FUTURE CLOUD RESOURCE USAGE COST MANAGEMENT

• US 20160034835A1
• Filed: 07/31/2014
• Published: 02/04/2016
• Est. Priority Date: 07/31/2014
• Status: Abandoned Application

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: COHEN, Ira, LEVI, Efrat Egozi, LEVI, Ran, SADE, Sigalit
• Application Number:
  US14/448,729
• Publication Number:
  US 20160034835A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/06313 Resource planning in a project environment
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

According to an example, a history of usage and a history of utilization of resources may be accessed. A usage regression model to predict a cloud resource usage and a utilization regression model to predict a cloud resource utilization at a future time period may be developed. The usage regression model and the utilization regression model may be used to manage cloud resource usage costs.

Claims

1. A method for future cloud resource usage cost management, said method comprising:

accessing a history of usage of a plurality of resources;

accessing a history of utilization of the plurality of resources;

developing, by a processor and based upon the history of usage, a usage regression model to predict a cloud resource usage at a future time period;

developing, by the processor and based upon the history of utilization, a utilization regression model to predict a cloud resource utilization for each of a plurality of utilization variable/resource pairs at the future time period; and

managing a future cloud resource usage cost based upon the usage regression model and the utilization regression model.

2. The method according to claim 1, further comprising:

predicting a cloud resource usage at the future time period based upon the usage regression model;

predicting a cloud resource utilization at the future time period based upon the utilization regression model;

wherein managing the future cloud resource usage cost further comprises determining a cost optimization recommendation based upon the predicted cloud resource usage and the predicted cloud resource utilization at the future time period.

3. The method according to claim 2, wherein determining the cost optimization recommendation further comprises determining the cost optimization recommendation to be a reservation of resources from a cloud computing service provider for the predicted cloud resource usage at the future time period that results in a minimized cost for the predicted cloud resource usage.

4. The method according to claim 1, further comprising:

developing, by the processor, a plurality of usage regression models that each predicts a cloud resource usage at a plurality of future time periods; and

developing, by the processor, a plurality of utilization regression models that each predicts a cloud resource utilization for each of a plurality of utilization variable/resource pairs at the plurality of future time periods.

5. The method according to claim 4, further comprising:

predicting a cloud resource usage at each of the plurality of future time periods based upon the usage regression model at a respective one of the plurality of future time periods;

predicting a cloud resource utilization at each of the plurality of future time periods based upon the utilization regression model at a respective one of the plurality of future time periods; and

wherein managing the future cloud resource usage cost further comprises determining a cost optimization recommendation for each of the plurality of future time periods based upon the predicted cloud resource usage and the predicted cloud resource utilization at each of the plurality of future time periods.

6. The method according to claim 5, further comprising:

determining a confidence measure for each of the cost optimization recommendations at the plurality of future time periods.

7. The method according to claim 6, further comprising:

calculating respective scores for each of the cost optimization recommendations at the plurality of future time periods based upon the confidence measures for each of the plurality of future time periods; and

ranking the cost optimization recommendations according to the calculated scores.

8. The method according to claim 5, wherein determining the cost optimization recommendations for each of the plurality of future time periods further comprises determining the cost optimization recommendations to each be a reservation of resources from a cloud computing service provider for the predicted cloud resource usage and the predicted cloud resource utilization at each of the plurality of future time periods.

9. An apparatus for recommending an order for future cloud resource usage, said apparatus comprising:

a processor; and

a memory on which is stored machine readable instructions to cause the processor to;

access a history of usage and a history of utilization of a plurality of resources;

develop, based upon the history of usage, a usage regression model;

develop, based upon the history of utilization, a utilization regression model;

predict a cloud resource usage at a future time period based upon the usage regression model;

predict a cloud resource utilization for each of a plurality of utilization variable/resource pairs at the future time period based upon the utilization regression model; and

recommend the order for future cloud resource usage based upon the predicted cloud resource usage and the predicted cloud resource utilization, wherein the order recommendation is a recommendation for usage of cloud resources supplied by a cloud computing services provider at the future time period.

10. The apparatus according to claim 9, wherein the machine readable instructions are further to cause the processor to:

develop a plurality of usage regression models that each predicts a cloud resource usage at a plurality of future time periods; and

develop a plurality of utilization regression models that each predicts a cloud resource utilization for each of a utilization variable/resource pair at the plurality of future time periods.

11. The apparatus according to claim 10, wherein the machine readable instructions are further to cause the processor to:

predict a cloud resource usage at each of the plurality of future time periods based upon the usage regression model at a respective one of the plurality of future time periods;

predict a cloud resource utilization at each of the plurality of future time periods based upon the utilization regression model at a respective one of the plurality of future time periods; and

wherein, to recommend the order, the instructions are further to cause the processor to determine respective costs corresponding to the predictions at each of the plurality of future time periods, and to determine the order for future cloud resource usage to be the order that corresponds to the lowest cost.

12. The apparatus according to claim 11, wherein the machine readable instructions are further to cause the processor to:

determine a respective confidence measure for each of the resource usage and resource utilization predictions at the plurality of future time periods.

13. The apparatus according to claim 12, wherein the machine readable instructions are further to cause the processor to:

calculate respective scores for each of the resource usage and resource utilization predictions at the plurality of future time periods based upon the confidence measures for each of the plurality of future time periods; and

rank the cost optimization recommendations according to the calculated scores.

14. A non-transitory computer-readable storage medium on which is stored machine readable instructions that when executed by a processor cause the processor to:

access a history of usage of a history of utilization by an entity of a plurality of cloud resources;

develop, based upon the history of usage, a plurality of usage regression models;

develop, based upon the history of utilization, a plurality of utilization regression models;

predict cloud resource usages at a plurality of future time periods based upon the plurality of usage regression models;

predict cloud resource utilizations for each of a plurality of utilization variable/resource pairs at the plurality of future time periods based upon the plurality of utilization regression models; and

determine a cost optimization recommendation for the entity for each of the plurality of future time periods based upon the predicted cloud resource usages and the predicted cloud resource utilizations at the plurality of future time periods.

15. The non-transitory computer-readable storage medium according to claim 14, wherein the machine readable instructions are further to cause the processor to:

determine a respective confidence measure for each of the resource usage and resource utilization predictions at the plurality of future time periods;

calculate respective scores for each of the resource usage and resource utilization predictions at the plurality of future time periods based upon the confidence measures for each of the plurality of future time periods; and

rank the cost optimization recommendations according to the calculated scores.