Localized weather prediction through utilization of cameras

Patent metadata

Field	Value
Publication number	US-10126771-B2
Application number	US-201514727746-A
Country	US
Kind code	B2
Filing date	Jun 1, 2015
Priority date	Dec 17, 2010
Publication date	Nov 13, 2018
Grant date	Nov 13, 2018

Abstract

Described herein are various technologies pertaining to predicting an amount of electrical power that is to be generated by a power system at a future point in time, wherein the power system utilizes a renewable energy resource to generate electrical power. A camera is positioned to capture an image of sky over a geographic region of interest. The image is analyzed to predict an amount of solar radiation that is to be received by the power source at a future point in time. The predicted solar radiation is used to predict an amount of electrical power that will be output by the power system at the future point in time. A computational resource of a data center that is powered by way of the power source is managed as a function of the predicted amount of power.

First claim

What is claimed is:

1. A computing system comprising:
at least one processor; and
memory that stores instructions that, when executed by the at least one processor, cause the at least one processor to perform acts comprising:
generating, for a time in the future, an estimate of an amount of electrical energy that is to be provided to a data center by an energy source, wherein the energy source generates the electrical energy based upon a renewable energy resource, and further wherein generating the estimate comprises:
receiving data that is indicative of at least one weather condition in a geographic region, wherein the data center is located in the geographic region; and
predicting a weather condition for the time in the future in the geographic region based upon the data, wherein the estimate is generated based upon the predicted weather condition;

based upon the estimate, generating a prediction that the amount of electrical energy that is to be provided to the data center by the energy source will drop beneath a threshold at the time in the future; and
based upon the prediction, scheduling at least one server computing device in the data center to perform a computational task, wherein the at least one server computing device performs the computational task in accordance with the scheduling.

2. The computing system of claim 1 , wherein the data comprises
an image pertaining to the geographic region,
and further wherein the weather condition for the geographic region is predicted based upon the image.

3. The computing system of claim 2 , the image being an image of the sky above the geographic region captured from the ground.

4. The computing system of claim 2 , wherein generating the estimate further comprises:
computing a size of a cloud captured in the image, wherein the weather condition is predicted based upon the size of the cloud captured in the image.

5. The computing system of claim 2 , wherein generating the estimate further comprises:
based upon the image, computing a rate of change of a size of a cloud captured in the image, wherein the weather condition is predicted based upon the rate of change of the size of the cloud captured in the image.

6. The computing system of claim 2 , wherein generating the estimate further comprises:
based upon the image, computing a direction of movement of a cloud captured in the image, wherein the weather condition is predicted based upon the direction of movement of the cloud captured in the image.

7. The computing system of claim 2 , wherein generating the estimate further comprises:
based upon the image, computing a velocity of a cloud captured in the image, wherein the weather condition is predicted based upon the velocity of the cloud captured in the image.

8. The computing system of claim 1 , the acts further comprising:
preparing a backup power source to provide power to the data center in response to predicting the weather condition for the time in the future.

9. The computing system of claim 1 , the backup power source being a battery backup, wherein preparing the backup power source to provide power to the data center comprises scheduling charging of the battery backup in response to predicting the weather condition for the time in the future.

10. A method for scheduling a server computing device in a data center to perform a computational task, the method performed by at least one computer processor, the method comprising:
generating an estimate of an amount of electrical energy that will be output by an energy source at a point in time in the future, wherein a data center is powered based upon electrical energy output by the energy source, and further wherein the energy source generates the electrical energy based upon a renewable resource, wherein generating the estimate comprises:
receiving data that is indicative of at least one weather condition in a geographic region, wherein the energy source is located in the geographic region; and
predicting, for the point in time in the future, a weather condition in the geographic region, the weather condition predicted based upon the data, and further wherein the estimate is generated based upon the predicted weather condition;

based upon the estimate, generating a prediction that, at the point in time in the future, the amount of electrical energy provided to the data center by the energy source will be below a threshold amount of electrical energy;
based upon the prediction, scheduling the server computing device in the data center to perform the computational task, wherein the server computing device performs the computational task in accordance with the scheduling of the computational task.

11. The method of claim 10 , further comprising:
based upon the estimate, scheduling the server computing device to offload a second computational task to a second server computing device at another data center.

12. The method of claim 10 , wherein scheduling the server computing device to perform the computational task comprises scheduling a reduction in processing cycles available for completion of the computational task.

13. The method of claim 10 , wherein scheduling the server computing device to perform the computational task comprises scheduling the server computing device to complete the computational task prior to the time in the future when the amount of electrical energy is predicted to drop beneath the threshold.

14. The method of claim 10 , wherein the data comprises an image, and wherein predicting, for the point in time in the future, the weather condition comprises:
computing depth of a cloud based upon the image pertaining to the geographic region, the image captured by a camera pointed upwards from earth towards sky, wherein the weather condition is predicted based upon the depth of the cloud.

15. The method of claim 10 , wherein the data comprises an image, and wherein predicting, for the point in time in the future, the weather condition comprises:
computing a rate of change of size of a cloud based upon the image pertaining to the geographic region, the image captured by a camera pointed upwards from earth towards sky, wherein the weather condition is predicted based upon the rate of change of the size of the cloud.

16. The method of claim 10 , wherein the data comprises an image, and wherein predicting, for the point in time in the future, the weather condition comprises:
computing a direction of travel of a cloud across sky based upon the image pertaining to the geographic region, the image captured by a camera pointed upwards from earth towards the sky, wherein the weather condition is predicted based upon the direction of travel of the cloud across the sky.

17. The method of claim 10 , wherein the data comprises an image, and wherein predicting, for the time in the future, the weather condition comprises:
computing a position of the sun in sky at the time in the future based upon the image pertaining to the geographic image, the image captured by a camera pointed upwards from earth towards the sky, wherein the weather condition is predicted based upon the position of the sun in the sky at the time in the future.

18. A computer-readable memory comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:
predicting an amount of solar radiation that will be received by a solar system at a time in the future based upon an image generated by a camera, the camera pointed upwards from earth towards sky;
based upon the amount of solar radiation predicted to be recei

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Williams Charles Joseph
• Kliot Gabriel
• Lin Chia-Chi
• Harris Shaun L
• Belady Christian L
• Peterson Eric C

Classifications

• G06V20/13

  Satellite images · CPC title

• G05F1/66 Primary

  Regulating electric power · CPC title

• G06N5/048

  Fuzzy inferencing · CPC title

• G01W1/00

  Meteorology · CPC title

• G06K9/0063

  Physics · mapped topic