Data center power management utilizing a power policy and a load factor

• US 8,001,403 B2
• Filed: 03/14/2008
• Issued: 08/16/2011
• Est. Priority Date: 03/14/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Freely, James J, Fortin, Michael R, Neil, Mike, Hamilton, James R, Manos, Michael J
• Primary Examiner(s): Suryawanshi; Suresh
• Application Number:
  US12/049,050
• Publication Number:
  US 20090235097A1
• Time in Patent Office: 1,250 Days
• Field of Search: 713/320
• US Class Current: 713/320
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode

Abstract

An exemplary method for managing power consumption of a data center includes monitoring power consumption of a data center, assessing power consumption with respect to a billing equation for power, based on the assessment, deciding whether to implement a power policy where the power policy reduces instantaneous power consumption by the data center and increases a load factor wherein the load factor is an average power consumed by the data center divided by a peak power consumed by the data center over a period of time. Various other methods, devices, systems, etc., are also disclosed.

Claims

1. A method for managing power consumption of a data center, the method comprising:

monitoring power consumption of a data center;

comparing power consumption to a power consumption threshold;

based on the comparing, deciding whether to implement a power policy wherein the power policy reduces instantaneous power consumption by the data center and increases a load factor wherein the load factor is an average power consumed by the data center divided by a peak power consumed by the data center over a period of time.

2. The method of claim 1 wherein the data center comprises multi-core servers.

3. The method of claim 1 wherein the power policy comprises adjusting performance states associated with dynamic voltage and frequency scaling.

4. The method of claim 3 wherein the adjusting performance states causes a delay in processing workload of the data center and decreases instantaneous power consumption of the data center.

5. The method of claim 1 wherein the power policy comprises adjusting throttle states.

6. The method of claim 5 wherein the adjusting throttle states causes a delay in processing workload of the data center and decreases instantaneous power consumption of the data center.

7. The method of claim 1 wherein the data center comprises servers and the power policy comprises shutting down at least some of the servers.

8. The method of claim 1 wherein the power policy comprises adjusting sleep states.

9. The method of claim 8 wherein the adjusting sleep states decreases instantaneous power consumption of the data center.

10. The method of claim 1 wherein the power policy comprises redirecting requests for data center resources to one or more other data centers.

11. The method of claim 1 wherein the data center comprises servers and wherein the power policy comprises consolidating workload to increase efficiency.

12. The method of claim 2 wherein the power policy further comprises adjusting sleep states of at least some of the servers.

13. A method for managing power consumption of a data center, the method comprising:

monitoring power consumption of a data center;

assessing power consumption with respect to a billing equation for power;

based on the assessing, deciding whether to implement a power policy wherein the power policy reduces instantaneous power consumption by the data center and increases a load factor wherein the load factor is an average power consumed by the data center divided by a peak power consumed by the data center over a period of time.

14. The method of claim 13 wherein the power policy comprises selecting a different power source.

15. The method of claim 13 wherein the data center comprises multi-core servers and wherein the power policy comprises adjusting operational states for one or more cores of a multi-core server.

16. The method of claim 13 wherein the power policy comprises a policy that accounts for ambient temperature.

17. The method of claim 13 wherein the power policy comprises a policy that accounts for weather.

18. The method of claim 13 wherein the power policy comprises a policy that accounts for power consumption by a cooling unit.

19. The method of claim 18 wherein the policy accounts for cyclical power consumption by the cooling unit.

20. A module for shaping power consumption by a multi-core server, the module comprising:

instructions to adjust performance states responsive to a data center power consumption signal to reduce instantaneous power consumption by a multi-core server;

instructions to adjust throttle states responsive to a data center power consumption signal to reduce instantaneous power consumption by a multi-core server; and

instructions to adjust sleep states responsive to a data center power consumption signal to reduce instantaneous power consumption by a multi-core server;

wherein a reduction in instantaneous power consumption by a multi-core server acts to increases a load factor for a data center wherein the load factor is an average power consumed by the data center divided by a peak power consumed by the data center over a period of time.