Intelligent and adaptive method to manage mobile device power

1. A system that facilitates power management in mobile devices, comprising:

a power source that provides power to a processor for maintaining communication with a set of peripheral devices; and

a peripheral power management component that tracks usage of at least one of the peripheral devices associated with a set of observed mobile device attributes including a status of at least one application and manages the power expended by the power source based on the tracked usage of the at least one of the peripheral devices by one of: maintaining communication with at least one of the peripheral devices and disabling communication with at least one of the peripheral devices, based on the set of observed mobile device attributes and at least one peripheral device power management schema.

2. The system of claim 1 , wherein the peripheral power management component further sets a state of the peripheral device.

3. The system of claim 1 , the power management schema includes artificial intelligence.

4. The system of claim 3 , the artificial intelligence includes at least one of: a decision tree, a naïve Bayes, a Bayesian network, a neural network, a fuzzy logic model, or a probabilistic classification model providing different patterns of independence.

5. The system of claim 3 , the peripheral power management component generates the decision trees based on a matrix, the matrix including at least one of: a set of observed mobile device attributes, or a set of observed peripheral device states.

6. The system of claim 1 , the peripheral power management component further includes an adaptive component that modifies the power management schemas based on at least one of tracked usage of peripheral devices, predicted usages of the peripheral devices, or observed attribute values associated with peripheral device usage.

7. The system of claim 5 , wherein the peripheral power management component determines usage of the peripheral devices by monitoring one or more attributes of the mobile device and the state of the peripheral devices.

8. The system of claim 1 , the peripheral power management component generates at least one power management schema during a learning phase, wherein the peripheral power management component logs a set of mobile device attributes and peripheral device states, and generates the power management schema based at least in part on the logged attributes and peripheral device states.

9. A method for facilitating power management in mobile devices, comprising:

providing power to a processor for communicating with a set of peripheral devices;

tracking usage of at least one of the peripheral devices associated with a set of observed mobile device attributes including a status of at least one application; and

managing the power based on the tracked usage of the at least one of the peripheral devices by one of: maintaining communication with at least one of the peripheral devices and disabling communication with at least one of the peripheral devices, based at least in part on the set of observed mobile device attributes and at least one peripheral device power management schema.

10. The method of claim 9 , further comprising setting a state of the peripheral device.

11. The method of claim 9 , the power management schema includes machine learning.

12. The method of claim 11 , the machine learning includes at least one of: a decision tree, a naïve Baye, a Bayesian network, a neural network, a fuzzy logic model, or a probabilistic classification model providing different patterns of independence.

13. The method of claim 11 , further comprising generating the decision trees based on a matrix, the matrix includes at least one of the set of observed mobile device attributes, or a set of observed peripheral device states.

14. The method of claim 9 , further comprising adapting the power management schemas based on at least one of: tracked usage of peripheral devices, predicted usage of the peripheral devices, or observed attribute values associated with peripheral device usage.

15. The method of claim 13 , further comprising determining usage of the peripheral devices by monitoring one or more attributes of the mobile device and the state of the peripheral devices.

16. The method of claim 9 , further comprising generating at least one power management schema during a learning phase, including logging a set of mobile device attributes and peripheral device states, and generating the power management schema based at least in part on the logged attributes and peripheral device states.

17. A system for power management in mobile devices, comprising:

means for providing power to a processor for communication with a set of peripheral devices; and

means for tracking usage of at least one of the peripheral devices associated with a set of observed mobile device attributes including a status of at least one application and managing the power expended based on the tracked usage of the at least one of the peripheral devices by one of: maintaining communication with at least one of the peripheral devices and disabling communication with at least one of the peripheral devices, based at least in part on the set of observed mobile device attributes and at least one peripheral device power management schema.

18. The system of claim 17 , further comprising means for at least one of generating, or modifying the schemas based on at least one of a set of observed mobile device attributes, or a set of observed peripheral device states.

19. The system of claim 17 , the power management schema includes at least one artificial intelligence technique.

20. The system of claim 19 , the artificial intelligence techniques include at least one of: a decision tree, a naïve Bayes, a Bayesian network, a neural network, a fuzzy logic model, or a probabilistic classification model providing different patterns of independence.