MANAGING COMPUTATIONAL WORKLOADS OF COMPUTING APPARATUSES POWERED BY RENEWABLE RESOURCES

• US 20120065788A1
• Filed: 09/14/2010
• Published: 03/15/2012
• Est. Priority Date: 09/14/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Harper, David Tennyson III, Peterson, Eric C., Harris, Shaun L., Belady, Christian L.
• Granted Patent: US 9,348,394 B2
• Time in Patent Office: Days
• US Class Current: 700/291
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 1/329 by task scheduling
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A method described herein includes an act of receiving data that is indicative of predicted weather conditions for a particular geographic region, wherein the particular geographic region has an energy generation system therein, and wherein the energy generation system utilizes at least one renewable energy resource to generate electrical power. The method also includes the act of scheduling a computational workload for at least one computer in a data center based at least in part upon the data that is indicative of the predicted weather conditions for the particular geographic region.

Claims

1. A method comprising the following computer-executable acts:

receiving data that is indicative of predicted weather conditions for a particular geographic region, wherein the particular geographic region has a power system therein, and wherein the power system utilizes at least one renewable energy resource to generate electrical power; and

scheduling a computational workload for at least one computer in a data center based at least in part upon the data that is indicative of the predicted weather conditions for the particular geographic region.

2. The method of claim 1, further comprising:

computing a predicted power to be output by the power system based at least in part upon the data that is indicative of the predicted weather conditions for the particular geographic region; and

scheduling the computational workload for the at least one computer in the data center based at least in part upon the predicted power.

3. The method of claim 1, wherein the at least one renewable energy resource is at least one of wind, sunlight, geothermal energy, hydro energy, or waves.

4. The method of claim 1, wherein the at least one data center is provided electrical power by the power system.

5. The method of claim 1, wherein the at least one data center is provided electrical power by way of an electrical system grid.

6. The method of claim 1, wherein the predicted weather conditions comprise predicted weather conditions over a plurality of days.

7. The method of claim 1, wherein the predicted weather conditions comprise predicted weather conditions within an hour of a current time.

8. The method of claim 1, further comprising:

receiving current weather-related data pertaining to the particular geographic region generated by a plurality of sensors;

accessing a data store that comprises historical weather-related data pertaining to the particular geographic region; and

generating the data that is indicative of the predicted weather conditions based at least in part upon the current-weather related data and the historical weather-related data.

9. The method of claim 8, further comprising utilizing a machine-learned model to generate the data that is indicative of the predicted weather conditions.

10. The method of claim 9, wherein the machine learned model comprises one or more of a Bayesian network, a Support Vector Machine, an artificial neural network, or a regression tree.

11. The method of claim 1 configured for execution in a computing device in a data center.

12. A computing apparatus, comprising:

a processor; and

a memory that comprises a plurality of components that are executable by the processor, the components comprising;

a receiving component that receives data that is indicative of an expected amount of power to be generated by a power system whose power output varies with alterations in environmental conditions; and

a scheduler component that schedules a computational workload for a computer based at least in part upon the data that is indicative of the expected amount of power to be generated by the power system.

13. The computing apparatus of claim 12, wherein the power system utilizes at least one renewable resource to output electrical power.

14. The computing apparatus of claim 13, wherein the at least one renewable resource is one of radiation from the sun, wind, hydro energy, geothermal energy or waves.

15. The computing apparatus of claim 12, wherein the computer is in a first data center, and wherein the scheduler component schedules a computational workload for another computer in a second data center based at least in part upon the data that is indicative of the expected amount of power to be generated by the power system.

16. The computing apparatus of claim 12, wherein the components further comprise a power estimator component that estimates the expected amount of power based at least in part upon at least one estimated weather condition over a time range.

17. The computing apparatus of claim 16, wherein the components further comprise a weather estimator component that estimates the at least one weather condition over the time range based at least in part upon historical weather data and current weather conditions.

18. The computing apparatus of claim 17, wherein the estimator component comprises at least one of an artificial neural network, a support vector machine, a Bayesian network, or a regression tree.

19. The computing apparatus of claim 18, wherein the scheduler component schedules computational workloads for a plurality of computing devices in a data center based at least in part upon service level agreements corresponding to the computing devices and the data that is indicative of the expected amount of power to be generated by the power system.

20. A computer-readable medium comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:

receiving first data that is indicative of current weather conditions from one or more sensors for a particular geographic region;

receiving second data that is indicative of historical weather conditions for the particular geographic region;

based at least in part upon the first data and the second data, generating an estimate of at least one weather condition for the particular geographic region at a future point in time;

based at least in part upon the estimate of the at least one weather condition, generating an estimate of power to be output by a power system at a future point in time, wherein the power system outputs electrical power based at least in part upon a variable renewable resource; and

scheduling a computational workload for at least one computer in a data center based at least in part upon the estimate of the power to be output by the power system at the future point in time.