Exploring the Energy Consumption of Video
Streaming: Components, Challenges,
and Opportunities
Samira Afzal
Institute of Information Technology (ITEC), Alpen-Adria-Universität Austria
samira.afzal@aau.at | https://athena.itec.aau.at/
1
Agenda
GAIA project
Carbon estimation considerations
Components of energy consumption
Challenges & opportunities
Publications
Remarks
Video streaming accounts for 67.60%
current network traffic
3
Motivation
https://www.bbc.com/future/article/20200305-why-your-internet-habits-are-not-as-clean-as-you-think
1
2
2
https://www.sandvine.com/hubfs/Sandvine_Redesign_2019/Downloads/2023/reports/Sandvine%20GIPR%202023.pdf
Urgent action is needed against climate change and global greenhouse gas
(GHG) emissions
The carbon footprint of Internet data traffic accounts for about 3.7% of
GHG
1
4
GAIA (the Greek goddess of Earth, mother of all life, personification of the
Earth)
Funded by the Austrian Research Promotion Agency FFG (Basisprogramm)
A cooperative project between Bitmovin and Alpen-Adria-Universität
Klagenfurt (AAU)
GAIA: Intelligent Climate-Friendly Video
Platform
5
GAIA Project Leaders
6
Complete energy awareness and accountability, including energy
consumption and GHG emissions along the entire delivery chain, from
content creation and server-side encoding to video transmission and
client-side rendering
Reduced energy consumption and GHG emissions through advanced
analytics and optimizations on all phases of the video delivery chain
GAIA: Intelligent Climate-Friendly Video
Platform
Carbon
Estimation
Considerations
Carbon Estimation Considerations
Energy sources
Imported electricity
The role of timely electricity usage
8
Components
of Energy
Consumption
10
Components of Energy Consumption in
Video Streaming
Encoding
Storage
Core network
Access networks
Edge components
NIC
Decode
Display
Samira Afzal, Radu Prodan, and Christian Timmerer, Green Video Streaming: Challenges and Opportunities,
ACM SIGMM Records (2023)
https://athena.itec.aau.at/2023/04/ve-match-video-encoding-matching-based-model-for-cloud-and-edge-
computing-instances/
Opportunities
Challenges &
12
Energy Consumption in Video Encoding
Energy-efficient codecs
Maximizing efficiency through
parameter optimization
Efficient transcoding techniques
Compression algorithm complexity
13
Energy Consumption in Datacenters
On-demand segment encoding
Optimizing video bitrate ladder
Eliminating perceptually redundant
representations
Per-title optimizing bitrate ladders
Encoding and storing segments in ABR
14
Energy Consumption in Datacenters
Energy-efficient video encoding task
scheduler on the computing continuum
Suitable cloud services
Low-carbon cloud regions
Energy-based pricing options for cloud
computing platform providers
Power overhead in Cloud
instances
15
Networks
Exploring end-users' perception of quality
to reduce video streaming bitrates and
energy consumption
Automatic energy-efficient path selection
for video streaming
16
Hybrid CDNs
Multi-CDN
Maximizing CDN efficiency
Hit-ratio metric is not enough
On-demand segment caching
CDN
17
Choosing energy-efficient NICs and
optimizing network settings
Use of more energy-efficient devices
Improving screen display technologies
Optimize video decoding algorithms
Optimizing video playback
Raising awareness of the environmental
impact of video streaming among users
End-User Devices
18
Choosing energy-efficient NICs and
optimizing network settings
Use of more energy-efficient devices
Improving screen display technologies
Optimize video decoding algorithms
Optimizing video playback
Raising awareness of the environmental
impact of video streaming among users
End-User Devices
Subjective study on QoE ratings
QoE model of the high-quality user and the
green user [1]
[1] T. Hossfeld, M. Varela, L. Skorin-Kapov, P. E. Heegaard, A greener experience: Trade-offs between qoe and co2 emissions in today’s and 6g
networks, IEEE Communications Magazine (2023)
19
Optimizing energy consumption in interconnected video streaming
components
Tracked metrics for energy logging
End-to-end Perspective
Publications
Green Video Streaming:
Challenges and Opportunities
Samira Afzal, Radu Prodan, and Christian Timmerer, Green Video Streaming: Challenges and Opportunities,
ACM SIGMM Records (2023)
https://athena.itec.aau.at/2023/04/ve-match-video-encoding-matching-based-model-for-cloud-and-edge-
computing-instances/
21
22
VE-Match: Video Encoding
Matching-based Model for
Cloud and Edge Computing
Instances
Samira Afzal, Narges Mehran, Sandro Linder, Christian Timmerer, and Radu Prodan, VE-Match: Video
Encoding Matching-based Model for Cloud and Edge Computing Instances, ACM MMsys, GMSys workshop
(2023)
https://athena.itec.aau.at/2023/04/ve-match-video-encoding-matching-based-model-for-cloud-and-edge-
computing-instances/
23
ECO Player
Optimizing Video Streaming for
Sustainability and Quality: The Role of
Preset Selection in Per-Title Encoding
24
Hadi Amirpour, Vignesh V Menon, Samira Afzal, Radu Prodan, Christian Timmerer, Optimizing Video
Streaming for Sustainability and Quality: The Role of Preset Selection in Per-Title Encoding, IEEE ICME (2023)
https://athena.itec.aau.at/2023/05/3483/
Remarks
25
Challenges and opportunities to reduce video streaming energy consumption
Several key aspects should be highlighted when designing an energy-efficient
video streaming approach
Considering crucial components for accurately assessing energy usage
A holistic system design approach
Raising awareness of the environmental impact of video streaming among
users
publications
Green Video Streaming: Challenges and Opportunities
Video encoding matching-based model for Cloud and Edge computing
Instances
Eco player
The Role of preset selection in per-title encoding
Thank you
Have a
great day
ahead!
Institute of Information Technology (ITEC) Alpen-Adria-Universität Austria
samira.afzal@aau.at https://itec.aau.at/

Exploring the Energy Consumption of Video Streaming: Components, Challenges, and Opportunities

  • 1.
    Exploring the EnergyConsumption of Video Streaming: Components, Challenges, and Opportunities Samira Afzal Institute of Information Technology (ITEC), Alpen-Adria-Universität Austria samira.afzal@aau.at | https://athena.itec.aau.at/
  • 2.
    1 Agenda GAIA project Carbon estimationconsiderations Components of energy consumption Challenges & opportunities Publications Remarks
  • 4.
    Video streaming accountsfor 67.60% current network traffic 3 Motivation https://www.bbc.com/future/article/20200305-why-your-internet-habits-are-not-as-clean-as-you-think 1 2 2 https://www.sandvine.com/hubfs/Sandvine_Redesign_2019/Downloads/2023/reports/Sandvine%20GIPR%202023.pdf Urgent action is needed against climate change and global greenhouse gas (GHG) emissions The carbon footprint of Internet data traffic accounts for about 3.7% of GHG 1
  • 5.
    4 GAIA (the Greekgoddess of Earth, mother of all life, personification of the Earth) Funded by the Austrian Research Promotion Agency FFG (Basisprogramm) A cooperative project between Bitmovin and Alpen-Adria-Universität Klagenfurt (AAU) GAIA: Intelligent Climate-Friendly Video Platform
  • 6.
  • 7.
    6 Complete energy awarenessand accountability, including energy consumption and GHG emissions along the entire delivery chain, from content creation and server-side encoding to video transmission and client-side rendering Reduced energy consumption and GHG emissions through advanced analytics and optimizations on all phases of the video delivery chain GAIA: Intelligent Climate-Friendly Video Platform
  • 8.
  • 9.
    Carbon Estimation Considerations Energysources Imported electricity The role of timely electricity usage 8
  • 10.
  • 11.
    10 Components of EnergyConsumption in Video Streaming Encoding Storage Core network Access networks Edge components NIC Decode Display Samira Afzal, Radu Prodan, and Christian Timmerer, Green Video Streaming: Challenges and Opportunities, ACM SIGMM Records (2023) https://athena.itec.aau.at/2023/04/ve-match-video-encoding-matching-based-model-for-cloud-and-edge- computing-instances/
  • 12.
  • 13.
    12 Energy Consumption inVideo Encoding Energy-efficient codecs Maximizing efficiency through parameter optimization Efficient transcoding techniques Compression algorithm complexity
  • 14.
    13 Energy Consumption inDatacenters On-demand segment encoding Optimizing video bitrate ladder Eliminating perceptually redundant representations Per-title optimizing bitrate ladders Encoding and storing segments in ABR
  • 15.
    14 Energy Consumption inDatacenters Energy-efficient video encoding task scheduler on the computing continuum Suitable cloud services Low-carbon cloud regions Energy-based pricing options for cloud computing platform providers Power overhead in Cloud instances
  • 16.
    15 Networks Exploring end-users' perceptionof quality to reduce video streaming bitrates and energy consumption Automatic energy-efficient path selection for video streaming
  • 17.
    16 Hybrid CDNs Multi-CDN Maximizing CDNefficiency Hit-ratio metric is not enough On-demand segment caching CDN
  • 18.
    17 Choosing energy-efficient NICsand optimizing network settings Use of more energy-efficient devices Improving screen display technologies Optimize video decoding algorithms Optimizing video playback Raising awareness of the environmental impact of video streaming among users End-User Devices
  • 19.
    18 Choosing energy-efficient NICsand optimizing network settings Use of more energy-efficient devices Improving screen display technologies Optimize video decoding algorithms Optimizing video playback Raising awareness of the environmental impact of video streaming among users End-User Devices Subjective study on QoE ratings QoE model of the high-quality user and the green user [1] [1] T. Hossfeld, M. Varela, L. Skorin-Kapov, P. E. Heegaard, A greener experience: Trade-offs between qoe and co2 emissions in today’s and 6g networks, IEEE Communications Magazine (2023)
  • 20.
    19 Optimizing energy consumptionin interconnected video streaming components Tracked metrics for energy logging End-to-end Perspective
  • 21.
  • 22.
    Green Video Streaming: Challengesand Opportunities Samira Afzal, Radu Prodan, and Christian Timmerer, Green Video Streaming: Challenges and Opportunities, ACM SIGMM Records (2023) https://athena.itec.aau.at/2023/04/ve-match-video-encoding-matching-based-model-for-cloud-and-edge- computing-instances/ 21
  • 23.
    22 VE-Match: Video Encoding Matching-basedModel for Cloud and Edge Computing Instances Samira Afzal, Narges Mehran, Sandro Linder, Christian Timmerer, and Radu Prodan, VE-Match: Video Encoding Matching-based Model for Cloud and Edge Computing Instances, ACM MMsys, GMSys workshop (2023) https://athena.itec.aau.at/2023/04/ve-match-video-encoding-matching-based-model-for-cloud-and-edge- computing-instances/
  • 24.
  • 25.
    Optimizing Video Streamingfor Sustainability and Quality: The Role of Preset Selection in Per-Title Encoding 24 Hadi Amirpour, Vignesh V Menon, Samira Afzal, Radu Prodan, Christian Timmerer, Optimizing Video Streaming for Sustainability and Quality: The Role of Preset Selection in Per-Title Encoding, IEEE ICME (2023) https://athena.itec.aau.at/2023/05/3483/
  • 26.
    Remarks 25 Challenges and opportunitiesto reduce video streaming energy consumption Several key aspects should be highlighted when designing an energy-efficient video streaming approach Considering crucial components for accurately assessing energy usage A holistic system design approach Raising awareness of the environmental impact of video streaming among users publications Green Video Streaming: Challenges and Opportunities Video encoding matching-based model for Cloud and Edge computing Instances Eco player The Role of preset selection in per-title encoding
  • 27.
    Thank you Have a greatday ahead! Institute of Information Technology (ITEC) Alpen-Adria-Universität Austria samira.afzal@aau.at https://itec.aau.at/