24
Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns Soumya Kanti Datta Research Engineer, EURECOM, France Email: [email protected] 7 th IFIP Wireless and Mobile Networking Conference

Personalized power saving profiles generation analyzing smart device usage patterns

Embed Size (px)

Citation preview

Personalized Power Saving Profiles Generation Analyzing Smart Device Usage Patterns

Soumya Kanti Datta

Research Engineer, EURECOM, France

Email: [email protected]

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