SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
Personalized Power Saving Profiles Generation
Analyzing Smart Device Usage Patterns
Soumya Kanti Datta
Research Engineer, EURECOM, France
Email: soumya-kanti.datta@eurecom.fr
7th IFIP Wireless and Mobile Networking Conference
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 2
Introduction
• Power hungry components in smart devices
– Display, network, GPS
• Power consumption depends on individual
usage patterns
• Focus
– Analyse the usage pattern
– Recommend personalized power saving profiles
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 3
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 4
Client-Server Architecture
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 5
Monitoring Module Architecture
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 6
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 7
Usage Patterns
• Characterized by
– Day of the week (d)
– Time interval of a day (t)
– Location (s)
• For each (d, t, s)
– An usage pattern is generated
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 8
Algorithm to Generate Usage Patterns
• For each day of the week of individual users, repeat the following.
1. Count the number of distinct locations that the user is subscribed to from the
collected data.
2. Determine the time interval(s) associated with each distinct location. It is
possible for a location (e.g. home) to be associated with multiple time
intervals at different parts of the day.
3. For each pair of time interval and location, repeat the steps 4-9 which
produces the respective usage pattern.
4. Determine the running applications and their CPU load.
5. Determine the change in battery level and status.
6. Determine the volume level for audio functions.
7. Calculate the amount of network usage, status of Bluetooth, mobile data, Wi-
Fi and GPS (i.e. on/off) and the duration of GPS usage.
8. Read the CPU loads and corresponding operating frequencies.
9. Record the brightness level, screen timeout value and the interaction time
with the device.
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 9
Useful Information Derived
• Patterns corresponding to
– Very high device interaction time
– Higher network usage
– Battery charging
– Intense CPU operations
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 10
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 11
Power Saving Profiles
• Composed of different combination of settings
– Regulate network technologies
– Brightness value
– Limit network usage etc.
• Each pattern has its own power saving profile
• Intelligent activation of the profiles reduce
power consumption
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 12
Algorithm to generate Profiles
• Provide the users with choices to kill the unnecessary and CPU intensive
applications.
• If the pattern registers high device interaction time
– Reduce brightness and screen time out values
• Set a limit for the amount of daily network usage.
• For very less interaction with the device
– Switch off network when the screen is off
– Switched on network when the screen is on.
• During the night when there is no interaction with the devices
– Turn off the wireless network
• If battery is critically low (i.e. below 10%)
– Tone down brightness and timeout to min and turn off network usage.
– In jail broken devices, scale down frequency to minimum and kill CPU intensive apps.
– Turn off any vibration feedback for notification, haptic feedback and audible touch tones and
selections.
• Auto-sync is periodically switched on during the day. The time period can be
configured by user or the app.
• If GPS is on for long, ask the user to switch it off.
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 13
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 14
Use Case - 1
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 15
Use Case - 2
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 16
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 17
Power Consumption Reduction at Display
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 18
Reduction at Network Interfaces
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 19
Evaluation using Smart Devices
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 20
Advantages
• Dynamic computation of power saving profiles
• Detection of change in user behaviour
• Evolution of profiles
• Usage pattern based feedback
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 21
Contents
• Introduction
• Client-server architecture for power saving
• Usage Patterns
• Power Saving Profiles
• Use Cases
• Results
• Conclusion
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 22
Conclusion
• Client-server architecture to reduce power
consumption in smart devices
• Derivation of usage patterns and
corresponding power saving profiles
• Detection of change in usage pattern and
evolution of the pattern
• Power saving up to 87%
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 23
7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 24

Weitere ähnliche Inhalte

Ähnlich wie Personalized power saving profiles generation analyzing smart device usage patterns

Daily monitoring cbm of switchyard equipments through android app
Daily monitoring cbm of switchyard equipments through android appDaily monitoring cbm of switchyard equipments through android app
Daily monitoring cbm of switchyard equipments through android appNiraj Agrawal
 
Self adaptive battery and context aware mobile application development
Self adaptive battery and context aware mobile application developmentSelf adaptive battery and context aware mobile application development
Self adaptive battery and context aware mobile application developmentSoumya Kanti Datta
 
FUNDAMENTALS OF COMPUTER DESIGN
FUNDAMENTALS OF COMPUTER DESIGNFUNDAMENTALS OF COMPUTER DESIGN
FUNDAMENTALS OF COMPUTER DESIGNvenkatraman227
 
Synapseindia mobile apps cellular networks and mobile computing part1
Synapseindia mobile apps cellular networks and mobile computing part1Synapseindia mobile apps cellular networks and mobile computing part1
Synapseindia mobile apps cellular networks and mobile computing part1saritasingh19866
 
The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"
The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"
The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"Satnam Singh
 
How to Lower Android Power Consumption Without Affecting Performance
How to Lower Android Power Consumption Without Affecting PerformanceHow to Lower Android Power Consumption Without Affecting Performance
How to Lower Android Power Consumption Without Affecting Performancerickschwar
 
Android power management, current and future trends
Android power management, current and future trendsAndroid power management, current and future trends
Android power management, current and future trendsSoumya Kanti Datta
 
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...Deepak Shankar
 
Branndon Kelley Keynote on Cybersecurity and the Smart Utility
Branndon Kelley Keynote on Cybersecurity and the Smart Utility Branndon Kelley Keynote on Cybersecurity and the Smart Utility
Branndon Kelley Keynote on Cybersecurity and the Smart Utility EnergyTech2015
 
UCGEC Smart Grid Seminar Ii
UCGEC Smart Grid Seminar IiUCGEC Smart Grid Seminar Ii
UCGEC Smart Grid Seminar IiMartin Kurtovich
 
IRJET- Wifi based Smart Electric Meter using IoT
IRJET-  	  Wifi based Smart Electric Meter using IoTIRJET-  	  Wifi based Smart Electric Meter using IoT
IRJET- Wifi based Smart Electric Meter using IoTIRJET Journal
 
IBM Cloud Côte d'Azur Meetup - 20190328 - Optimisation
IBM Cloud Côte d'Azur Meetup - 20190328 - OptimisationIBM Cloud Côte d'Azur Meetup - 20190328 - Optimisation
IBM Cloud Côte d'Azur Meetup - 20190328 - OptimisationIBM France Lab
 
Predictive Maintenance Systems, Technologies & Equipment Management Softwares...
Predictive Maintenance Systems, Technologies & Equipment Management Softwares...Predictive Maintenance Systems, Technologies & Equipment Management Softwares...
Predictive Maintenance Systems, Technologies & Equipment Management Softwares...proudmehta
 
10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...
10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...
10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...RahulJain989779
 
Neuromophic device for Automotive
Neuromophic device for AutomotiveNeuromophic device for Automotive
Neuromophic device for AutomotiveYoshifumi Sakamoto
 
IoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the CloudIoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the CloudValue Amplify Consulting
 
Living objects network performance_management_v2
Living objects network performance_management_v2Living objects network performance_management_v2
Living objects network performance_management_v2Yoan SMADJA
 

Ähnlich wie Personalized power saving profiles generation analyzing smart device usage patterns (20)

10.5_Concordville Microgrid_PECO_EPRI/SNL Microgrid Symposium
10.5_Concordville Microgrid_PECO_EPRI/SNL Microgrid Symposium10.5_Concordville Microgrid_PECO_EPRI/SNL Microgrid Symposium
10.5_Concordville Microgrid_PECO_EPRI/SNL Microgrid Symposium
 
Daily monitoring cbm of switchyard equipments through android app
Daily monitoring cbm of switchyard equipments through android appDaily monitoring cbm of switchyard equipments through android app
Daily monitoring cbm of switchyard equipments through android app
 
Self adaptive battery and context aware mobile application development
Self adaptive battery and context aware mobile application developmentSelf adaptive battery and context aware mobile application development
Self adaptive battery and context aware mobile application development
 
FUNDAMENTALS OF COMPUTER DESIGN
FUNDAMENTALS OF COMPUTER DESIGNFUNDAMENTALS OF COMPUTER DESIGN
FUNDAMENTALS OF COMPUTER DESIGN
 
Synapseindia mobile apps cellular networks and mobile computing part1
Synapseindia mobile apps cellular networks and mobile computing part1Synapseindia mobile apps cellular networks and mobile computing part1
Synapseindia mobile apps cellular networks and mobile computing part1
 
The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"
The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"
The Fifth Elephant - 2013 Talk - "Smart Analytics in Smartphones"
 
How to Lower Android Power Consumption Without Affecting Performance
How to Lower Android Power Consumption Without Affecting PerformanceHow to Lower Android Power Consumption Without Affecting Performance
How to Lower Android Power Consumption Without Affecting Performance
 
Android power management, current and future trends
Android power management, current and future trendsAndroid power management, current and future trends
Android power management, current and future trends
 
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
Mastering IoT Design: Sense, Process, Connect: Processing: Turning IoT Data i...
 
Smart Grid Deployment Experience and Utility Case Studies
Smart Grid Deployment Experience and Utility Case StudiesSmart Grid Deployment Experience and Utility Case Studies
Smart Grid Deployment Experience and Utility Case Studies
 
Branndon Kelley Keynote on Cybersecurity and the Smart Utility
Branndon Kelley Keynote on Cybersecurity and the Smart Utility Branndon Kelley Keynote on Cybersecurity and the Smart Utility
Branndon Kelley Keynote on Cybersecurity and the Smart Utility
 
UCGEC Smart Grid Seminar Ii
UCGEC Smart Grid Seminar IiUCGEC Smart Grid Seminar Ii
UCGEC Smart Grid Seminar Ii
 
IRJET- Wifi based Smart Electric Meter using IoT
IRJET-  	  Wifi based Smart Electric Meter using IoTIRJET-  	  Wifi based Smart Electric Meter using IoT
IRJET- Wifi based Smart Electric Meter using IoT
 
GREEN_CLOUD_COMPUTING.ppt
GREEN_CLOUD_COMPUTING.pptGREEN_CLOUD_COMPUTING.ppt
GREEN_CLOUD_COMPUTING.ppt
 
IBM Cloud Côte d'Azur Meetup - 20190328 - Optimisation
IBM Cloud Côte d'Azur Meetup - 20190328 - OptimisationIBM Cloud Côte d'Azur Meetup - 20190328 - Optimisation
IBM Cloud Côte d'Azur Meetup - 20190328 - Optimisation
 
Predictive Maintenance Systems, Technologies & Equipment Management Softwares...
Predictive Maintenance Systems, Technologies & Equipment Management Softwares...Predictive Maintenance Systems, Technologies & Equipment Management Softwares...
Predictive Maintenance Systems, Technologies & Equipment Management Softwares...
 
10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...
10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...
10-IoT Data Analytics, Cloud Computing for IoT, Cloud Based platforms, ML for...
 
Neuromophic device for Automotive
Neuromophic device for AutomotiveNeuromophic device for Automotive
Neuromophic device for Automotive
 
IoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the CloudIoT Evolution Expo- Machine Learning and the Cloud
IoT Evolution Expo- Machine Learning and the Cloud
 
Living objects network performance_management_v2
Living objects network performance_management_v2Living objects network performance_management_v2
Living objects network performance_management_v2
 

Mehr von Soumya Kanti Datta

Survey, comparison & evaluation of cross platform mobile application developm...
Survey, comparison & evaluation of cross platform mobile application developm...Survey, comparison & evaluation of cross platform mobile application developm...
Survey, comparison & evaluation of cross platform mobile application developm...Soumya Kanti Datta
 
An IoT gateway centric architecture to provide novel m2m services
An IoT gateway centric architecture to provide novel m2m servicesAn IoT gateway centric architecture to provide novel m2m services
An IoT gateway centric architecture to provide novel m2m servicesSoumya Kanti Datta
 
Smart M2M gateway based architecture for m2m device and endpoint management
Smart M2M gateway based architecture for m2m device and endpoint managementSmart M2M gateway based architecture for m2m device and endpoint management
Smart M2M gateway based architecture for m2m device and endpoint managementSoumya Kanti Datta
 
Usage patterns based security attacks for smart devices
Usage patterns based security attacks for smart devicesUsage patterns based security attacks for smart devices
Usage patterns based security attacks for smart devicesSoumya Kanti Datta
 
M2M communications and internet of things for smart cities
M2M communications and internet of things for smart citiesM2M communications and internet of things for smart cities
M2M communications and internet of things for smart citiesSoumya Kanti Datta
 
A lightweight framework for efficient m2m device management in onem2m archite...
A lightweight framework for efficient m2m device management in onem2m archite...A lightweight framework for efficient m2m device management in onem2m archite...
A lightweight framework for efficient m2m device management in onem2m archite...Soumya Kanti Datta
 

Mehr von Soumya Kanti Datta (8)

WoT framework and use cases
WoT framework and use casesWoT framework and use cases
WoT framework and use cases
 
Survey, comparison & evaluation of cross platform mobile application developm...
Survey, comparison & evaluation of cross platform mobile application developm...Survey, comparison & evaluation of cross platform mobile application developm...
Survey, comparison & evaluation of cross platform mobile application developm...
 
An IoT gateway centric architecture to provide novel m2m services
An IoT gateway centric architecture to provide novel m2m servicesAn IoT gateway centric architecture to provide novel m2m services
An IoT gateway centric architecture to provide novel m2m services
 
Connect and control things
Connect and control thingsConnect and control things
Connect and control things
 
Smart M2M gateway based architecture for m2m device and endpoint management
Smart M2M gateway based architecture for m2m device and endpoint managementSmart M2M gateway based architecture for m2m device and endpoint management
Smart M2M gateway based architecture for m2m device and endpoint management
 
Usage patterns based security attacks for smart devices
Usage patterns based security attacks for smart devicesUsage patterns based security attacks for smart devices
Usage patterns based security attacks for smart devices
 
M2M communications and internet of things for smart cities
M2M communications and internet of things for smart citiesM2M communications and internet of things for smart cities
M2M communications and internet of things for smart cities
 
A lightweight framework for efficient m2m device management in onem2m archite...
A lightweight framework for efficient m2m device management in onem2m archite...A lightweight framework for efficient m2m device management in onem2m archite...
A lightweight framework for efficient m2m device management in onem2m archite...
 

Kürzlich hochgeladen

Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost LoverPowerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost LoverPsychicRuben LoveSpells
 
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,Pooja Nehwal
 
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort ServiceDelhi Call girls
 
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual serviceCALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual serviceanilsa9823
 
9892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x79892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x7Pooja Nehwal
 
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCRFULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCRnishacall1
 
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun serviceCALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun serviceanilsa9823
 

Kürzlich hochgeladen (7)

Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost LoverPowerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
Powerful Love Spells in Arkansas, AR (310) 882-6330 Bring Back Lost Lover
 
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
Call US Pooja 9892124323 ✓Call Girls In Mira Road ( Mumbai ) secure service,
 
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 71 Noida Escorts >༒8448380779 Escort Service
 
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual serviceCALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
CALL ON ➥8923113531 🔝Call Girls Saharaganj Lucknow best sexual service
 
9892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x79892124323 | Book Call Girls in Juhu and escort services 24x7
9892124323 | Book Call Girls in Juhu and escort services 24x7
 
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCRFULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
FULL ENJOY - 9999218229 Call Girls in {Mahipalpur}| Delhi NCR
 
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun serviceCALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
CALL ON ➥8923113531 🔝Call Girls Gomti Nagar Lucknow best Night Fun service
 

Personalized power saving profiles generation analyzing smart device usage patterns

  • 1. Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns Soumya Kanti Datta Research Engineer, EURECOM, France Email: soumya-kanti.datta@eurecom.fr 7th IFIP Wireless and Mobile Networking Conference
  • 2. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 2
  • 3. Introduction • Power hungry components in smart devices – Display, network, GPS • Power consumption depends on individual usage patterns • Focus – Analyse the usage pattern – Recommend personalized power saving profiles 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 3
  • 4. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 4
  • 5. Client-Server Architecture 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 5
  • 6. Monitoring Module Architecture 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 6
  • 7. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 7
  • 8. Usage Patterns • Characterized by – Day of the week (d) – Time interval of a day (t) – Location (s) • For each (d, t, s) – An usage pattern is generated 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 8
  • 9. Algorithm to Generate Usage Patterns • For each day of the week of individual users, repeat the following. 1. Count the number of distinct locations that the user is subscribed to from the collected data. 2. Determine the time interval(s) associated with each distinct location. It is possible for a location (e.g. home) to be associated with multiple time intervals at different parts of the day. 3. For each pair of time interval and location, repeat the steps 4-9 which produces the respective usage pattern. 4. Determine the running applications and their CPU load. 5. Determine the change in battery level and status. 6. Determine the volume level for audio functions. 7. Calculate the amount of network usage, status of Bluetooth, mobile data, Wi- Fi and GPS (i.e. on/off) and the duration of GPS usage. 8. Read the CPU loads and corresponding operating frequencies. 9. Record the brightness level, screen timeout value and the interaction time with the device. 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 9
  • 10. Useful Information Derived • Patterns corresponding to – Very high device interaction time – Higher network usage – Battery charging – Intense CPU operations 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 10
  • 11. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 11
  • 12. Power Saving Profiles • Composed of different combination of settings – Regulate network technologies – Brightness value – Limit network usage etc. • Each pattern has its own power saving profile • Intelligent activation of the profiles reduce power consumption 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 12
  • 13. Algorithm to generate Profiles • Provide the users with choices to kill the unnecessary and CPU intensive applications. • If the pattern registers high device interaction time – Reduce brightness and screen time out values • Set a limit for the amount of daily network usage. • For very less interaction with the device – Switch off network when the screen is off – Switched on network when the screen is on. • During the night when there is no interaction with the devices – Turn off the wireless network • If battery is critically low (i.e. below 10%) – Tone down brightness and timeout to min and turn off network usage. – In jail broken devices, scale down frequency to minimum and kill CPU intensive apps. – Turn off any vibration feedback for notification, haptic feedback and audible touch tones and selections. • Auto-sync is periodically switched on during the day. The time period can be configured by user or the app. • If GPS is on for long, ask the user to switch it off. 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 13
  • 14. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 14
  • 15. Use Case - 1 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 15
  • 16. Use Case - 2 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 16
  • 17. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 17
  • 18. Power Consumption Reduction at Display 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 18
  • 19. Reduction at Network Interfaces 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 19
  • 20. Evaluation using Smart Devices 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 20
  • 21. Advantages • Dynamic computation of power saving profiles • Detection of change in user behaviour • Evolution of profiles • Usage pattern based feedback 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 21
  • 22. Contents • Introduction • Client-server architecture for power saving • Usage Patterns • Power Saving Profiles • Use Cases • Results • Conclusion 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 22
  • 23. Conclusion • Client-server architecture to reduce power consumption in smart devices • Derivation of usage patterns and corresponding power saving profiles • Detection of change in usage pattern and evolution of the pattern • Power saving up to 87% 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 23
  • 24. 7-Apr-15 Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns 24