Predictive control systems and methods

Patent metadata

Field	Value
Publication number	US-2016357232-A1
Application number	US-201514871526-A
Country	US
Kind code	A1
Filing date	Sep 30, 2015
Priority date	Jun 5, 2015
Publication date	Dec 8, 2016
Grant date	—

Abstract

Systems and methods are disclosed for determining a current machine state of a processing device, predicting a future processing task to be performed by the processing device at a future time, and predicting a list of intervening processing tasks to be performed by a first time (e.g. a current time) and the start of the future processing task. The future processing task has an associated initial state. A feed-forward thermal prediction model determines a predicted future machine state at the time for starting the future processing task. Heat mitigation processes can be applied in advance of the starting of the future processing task, to meet the future initial machine state for starting the future processing task.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
determining a future processing task for a processing device, the future processing task having a future start time; predicting a plurality of processing tasks for the processing device between a first time and the future start time, each processing task of the plurality of processing tasks having an associated power requirement to perform the processing task; predicting a future temperature of the processing device, T P , that the processing device will be at the future start time, based upon a current temperature of the processing device and the power requirements to perform one or more of the plurality of processing tasks; and in response to T P being greater than a temperature T I , preparing the processing device so that the temperature of the processing device at the start of the future processing task is less than or equal to the temperature, T I .

2 . The method of claim 1 , wherein predicting the plurality of processing tasks for the processing device between a first time and the future start time comprises analyzing a history of past processing tasks to determine a pattern of user behavior in the past processing tasks.

3 . The method of claim 2 , wherein a pattern of user behavior comprises one or more of: determining an approximate time of day that a user starts a particular task, determining an approximate duration that the user performs the particular task, determining a particular day of the week that the user performs the particular task, or any combination of these.

4 . The method of claim 1 , wherein predicting the plurality of processing tasks comprises analyzing data in a calendar application.

5 . The method of claim 1 , wherein determining a power requirement of a processing task comprises accessing a database of power usage data for processing tasks.

6 . The method of claim 5 , wherein determining the power requirement of the processing task comprises multiplying an incremental power usage for the processing task, retrieved from the database of power usage data, by a predicted duration of the processing task retrieved from a history of past processing tasks.

7 . The method of claim 1 , wherein preparing the processing device comprises one or more of: rescheduling one or more of the plurality of predicted processing tasks to later time, or lowering the scheduling priority of one or more of the plurality of predicted processing tasks.

8 . The method of claim 1 , wherein preparing the processing device comprises one or more of: reducing audio volume, reducing audio resolution, reducing video resolution, or reducing video frame rate.

9 . The method of claim 2 , wherein predicting the plurality of processing tasks for the processing device further comprises correlating a past processing tasks with one or more sensors values of the processing device.

10 . The method of claim 9 , wherein correlating a past processing task with one or more sensor values of the processing comprises correlating the running of a past processing task with one or more of: a location, a time of day, a day of a week, whether the processing device is connected to a network, or a signal strength of a network.

11 . A non-transitory computer-readable medium programmed with executable instructions that, when executed, perform a method comprising the operations:
determining a future processing task for a processing device, the future processing task having a future start time; predicting a plurality of processing tasks for the processing device between a first time and the future start time, each processing task of the plurality of processing tasks having an associated power requirement to perform the processing task; predicting a future temperature of the processing device, T P , that the processing device will be at the future start time, based upon a current temperature of the processing device and the power requirements to perform one or more of the plurality of processing tasks; and in response to T P being greater than a temperature T I , preparing the processing device so that the temperature of the processing device at the start of the future processing task is less than or equal to the temperature, T I .

12 . The medium of claim 11 , wherein predicting the plurality of processing tasks for the processing device between a first time and the future start time comprises analyzing a history of past processing tasks to determine a pattern of user behavior in the past processing tasks.

13 . The medium of claim 12 , wherein a pattern of user behavior comprises one or more of: determining an approximate time of day that a user starts a particular task, determining an approximate duration that the user performs the particular task, determining a particular day of the week that the user performs the particular task, or any combination of these.

14 . The medium of claim 11 , wherein predicting the plurality of processing tasks comprises analyzing data in a calendar application.

15 . The medium of claim 11 , wherein determining a power requirement of a processing task comprises accessing a database of power usage data for processing tasks.

16 . The medium of claim 15 , wherein determining the power requirement of the processing task comprises multiplying an incremental power usage for the processing task, retrieved from the database of power usage data, by a predicted duration of the processing task retrieved from a history of past processing tasks.

17 . The medium of claim 11 , wherein preparing the processing device comprises one or more of: rescheduling one or more of the plurality of predicted processing tasks to later time, or lowering the scheduling priority of one or more of the plurality of predicted processing tasks.

18 . The medium of claim 11 , wherein preparing the processing device comprises one or more of: reducing audio volume, reducing audio resolution, reducing video resolution, or reducing video frame rate.

19 . The medium of claim 12 , wherein predicting the plurality of processing tasks for the processing device further comprises correlating a past processing tasks with one or more sensors values of the processing device.

20 . The medium of claim 19 , wherein correlating a past processing task with one or more sensor values of the processing comprises correlating the running of a past processing task with one or more of: a location, a time of day, a day of a week, whether the processing device is connected to a network, or a signal strength of a network.

21 . A processing device comprising:
one or more processors; a storage comprising a history of past processing tasks and a database of power usage data, coupled to the one or more processors; and a memory coupled to one more processors, the memory programmed with executable instructions that, when executed, perform a method comprising the operations:
determining a future processing task for the processing device, the future processing task having a future start time;
predicting a plurality of processing tasks for the processing device between a first time and the future start time, each processing task of the plurality of processing tasks having an associated power requirement to perform the processing task;
predicting a future temperature of the processing device, T P , that the processing device will be at the future start time, based upon a current temperature of the processing device and the power requirements to perform one or more o

Assignees

• Apple Inc

Inventors

• Kalyanasundaram Nagarajan
• Nigen Jay S
• Ismail James S
• Tan Richard H

Classifications

• G06F1/329

  by task scheduling · CPC title

• G06F1/3296

  by lowering the supply or operating voltage · CPC title

• G06F1/206 Primary

  comprising thermal management · CPC title

• Y02D10/00

  Energy efficient computing, e.g. low power processors, power management or thermal management · CPC title