Systems and methods of power management
Inventors
Levchuk, Georgiy • Schurr, Nathan • Hering, Darby E. • Zakin, Mitch
Assignees
Publication Number
US-8909950-B1
Publication Date
2014-12-09
Expiration Date
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
A method for power management comprising inferring a user behavior from an action, inferring a mission state from the action and an event, forecasting a forecasted action from the user behavior and the mission state and outputting an instruction to modify a power resource allocation based on the forecasted action. A processor based assembly for power management of at least one device comprising a means to infer a user behavior from an action, a means to infer a mission state from the action and an event, a means to forecast and a means to plan power management from the inferred information. In some embodiments, the systems and methods apply pattern recognition algorithms and pattern learning algorithms to manage the power allocation to power consuming devices.
Core Innovation
A method for power management comprising inferring a user behavior from an action, inferring a mission state from the action and an event, forecasting a forecasted action from the user behavior and the mission state and outputting an instruction to modify a power resource allocation based on the forecasted action. A processor based assembly for power management of at least one device comprising a means to infer a user behavior from an action, a means to infer a mission state from the action and an event, a means to forecast and a means to plan power management from the inferred information. In some embodiments, the systems and methods apply pattern recognition algorithms and pattern learning algorithms to manage the power allocation to power consuming devices.
The invention addresses the need for advanced energy management caused by a mismatch between handheld power needs and the resources available to meet these needs, where users want more performance but batteries are scarce and battery recharging is an issue. The invention applies pattern recognition algorithms and pattern learning algorithms to forecast user specific resource allocations based on observable data, inferring user behavior and activities such as tasks, and dynamically prioritizes and allocates resources using mission-oriented "power modes" and application "hooks" to manage power across multiple applications and services.
Claims Coverage
Four independent claims were identified and their main inventive features are listed below.
Inferring and forecasting application use to modify power resource allocation
Inferring a user behavior of a user from an action; inferring a mission state of a mission from the action and an event; forecasting a forecasted action from the user behavior and the mission state; outputting an instruction to modify a power resource allocation based on the forecasted action; the action comprises the user selecting an application; the mission comprises a sequence of a plurality of tasks; each task having a task state of complete or not complete; and the forecasting a forecasted action comprises: automatically determining a probability of a future task given the mission and the tasks that have the task state of not complete; automatically determining a future user behavior given the future task; and automatically determining the forecasted action from the future task and the future user behavior.
Hierarchical probabilistic user behavior inference
The action comprises an application use representing the user selecting an application; the inferring a user behavior from an action comprises automatically determining a probability of user behavior according to a hierarchical probabilistic model given the application use, the event and a mission; and the hierarchical probabilistic model configured to determine a P(B|U), a P(U) and a P(A|B,T,E) where P(B|U) is the probability of user behavior given the user, P(U) is a probability of the user and P(A|B,T,E) is a probability of the application use given the user behavior, a task and the event.
Reiteration of mission- and user-based forecasting for power allocation
Inferring a user behavior of a user from an action; inferring a mission state of a mission from the action; forecasting a forecasted action from the user behavior and the mission state; outputting an instruction to modify a power resource allocation based on the forecasted action; the action comprises the user selecting an application; the mission comprises a sequence of a plurality of tasks; each task having a task state of complete or not complete; and the forecasting a forecasted action comprises: automatically determining a probability of a future task given the mission and the tasks that have the task state of not complete; automatically determining a future user behavior given the future task; and automatically determining the forecasted action from the future task and the future user behavior.
Processor based assembly for mission- and user-informed power management
A processor based assembly for power management of a device comprising a means to infer a user behavior of a user from an action; a means to infer a mission state of a mission from the action; a means to forecast a forecasted action from the user behavior and the mission state; a means to output an instruction to modify a power resource allocation based on the forecasted action; the action comprises the user selecting an application; the mission comprises a sequence of a plurality of tasks; each task having a task state of complete or not complete; and the forecasting a forecasted action comprises: automatically determining a probability of a future task given the mission and the tasks that have the task state of not complete; automatically determining a future user behavior given the future task; and automatically determining the forecasted action from the future task and the future user behavior.
The independent claims focus on inferring user behavior and mission state from observed actions and events, forecasting future actions from those inferences, and outputting instructions to modify power resource allocation, with embodiments specifying hierarchical probabilistic models and a processor based assembly to implement these functions.
Stated Advantages
Extension of mission duration by dynamically managing power settings and application priorities to extend battery life.
Simplified logistics and ability to perform longer, more complex missions through improved energy management.
Increased device usability and consumer satisfaction by providing individualized profile of power requirements and run-time suggestions.
Energy savings through coordinated application power modes and management across multiple applications and services, including examples of potential multi-fold savings.
Provision of visual feedback via a dashboard for real-time energy-usage feedback and after-action reviews for training purposes.
Documented Applications
Manage the power consumption of handheld devices.
Manage the power consumption of military equipment.
Manage building power allocation.
Manage electrical grid power allocation.
Allocate other types of resources used in a system or network, including personnel resource allocation.
Allocation of attention such as in a command and control environment.
Allocation of budgets.
Allocation of computing resources.
Use as middleware for processor based systems such as the Android operating system to provide user-individualized power resource management for devices running multiple apps.
Interested in licensing this patent?