Method and apparatus for user-activity-based dynamic power management and policy creation for mobile platforms

• US 7,861,099 B2
• Filed: 09/27/2006
• Issued: 12/28/2010
• Est. Priority Date: 06/30/2006
• Status: Expired due to Fees

• Current Assignee: Tahoe Research Limited (f/k/a Learndale Limited) (Vector Capital Corporation)
• Original Assignee: Intel Corporation
• Inventors: Shah, Nilesh N., Schilit, William N., Sengupta, Uttam K., Silvester, Kelan C., Theocharous, Georgios N., Dunstan, Robert A.
• Primary Examiner(s): ELAMIN, ABDELMONIEM I
• Application Number:
  US11/528,967
• Publication Number:
  US 20080005599A1
• Time in Patent Office: 1,553 Days
• Field of Search: 713/300, 713/310, 713320-324, 713/330, 713/340
• US Class Current: 713/300
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/3209 Monitoring remote activity, e.g. over telephone lines or network connections
• CPC Class Codes: G06F 1/324 by lowering clock frequency
• CPC Class Codes: G06F 1/3287 by switching off individual functional units in the computer system
• CPC Class Codes: H04W 52/0258 controlling an operation mode according to history or models of usage information, e.g. activity schedule or time of day
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management
• CPC Class Codes: Y02D 30/70 in wireless communication networks

Abstract

A method and apparatus for user activity-based dynamic power management and policy creation for mobile platforms are described. In one embodiment, the method includes the monitoring of one or more sensor values of a mobile platform device to gather sensor activity data. Once the sensor activity data is gathered, the user state may be predicted according to the gathered user activity and an updated user state model. In one embodiment, the user state model is updated according to the sensor activity data. In one embodiment, a switch occurs from the present power management policy to a new power management policy if the new user state differs from a present user state by a predetermined amount. In one embodiment, at least one time-out parameter of a selected power management policy may be adjusted to comply with a predicted user state. Other embodiments are described and claimed.

Claims

1. A method comprising:

operating a computing device according to a first power management policy;

monitoring one or more sensor values of the computing device;

periodically predicting changing user states based on updates to user state models, wherein a user state model is updated according to gathered user activity data, wherein periodically predicting includes predicting a new user state each time an updated user state model is determined to be different from a previous user state model;

switching from the first power management policy to a second power management policy if the new user state differs from a present user state by a predetermined amount; and

placing at least one system resource in a reduced power state or an increased power state as indicated by the second power management policy.

2. The method of claim 1, wherein disabling the at least one system resource comprises:

disabling a display for operation according to the second power management policy.

3. The method of claim 1, wherein switching the first power management policy further comprises:

throttling a system processor to operate at a reduced frequency.

4. The method of claim 1, wherein monitoring the one or more sensor values further comprises:

monitoring one or more of a user mouse movement, a user keyboard activity, a hard drive activity, a CPU activity, power consumption, time, loaded/running/in-use applications and a device movement to form sensor activity data;

storing the sensor activity data; and

updating a user state model according to the sensor activity data.

5. The method of claim 1, wherein switching from the current power management policy further comprises:

comparing the new user state to the present user state;

selecting the second power management policy if the new user state differs from the present user state by the predetermined amount; and

altering a time-out policy of the first power management state if the new user state differs from the current state by less than the predetermined amount.

6. The method of claim 1, further comprising:

detecting a first sensor value indicating the user activity to enable a disabled resource; and

adjusting a time-out policy of the resource to increase a first value established for a timeout parameter.

7. A system comprising:

a clock to trigger a new user state alarm;

a direct current (DC) power source, wherein the DC power source couples to the clock;

a processor coupled to the DC power source, the processor having at least one power state condition to cause the processor to perform at a selected operating mode; and

a chipset coupled to the processor, the chipset including power management logic configured to predict a new user state in response to the triggered user state alarm by monitoring one or more sensor values, to select a new power management policy if the predicted user state differs from a previous user state, by a predetermined amount and to switch from a current power management policy to the new power management policy, wherein the power management logic is further to periodically predict changing user states based on updates to user state models, wherein a user state model is updated according to the gathered user activity data, wherein the power management logic is further to place at least one system resource in a reduced power state or an increased power state as indicated by the new power management policy.

8. The system of claim 7, wherein the logic further comprises:

policy parameter adjustment logic configured to adjust a time-out parameter of a power management policy if a value of the time-out parameter does not comply with the predicted user state, wherein the policy parameter adjustment logic monitors the power management logic.

9. The system of claim 7, further comprising:

a display, the display to be illuminated in response if required by the new power management policy established by the power management logic.

10. The system of claim 7, wherein the power management logic is further configured to throttle the processor to operate at a reduced frequency from its current frequency according to the new power management policy.

11. The system of claim 7, further comprising:

user state logic coupled to the Direct Current power source, wherein the user state logic to detect a new user state notification according to a timer.

12. A machine-readable storage medium comprising instructions which, when executed, cause a machine to perform the following operations:

operating a computing device according to a first power management policy;

monitoring one or more sensor values of the computing device;

periodically predicting changing user states based on updates to user state models, wherein a user state model is updated according to gathered user activity data, wherein periodically predicting includes predicting a new user state each time an updated user state model is determined to be different from a previous user state model;

switching from the first power management policy to a second power management policy if the new user state differs from a present user state by a predetermined amount; and

placing at least one system resource in a reduced power state or an increased power state as indicated by the second power management policy.

13. The machine-readable storage medium of claim 12, wherein disabling the at least one system resource comprises:

disabling a display for operation according to the second power management policy.

14. The machine-readable storage medium of claim 12, wherein switching the first power management policy further comprises:

throttling a system processor to operate at a reduced frequency.

15. The machine-readable storage medium of claim 12, wherein monitoring the one or more sensor values further comprises:

monitoring one or more of a user mouse movement, a user keyboard activity, a hard drive activity, a CPU activity, power consumption, time, loaded/running/in-use applications and a device movement to form sensor activity data;

storing the sensor activity data; and

updating a user state model according to the sensor activity data.