POINT-IN-TIME BASED ENERGY SAVING RECOMMENDATIONS

• US 20110010222A1
• Filed: 07/08/2009
• Published: 01/13/2011
• Est. Priority Date: 07/08/2009
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Subramanian, Balan, Verma, Akshat, Jhoney, Albee, Dasgupta, Gargi B., Salahshour, Abdolreza, Choudhary, Samar
• Application Number:
  US12/499,179
• Publication Number:
  US 20110010222A1
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: Y02P 90/82 Energy audits or management systems therefor

Abstract

Energy saving efforts should not compromise data center performance. An energy management application can determine usage patterns in historical energy usage data based on statistical analysis and energy models. Energy savings recommendations can be generated for future points-in-time based on the usage patterns. Business constraints can be applied to the energy savings recommendations to ensure that the energy savings recommendations meet performance requirements.

Claims

1. A computer implemented method comprising:

retrieving historical usage data in response to a request to generate energy saving recommendations for a data center, wherein the historical usage data represents energy usage of the data center;

determining usage patterns in the historical usage data based on statistical analysis;

determining repetitions of the usage patterns;

generating energy saving recommendations that indicate energy saving actions to initiate at particular times based on the usage patterns and the repetitions;

determining a business constraint of the data center; and

refining the energy saving recommendations based on the business constraint.

2. The computer implemented method of claim 1 further comprising storing the energy saving recommendations in a standardized format.

3. The computer implemented method of claim 1, wherein said determining the usage patterns in the historical usage data based on statistical analysis comprises:

determining an optimization interval, wherein the optimization interval represents a time period smaller than a past time period of the historical usage data;

dividing the historical usage data into time intervals based, at least in part, on the optimization interval; and

determining the usage patterns based on each of the time intervals.

4. The computer implemented method of claim 1, wherein the energy saving actions comprise one or more of powering down resources, putting resources in standby mode, putting resource in dynamic power savings mode, shifting workloads to more efficient resources, using Dynamic Voltage and Frequency Scaling, and deploying more efficient resources.

5. The computer implemented method of claim 1 further comprising computing a confidence, a risk, and a savings amount for each energy saving recommendation, wherein the confidence represents quality of the historical data, wherein the risk represents likelihood of the energy saving recommendation violating the business constraint.

6. The computer implemented method of claim 1, wherein said refining the energy saving recommendations based on the business constraint comprises:

determining that a first of the energy saving recommendations violates the business constraint;

determining that the first energy saving recommendation can be updated to comply with the business constraint; and

updating the first energy saving recommendation to comply with the business constraint.

7. A computer program product for generating energy saving recommendations, the computer program product comprising:

a computer usable medium having computer usable program code embodied therewith, the computer usable program code comprising;

computer usable program code configured to,

retrieve historical usage data in response to a request to generate energy saving recommendations for a data center, wherein the historical usage data represents energy usage of the data center;

determine usage patterns in the historical usage data based on statistical analysis;

determine repetitions of the usage patterns;

generate energy saving recommendations that indicate energy saving actions to initiate at particular times based on the usage patterns and the repetitions;

determine a business constraint of the data center; and

refine the energy saving recommendations based on the business constraint.

8. The computer program product of claim 7, wherein the computer usable program code being configured to retrieve historical usage data in response to a request to generate energy saving recommendations for a data center is based, at least in part, on a past time period.

9. The computer program product of claim 7, wherein the computer usable program code being configured to determine the usage patterns in the historical usage data based on statistical analysis comprises the computer usable program code being configured to:

determine an optimization interval, wherein the optimization interval represents a time period smaller than a past time period of the historical usage data;

divide the historical usage data into time intervals based, at least in part, on the optimization interval; and

determine the usage patterns based on each of the time intervals.

10. The computer program product of claim 7, wherein the computer usable program code is further configured to deploy the energy saving recommendations in the data center.

11. The computer program product of claim 7, wherein the computer usable program code is further configured to compute a confidence, a risk, and a savings amount for each energy saving recommendation, wherein the confidence represents quality of the historical data, wherein the risk represents likelihood of the energy saving recommendation violating the business constraint.

12. The computer program product of claim 7, wherein the computer usable program code being configured to refine the energy saving recommendations based on the business constraint comprises the computer usable program code being configured to:

determine that a first of the energy saving recommendations violates the business constraint;

determine that the first energy saving recommendation can be updated to comply with the business constraint; and

update the first energy saving recommendation to comply with the business constraint.

13. A computer program product for generating energy saving recommendations, the computer program product comprising:

a computer usable medium having computer usable program code embodied therewith, the computer usable program code comprising;

computer usable program code configured to,

detect a request to generate energy saving recommendations for a data center;

determine an optimization period, a date range, and an optimization interval based on the request;

retrieve historical usage data corresponding to the date range, wherein the historical usage data represents energy usage of a plurality of resources in a data center;

divide the historical usage data into time intervals based on the optimization interval;

determine a pattern in each time interval based on statistical analysis;

determine repetitions of the patterns within the date range;

predict future usage over the optimization period based on the repetitions;

generate energy saving recommendations that indicate specific energy saving actions at specific times based on the future usage;

determining a business constraint for the data center; and

refining the energy saving recommendations based on the business constraint; and

computing a confidence, a risk, and a savings amount for each energy saving recommendation.

14. The computer program product of claim 13 further comprises:

determine that the energy saving recommendations should be coalesced with second energy savings recommendations for a second data center;

retrieving the second energy saving recommendations from the second data center;

determining relationships between resources in the data center and the second data center;

determining second business constraint governing the overall performance of the data center and the second data center; and

refining the energy saving recommendations and the second energy saving recommendations based on the second business constraint and the relationships.

15. An apparatus comprising:

a processing unit;

a network interface; and

an energy optimization unit comprising;

a data collector operable to,

retrieve historical usage data in response to a request to generate energy saving recommendations for a data center, wherein the historical usage data represents energy usage of the data center;

an analyzer operable to,

determine usage patterns in the historical usage data based on statistical analysis;

determine repetitions of the usage patterns;

a modeler operable to,

generate energy saving recommendations that indicate energy saving actions to initiate at particular times based on the usage patterns and the repetitions; and

a recommendation builder operable to,

determine a business constraint of the data center; and

refine the energy saving recommendations based on the business constraint.

16. The apparatus of claim 15, wherein the data collector being operable to retrieve historical usage data in response to a request to generate energy saving recommendations for a data center is based, at least in part, on a past time period.

17. The apparatus of claim 15, wherein the analyzer being operable to determine the usage patterns in the historical usage data based on statistical analysis comprises the analyzer being operable to:

determine an optimization interval, wherein the optimization interval represents a time period smaller than a past time period of the historical usage data;

divide the historical usage data into time intervals based, at least in part, on the optimization interval; and

determine the usage patterns based on each of the time intervals.

18. The apparatus of claim 15, wherein the energy saving actions comprise one or more of powering down resources, putting resources in standby mode, putting resource in dynamic power savings mode, shifting workloads to more efficient resources, using Dynamic Voltage and Frequency Scaling, and deploying more efficient resources.

19. The apparatus of claim 15, wherein the recommendation builder is further operable to compute a confidence, a risk, and a savings amount for each energy saving recommendation, wherein the confidence represents quality of the historical data, wherein the risk represents likelihood of the energy saving recommendation violating the business constraint.

20. The apparatus of claim 15, wherein the recommendation builder being operable to refine the energy saving recommendations based on the business constraint comprises the recommendation builder being operable to:

determine that a first of the energy saving recommendations violates the business constraint;

determine that the first energy saving recommendation can be updated to comply with the business constraint; and

update the first energy saving recommendation to comply with the business constraint.