Components, Measurements, and Strategies by
Energy Consumption in Video Streaming: Components, Measurements, and StrategiesEnergy Consumption in Video Streaming: Components, Measurements, and Strategies
Energy Consumption in Video Streaming: Components, Measurements, and StrategiesAlpen-Adria-Universität
658 views32 slides
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ... by
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...Alpen-Adria-Universität
515 views27 slides
Video Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning by
Video Coding Enhancements for HTTP Adaptive Streaming Using Machine LearningVideo Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning
Video Coding Enhancements for HTTP Adaptive Streaming Using Machine LearningAlpen-Adria-Universität
282 views63 slides

More from Alpen-Adria-Universität(20)

VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In... by Alpen-Adria-Universität
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing In...
Energy Consumption in Video Streaming: Components, Measurements, and Strategies by Alpen-Adria-Universität
Energy Consumption in Video Streaming: Components, Measurements, and StrategiesEnergy Consumption in Video Streaming: Components, Measurements, and Strategies
Energy Consumption in Video Streaming: Components, Measurements, and Strategies
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ... by Alpen-Adria-Universität
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Exploring the Energy Consumption of Video Streaming: Components, Challenges, ...
Video Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning by Alpen-Adria-Universität
Video Coding Enhancements for HTTP Adaptive Streaming Using Machine LearningVideo Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning
Video Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications by Alpen-Adria-Universität
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
LLL-CAdViSE: Live Low-Latency Cloud-based Adaptive Video Streaming Evaluation... by Alpen-Adria-Universität
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...
MPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum by Alpen-Adria-Universität
MPEC2: Multilayer and Pipeline Video Encoding on the Computing ContinuumMPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
MPEC2: Multilayer and Pipeline Video Encoding on the Computing Continuum
Collaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming by Alpen-Adria-Universität
Collaborative Edge-Assisted Systems for HTTP Adaptive Video StreamingCollaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
Collaborative Edge-Assisted Systems for HTTP Adaptive Video Streaming
OTEC: An Optimized Transcoding Task Scheduler for Cloud and Fog Environments by Alpen-Adria-Universität
OTEC: An Optimized Transcoding Task Scheduler for Cloud and Fog EnvironmentsOTEC: An Optimized Transcoding Task Scheduler for Cloud and Fog Environments
OTEC: An Optimized Transcoding Task Scheduler for Cloud and Fog Environments
ETPS: Efficient Two-pass Encoding Scheme for Adaptive Live Streaming by Alpen-Adria-Universität
ETPS: Efficient Two-pass Encoding Scheme for Adaptive Live StreamingETPS: Efficient Two-pass Encoding Scheme for Adaptive Live Streaming
ETPS: Efficient Two-pass Encoding Scheme for Adaptive Live Streaming

Recently uploaded

Network Source of Truth and Infrastructure as Code revisited by
Network Source of Truth and Infrastructure as Code revisitedNetwork Source of Truth and Infrastructure as Code revisited
Network Source of Truth and Infrastructure as Code revisitedNetwork Automation Forum
49 views45 slides
Elevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlue by
Elevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlueElevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlue
Elevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlueShapeBlue
149 views7 slides
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... by
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...ShapeBlue
113 views18 slides
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue by
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlueWhat’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlueShapeBlue
191 views23 slides
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online by
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineKVM Security Groups Under the Hood - Wido den Hollander - Your.Online
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineShapeBlue
154 views19 slides
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... by
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...ShapeBlue
86 views25 slides

Recently uploaded(20)

Elevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlue by ShapeBlue
Elevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlueElevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlue
Elevating Privacy and Security in CloudStack - Boris Stoyanov - ShapeBlue
ShapeBlue149 views
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... by ShapeBlue
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
ShapeBlue113 views
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue by ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlueWhat’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
What’s New in CloudStack 4.19 - Abhishek Kumar - ShapeBlue
ShapeBlue191 views
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online by ShapeBlue
KVM Security Groups Under the Hood - Wido den Hollander - Your.OnlineKVM Security Groups Under the Hood - Wido den Hollander - Your.Online
KVM Security Groups Under the Hood - Wido den Hollander - Your.Online
ShapeBlue154 views
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit... by ShapeBlue
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
Transitioning from VMware vCloud to Apache CloudStack: A Path to Profitabilit...
ShapeBlue86 views
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool by ShapeBlue
Extending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPoolExtending KVM Host HA for Non-NFS Storage -  Alex Ivanov - StorPool
Extending KVM Host HA for Non-NFS Storage - Alex Ivanov - StorPool
ShapeBlue56 views
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ... by ShapeBlue
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...
How to Re-use Old Hardware with CloudStack. Saving Money and the Environment ...
ShapeBlue97 views
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f... by TrustArc
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc Webinar - Managing Online Tracking Technology Vendors_ A Checklist f...
TrustArc130 views
Centralized Logging Feature in CloudStack using ELK and Grafana - Kiran Chava... by ShapeBlue
Centralized Logging Feature in CloudStack using ELK and Grafana - Kiran Chava...Centralized Logging Feature in CloudStack using ELK and Grafana - Kiran Chava...
Centralized Logging Feature in CloudStack using ELK and Grafana - Kiran Chava...
ShapeBlue74 views
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P... by ShapeBlue
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
Developments to CloudStack’s SDN ecosystem: Integration with VMWare NSX 4 - P...
ShapeBlue120 views
CloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&T by ShapeBlue
CloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&TCloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&T
CloudStack and GitOps at Enterprise Scale - Alex Dometrius, Rene Glover - AT&T
ShapeBlue81 views
NTGapps NTG LowCode Platform by Mustafa Kuğu
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform
Mustafa Kuğu287 views
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti... by ShapeBlue
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
DRaaS using Snapshot copy and destination selection (DRaaS) - Alexandre Matti...
ShapeBlue69 views
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue by ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlueCloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
CloudStack Managed User Data and Demo - Harikrishna Patnala - ShapeBlue
ShapeBlue68 views
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R... by ShapeBlue
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
ShapeBlue105 views
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue by ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlueMigrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
Migrating VMware Infra to KVM Using CloudStack - Nicolas Vazquez - ShapeBlue
ShapeBlue147 views
Future of AR - Facebook Presentation by Rob McCarty
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
Rob McCarty54 views
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading... by The Digital Insurer
Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...Webinar : Desperately Seeking Transformation - Part 2:  Insights from leading...
Webinar : Desperately Seeking Transformation - Part 2: Insights from leading...

LwTE-Live: Light-weight Transcoding at the Edge for Live Streaming

  • 1. All rights reserved. ©2020 1 LwTE-Live: Light-weight Transcoding at the Edge for Live Streaming ViSNext’21: 1st ACM CoNEXT Workshop on Design, Deployment, and Evaluation of Network-assisted Video Streaming) December 7th 2021 Alireza Erfanian, Hadi Amirpour, Farzad Tashtarian, Christian Timmerer, and Hermann Hellwagner Christian Doppler laboratory ATHENA | Klagenfurt University | Austria alireza.erfanian@aau.at | https://athena.itec.aau.at/
  • 2. All rights reserved. ©2020 ● Introduction ● Proposed approach ● Results ● Conclusion and future work ● Q&A All rights reserved. ©2020 TABLE OF CONTENTS
  • 3. All rights reserved. ©2020 3 Live video streaming Live streaming: a specific type of streaming that media broadcasts in real-time (it can be pre-recorded or simultaneously recorded) such as: ● News, concerts, sports or awards shows ● Conferences ● Educational events ● Gaming 3/17 Source: http://statista.com/
  • 4. All rights reserved. ©2020 4 Live streaming: main challenges 1. End-to-end (E2E) latency is a critical QoE parameter, conflicting with other QoE parameters such as video quality, low rebuffering rate, and few quality switches. 2. Scalability: a huge number of requests especially for popular events leads to congestion in the network and undesirable performance at the origin server. 4/17 Throughput
  • 5. All rights reserved. ©2020 5 HAS Player Distribution Internet Ingest CDN Server CDN Server CDN Server Origin Server ABR Encoder Live Source HAS Player HAS Player Delivery CDN-enable live streaming workflow Introduces high bandwidth utilization in the network backhaul, especially between CDN servers and HAS players 5/17
  • 6. All rights reserved. ©2020 6 HAS Player Distribution Ingest CDN Server CDN Server Origin Server ABR Encoder Live Source HAS Player HAS Player Edge Server Edge Server Edge Server Delivery Internet Edge-enable live streaming workflow Decrease the backhaul network utilization Introduce higher E2E latency due to requests aggregation at the edge 6/17
  • 7. All rights reserved. ©2020 7 HAS Player Distribution Ingest CDN Server CDN Server Origin Server ABR Encoder Live Source HAS Player HAS Player Edge Server Edge Server Edge Server Delivery Internet Edge-transcoding enable live streaming workflow 7/17 Decrease the backhaul network utilization Higher E2E latency while transcoding is the compute-intensive and time-consuming process
  • 8. All rights reserved. ©2020 8 LwTE: Light-weight Transcoding at the Edge [1] ● In our previous work [1], we propose a new lightweight transcoding method at the edge named LwTE that reduces the transcoding time up to 80% compared with the conventional transcoding method. ● The main idea of LwTE is to extract some features as metadata during the encoding process in the origin server and reuse them in the transcoding process to reduce the transcoding time and computational costs. [1] A. Erfanian, H. Amirpour, F. Tashtarian, C. Timmerer and H. Hellwagner, "LwTE: Light-Weight Transcoding at the Edge," in IEEE Access, vol. 9, pp. 112276-112289, 2021 8/17
  • 9. All rights reserved. ©2020 Motivating example 99/17 How to decrease the live streaming cost including the computation and bandwidth costs while increase scalability by saving network backhaul bandwidth considering the following constraints: 1. Bandwidth limitation between edge and CDN/origin server 2. Available computation resource at the edge 3. E2E latency
  • 10. All rights reserved. ©2020 Proposed Mixed-Binary Linear Programming (MBLP) model 1 Bandwidth cost Computation cost Required computation resources for transcoding Total amount of data fetched from CDN/origin server 10/17 Serving policy constraints that select an optimal policy, including transcoding at the edge server or fetching from the origin/CDN server ● Select a policy for each request ● Selects an instance for request 𝑟 if the transcoding policy has been chosen for 𝑟 ● Guarantees that at least one representation with higher bitrate than 𝑟 must be downloaded from the origin/CDN server
  • 11. All rights reserved. ©2020 Proposed Mixed-Binary Linear Programming (MBLP) model 1 11/17 Serving time constraints that guarantee to meet the given deadline for serving all requests ● Determines the total transcoding time by considering the available computation resources ● Determines the total fetching time by taking into account the available bandwidth between edge and the origin/CDN server ● Guarantees that total transcoding time + total fetch time be less than the given deadline Computation resource constraints that determine the required computation resources for transcoding operations at the edge server ● Determines the required computation resources for transcoding operations at the edge server ● Guarantees that the largest selected instance does not exceed the available computation resources at the edge server ● Guarantees to provide the required computation resources during the transcoding time
  • 12. All rights reserved. ©2020 1 Performance Evaluation ● Ten minutes live streaming session ● Transcoding is performed on Amazon EC2 instances with various resource profiles ● Default values for segment length = 2 sec, available computation resources = 16 CPU cores, and bandwidth between edge and origin/CDN server = 100𝑀𝑏𝑝𝑠 ● Compare with the following state-of-the-art approaches ○ OSCAR [1]: determines the optimal policy, including fetching and transcoding, from a higher representation through the conventional transcoding approach, for serving the incoming request at the edge server. ○ FetchAll: does not perform any transcoding, and the clients’ requested segments are fetched from the origin/CDN server after aggregation at the edge sever. [1] A.Erfanian, F.Tashtarian, A.Zabrovskiy, C.Timmerer, and H.Hellwagner. 2021. “OSCAR: On Optimizing Resource Utilization in Live Video Streaming.” IEEE Transactions on Network and Service Management 18, 1 (2021), 552–569 12/17
  • 13. All rights reserved. ©2020 1 Evaluation results: LwTE’s performance in terms of (a) Transcoding time saving of the proposed method (with metadata) compared to the conventional method (without metadata), (b) relative bitrates of metadata to its corresponding representations 13/17
  • 14. All rights reserved. ©2020 1 Evaluation results: Performance of the proposed model and compare it with state-of-the-art approaches’ in terms of (c) bandwidth utilization, (d) normalized cost 14/17
  • 15. All rights reserved. ©2020 1 Evaluation results: Performance comparison of LwTE-Live with state-of-the-art approaches in terms of (a) normalized cost, (b) bandwidth utilization, (c) CPU utilization, and (d) number of transcoded representations for various bandwidth profiles (60, 100, 150, and 200 Mbps) 15/17
  • 16. All rights reserved. ©2020 1 Evaluation results: Performance comparison of LwTE-Live with state-of-the-art approaches in terms of (a) normalized cost, (b) bandwidth utilization, (c) CPU utilization, and (d) number of transcoded representations for various segment lengths (1sec, 2sec, 4sec) 16/17
  • 17. All rights reserved. ©2020 Conclusion and Future Work ● Investigate the cost efficiency of LwTE for live streaming applications. ● Formulate the problem of minimizing live streaming cost by selecting the optimal policy, including fetching and transcoding, for serving incoming requests to the edge server as a MBLP model. ● Compare the proposed method with state-of-the-art approaches in terms of live streaming cost and backhaul network utilization. ● Show that our proposed method saves the cost and backhaul bandwidth utilization up to 34% and 45%, respectively. ● Extending LwTE-live to support multiple video channels and relaxing assumptions is subject to future work direction. 1 17/17