Wearable device-aware supervised power management for mobile platforms

Patent metadata

Field	Value
Publication number	US-10915156-B2
Application number	US-201816211888-A
Country	US
Kind code	B2
Filing date	Dec 6, 2018
Priority date	Jan 29, 2013
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

Methods, systems, and computer program products are provided for supervised power management between a primary platform and a secondary platform. Communication between a primary platform and a secondary platform is established. An application running on the secondary platform is captured. Input features and output measures are collected to build a training set for the application, wherein the input features are collected through direct measurement and the output measures reflect characteristics of the application. Based on the training set, power consumption of the secondary platform with an expected performance level is predicted for a new application running on the secondary platform. Accordingly, an optimal power management policy is derived that minimizes the total power consumption of the primary and secondary platforms.

First claim

What is claimed is:

1. A power management system on a first platform, comprising:
a memory that stores instructions; and
a processor configured to execute the instructions, the instructions, when executed by the processor, configuring the processor to:
capture a first application running on a second platform communicatively coupled to the first platform,
collect an input feature of the first application and an output measure of the first application reflecting a characteristic of the first application as a training set for the first application, wherein the input feature and the output measure are categorized into a low, medium or high category,
predict power consumption of the second platform with an expected performance level for a second application running on the second platform based on a combination of the category for the input feature and the category for the output measure collected as the training set for the first application, and
adjust a power management policy that reduces the power consumption of the second platform based on the predicted power consumption for the second application running on the second platform.

2. The power management system of claim 1 , wherein the second platform comprises:
a wearable device.

3. The power management system of claim 1 , wherein the first application comprises:
a video playback application;
a voice activation application; or
a web browser application.

4. The power management system of claim 1 , wherein the input feature of the first application comprises:
a utilization rate of the second platform representing a ratio of an active period and a total period, the total period being a combination of the active period and an idle period; and
wherein the output measure of the first application comprises:
a workload of the first application running on the second platform;
the power consumption of the second platform; or
a data rate of the second platform.

5. The power management system of claim 1 , wherein the training set comprises:
a utilization rate of the second platform;
a frame frequency of the second platform;
a power consumption of the second platform; or
a data rate of the second platform.

6. The power management system of claim 1 , wherein the instructions, when executed by the processor, further configure the processor to:
categorize the input feature of the first application into an input feature category from among the low, medium, or high category;
collect an output feature category from among the low, medium, or high category corresponding to the input feature category as the output measure of the first application; and
predict the power consumption of the second platform with an expected performance level for the second application running on the second platform based on the categorized input feature and output measure.

7. The power management system of claim 1 , wherein the instructions, when executed by the processor, configure the processor to:
adjust the power management policy with a clock frequency of the second platform that reduces the power consumption of the second platform.

8. A method for power management, comprising:
capturing, by a processor operating on a first platform, a first application running on a second platform communicatively coupled to the first platform,
collecting an input feature of the first application and an output measure of the first application reflecting a characteristic of the first application as a training set for the first application, wherein the input feature and the output feature measure are categorized into a low, medium or high category,
predicting power consumption of the second platform with an expected performance level for a second application running on the second platform based on a combination of the category for the input feature and the category for the output measure collected as the training set for the first application, and
adjusting a power management policy that reduces the power consumption of the second platform based on the predicted power consumption for the second application running on the second platform.

9. The method of claim 8 , wherein the second platform comprises:
a wearable device.

10. The method of claim 8 , wherein the first application comprises:
a video playback application;
a voice activation application; or
a web browser application.

11. The method of claim 8 , wherein the input feature of the first application comprises:
a utilization rate of the second platform representing a ratio of an active period and a total period, the total period being a combination of the active period and an idle period; and
wherein the output measure of the first application comprises:
a workload of the first application running on the second platform;
the power consumption of the second platform; or
a data rate of the second platform.

12. The method of claim 8 , wherein the training set comprises:
a utilization rate of the second platform;
a frame frequency of the second platform;
a power consumption of the second platform; or
a data rate of the second platform.

13. The method of claim 8 , further comprising:
categorizing the input feature of the first application into an input feature category from among the low, medium, or high category; and
collecting an output feature category from among the low, medium, or high category corresponding to the input feature category as the output measure of the first application; and
predicting the power consumption of the second platform with an expected performance level for the second application running on the second platform based on the categorized input feature and output measure.

14. The method of claim 8 , wherein the adjusting comprises:
adjusting the power management policy with a clock frequency of the second platform that reduces the power consumption of the second platform.

15. A power management system on a first platform, comprising:
a memory that stores instructions; and
a processor configured to execute the instructions, the instructions, when executed by the processor, configuring the processor to:
capture a first application running on a second platform that is communicatively coupled to the first platform,
categorize an input feature of the first application into an input feature category from among a plurality of input feature categories,
collect an output feature category from among a plurality of output feature categories corresponding to the input feature category as an output measure of the first application, wherein the input feature and the output measure are categorized into a low, medium, or high category,
predict power consumption of the second platform with an expected performance level for a second application running on the second platform based on a combination of the category for the input feature and the category for the output measure collected for the first application, and
adjust a power management policy that reduces the power consumption of the second platform based on the predicted power consumption for the second application running on the second platform.

16. The power management system of claim 15 , wherein the second platform comprises:
a wearable device.

17. The power management system of claim 15 , wherein the first application comprises:
a video playback application;
a voice activation application; or
a web browser application.

18. The power management system of claim 15 , wherein the input feature of the first application comprises:
a utilization rate o

Assignees

• Avago Tech Int Sales Pte Lid

Inventors

• Jung Hwisung

Classifications

• G06F1/3228

  Monitoring task completion, e.g. by use of idle timers, stop commands or wait commands · CPC title

• G06F1/3234 Primary

  Power saving characterised by the action undertaken · CPC title

• G06F9/4893

  taking into account power or heat criteria (power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206) · CPC title

• Y02D30/70

  in wireless communication networks · CPC title

• H04W52/223

  predicting future states of the transmission · CPC title