Systems and methods of power management
Inventors
Levchuk, Georgiy • Schurr, Nathan • Hering, Darby • Zakin, Mitch
Assignees
Publication Number
US-10803405-B1
Publication Date
2020-10-13
Expiration Date
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
Methods for power management are disclosed comprising a process of predefining one or more power mode for a user application, providing a processor based device and user interface configured to operate with the device to support the user with tasks using the user application, the user application communicating an intent message to a transformative power management (TPM) application and the TPM configured to define and output a power mode instruction for the application given the intention and the predefined power modes. In some embodiments, the methods are implemented on a processor based device. 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
Methods for power management are disclosed comprising a process of predefining one or more power mode for a user application, providing a processor based device and user interface configured to operate with the device to support the user with tasks using the user application, the user application communicating an intent message to a transformative power management (TPM) application and the TPM configured to define and output a power mode instruction for the application given the intention and the predefined power modes. In some embodiments, the methods are implemented on a processor based device. 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 background describes a need for advanced energy management because users want more performance and more sophisticated tools while batteries are scarce and battery recharging has become an issue as locations become distributed broadly. The current state of power management for handhelds relies on users to proactively remember and apply power management options and efficient behaviors as their mobile device usage changes over the course of each day, creating a mismatch between handheld power needs and the resources available to meet these needs. For critical situations, the optimal solution is power management that works with the user, customized to the individual user and acts autonomously, and transparently when required, and interactively when desired.
To address this need, the Transformative Power Management (TPM) system applies pattern recognition algorithms and/or pattern learning algorithms to forecast user specific resource allocations based on observable data by inferring user behavior and activities such as tasks, inferring a mission state from events and actions, 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. TPM uses the concept of predefined application power modes provided by applications and generates power mode instructions to applications or users, and may operate autonomously or interactively, provide a dashboard for energy-usage feedback, and permit app developers to create hooks to specify app power modes.
Claims Coverage
This section identifies four independent claims and extracts their main inventive features.
processor based system with transformative power management application
A processor based system comprising a processor based device with non-transitory memory, a user interface, and a processor; a user application stored in memory comprising one or more predefined power modes and program instructions to support at least one task; and a TPM application stored in memory comprising program instructions to receive an intent message from the user application, infer a user behavior from the action with a pattern recognition algorithm where the action comprises at least first and second actions and the pattern recognition algorithm comprises first and second sets of pattern recognition algorithm parameters with the second set updated according to a pattern learning algorithm, determine a selected power mode given the user behavior and the predefined power modes, and output an instruction for the device to use the selected power mode as a power resource allocation for the user application, with the processor executing both applications.
method for power management using intent messages and pattern learning
A method comprising predefining one or more predefined power modes for an application; providing a user interface; receiving an intent message from the application comprising an action of a user; inferring a user behavior from the action by automatically determining a probability of the user behavior from the action with a pattern recognition algorithm where the action comprises at least first and second actions, the pattern recognition algorithm comprises first and second sets of parameters, and the method updates the second set according to a pattern learning algorithm; defining a selected power mode from the predefined power modes given the user behavior; and outputting an instruction to modify a power resource allocation by modifying the predefined power mode to the selected power mode.
processor based system for controlling power management with stored instructions
A processor based system comprising a processor, a user interface, and a non-transient computer-readable storage device with program instructions that when executed predefine one or more predefined power modes for an application, provide a user interface, receive an intent message from the application comprising an action of a user, infer a user behavior from the action with a pattern recognition algorithm where the action comprises at least first and second actions and the pattern recognition algorithm comprises first and second parameter sets with the second set updated via a pattern learning algorithm, define a selected power mode given the intent and predefined power modes, and output an instruction to modify a power resource allocation by modifying the predefined power mode to the selected power mode.
method defining selected power mode then inferring user behavior
A method comprising predefining one or more predefined power modes for an application, providing a user interface, receiving an intent message, defining a selected power mode from the predefined power modes given the intent, outputting an instruction to modify a power resource allocation by modifying the predefined power mode to the selected power mode, and inferring a user behavior from an action of a user with the application by automatically determining a probability of the user behavior from the action with a pattern recognition algorithm where the action comprises at least first and second actions, the pattern recognition algorithm comprises first and second parameter sets, and updating the second set according to a pattern learning algorithm.
The independent claims consistently cover systems and methods in which a TPM application or program instructions receive intent messages from applications, use pattern recognition algorithms with distinct parameter sets and pattern learning updates to infer user behavior, and select and output predefined application power modes to modify device power resource allocations.
Stated Advantages
Apply pattern recognition and pattern learning algorithms to enhance the management of resources.
Provide individualized power resource management that can extend mission duration.
Enable dynamic prioritization and allocation of resources for optimal power use based on current mission status, user, and remaining power.
Allow autonomous to manual user-selectable control and the ability to be turned off completely for mission-critical apps.
Coordinate application power modes to reduce unsynchronized update power spikes and enable potential 2-to-10× savings during active data transfer with an indicated average power savings example of 50% when using TPM.
Seamless integration with applications via hooks to maximize the number of apps managed and improve efficiency of power usage.
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 such as personnel resource allocation.
Allocation of attention such as in a command and control environment.
Allocation of budgets.
Allocation of computing resources.
Middleware service for devices running multiple apps, exemplified by Android OS compatibility for mobile handheld devices.
Support mission tasks such as security, patrol, reconnaissance, fire suppression, and medical evacuation operations and task examples like report generation and media transfer.
Interested in licensing this patent?