Transcript
International Symposium on Low Power Electronics and Design
A Cloud-Based Energy-Saving Service for Mobile Streaming Applications
Cheng-Kang Hsieh, Chun-Han Lin, Pi-Cheng Hsiu
Research Center for Information Technology Innovation Academia Sinica, Taiwan
• Introduction
• A Dynamic Backlight Scaling Service
• Real-World Case Studies
• Conclusion
2
Outline
• Mobile applications and services are having a profound effect on people's lifestyles.
• The energy consumption of mobile devices is a major challenge in sustaining the applications and services.
3
Motivation
• The concept would be realized as a value-added service offered by ISPs, like AT&T.
• AT&T helps mobile devices to save energy when they access Internet applications.
• The services must be easy to use & transparent to the users.
4
Cloud-based Energy-Saving Services
• The screen backlight consumes most of the energy for mobile streaming applications.
• Dynamic backlight scaling is deemed a promising technical solution.
• When to dim the backlight to which level? Our ISPLED’11 paper has the answer!
5
Power Consumption when
browsing YouTube on iPad
CPU, 17.21%
WIFI, 4.32%
Backlight, 60.49%
LCD Screen, 17.98%
Dynamic Backlight Scaling
A Dynamic Backlight Scaling Service
6
System Architecture
Video Stream
Backlight File Backlight Server
Streaming Server
Mobile Device
• Responsible for generating backlight files
7
The Cloud Side
Phase 1 • Analyze the video to decide the critical backlight
levels (i.e., the dimmest backlight level with respect to the tolerable video distortion)
Phase 2 • Determine an optimal backlight assignment for the
video based on the device’s power model and capability
Backlight File
Download the requested video from YouTube
Critical backlight levels of the video
8
The Device Side
• Measure power models • Develop mobile application programs
iPad’s display subsystem Power Monitors
9
System Deployment
• The dynamic backlight scaling service has been deployed on Chunghwa Telecom’s hicloud.
• The mobile application program for Android is going to be released in the Android Market for free.
Backlight File
• Process Time & Transmission Delay
• Video Perceptual Quality (Demo)
10
Approach Validation
Video Download Phase I Phase II
124 seconds 1020 seconds 2.1 seconds
Transmission Delay
335 milliseconds
Cloud Side
Device Side
11
Performance Evaluation
Experimental Results Case Studies
12
Conclusion
• We raise the concept of cloud-based energy-saving services. – The dynamic backlight scaling service has been deployed on
CHT hicloud as a prototype service. – Two mobile application programs were developed for Google’s
Android and Apple’s iOS. – With the service applied, HTC Desire and Apple iPad achieved
energy savings of 11-20% and 31-41% when browsing videos on YouTube.
• We will release the mobile application programs to
seek the feedback on the performance and identify the issues that require further investigation.
13
We are the Research Center for IT Innovation
top related