Enterprise data-driven system for predictive resource provisioning in cloud environments

Patent metadata

Field	Value
Publication number	US-9606840-B2
Application number	US-201313928998-A
Country	US
Kind code	B2
Filing date	Jun 27, 2013
Priority date	Jun 27, 2013
Publication date	Mar 28, 2017
Grant date	Mar 28, 2017

Abstract

Implementations of the present disclosure include methods, systems, and computer-readable storage mediums for predicting resource consumption in cloud infrastructures. Implementations include actions of receiving event data from one or more enterprise data sources, determining that an event associated with the event data is a known event, retrieving resource consumption information associated with the event, and providing a resource consumption schedule to a cloud infrastructure, the resource consumption schedule indicating resources expected to be consumed during execution of the event.

First claim

What is claimed is:

1. A computer-implemented method for predicting resource consumption in cloud infrastructures, the method being executed using one or more processors and comprising:
receiving, by the one or more processors, event data from one or more enterprise data sources, the event data comprising an interaction between an enterprise and a cloud infrastructure;
determining, by the one or more processors, that an event associated with the event data is a known event by matching the event with an existing event entry in a matching table using a matching format comprising at least one of a class of the event, an average memory allocation consumed, and an average processing units consumed;
retrieving, by the one or more processors, resource consumption information associated with the event; and
providing, by the one or more processors, a resource consumption schedule to the cloud infrastructure, the resource consumption schedule indicating discrete values of a future demand using different levels of probability of the future demand, the future demand being associated with resources expected to be consumed during execution of the event that are quantified based on a stepwise refinement of a time, at which or during which the event is to be executed.

2. The method of claim 1 , wherein the resource consumption schedule further indicates a time at which or during which the event is to be executed, and a probability that the event will be executed at or during the time.

3. The method of claim 1 , further comprising normalizing the event data, such that the event data is provided in a format for resource consumption prediction.

4. The method of claim 1 , wherein determining that an event associated with the event data is a known event comprises referencing a deviation table, the deviation table indicating expected behavior associated with the event.

5. The method of claim 4 , wherein expected behavior comprises one or more of expected frequency, expected time intervals between event execution, and one or more event contexts.

6. The method of claim 1 , further comprising:
determining that at least one event associated with the event data is an unknown event; and
storing the at least one event in a storage table.

7. The method of claim 6 , wherein the at least one event is included in the resource consumption schedule.

8. The method of claim 6 , further comprising:
receiving feedback from the cloud infrastructure, the feedback comprising resource consumption information associated with the at least one event; and
updating a matching table to include the at least one event as a known event, and to include the resource consumption information associated with the at least one event.

9. The method of claim 1 , further comprising receiving feedback from the cloud infrastructure, the feedback comprising actual resource consumption information associated with the event.

10. The method of claim 9 , further comprising updating a matching table based on the actual resource consumption information.

11. The method of claim 1 , wherein the one or more resources comprise at least one of storage resources and computational resources.

12. The method of claim 1 , wherein the enterprise data sources comprise one or more of a workflow engine, a business object (BO) state machine, a collaboration portal, and an analytics data engine.

13. A non-transitory computer-readable storage medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for predicting resource consumption in cloud infrastructures, the operations comprising:
receiving event data from one or more enterprise data sources, the event data comprising an interaction between an enterprise and a cloud infrastructure;
determining that an event associated with the event data is a known event by matching the event with an existing event entry in a matching table using a matching format comprising at least one of a class of the event, an average memory allocation consumed, and an average processing units consumed;
retrieving resource consumption information associated with the event; and
providing a resource consumption schedule to the cloud infrastructure, the resource consumption schedule indicating discrete values of a future demand using different levels of probability of the future demand, the future demand being associated with resources expected to be consumed during execution of the event that are quantified based on a stepwise refinement of a time, at which or during which the event is to be executed.

14. A system, comprising:
a computing device; and
a computer-readable storage device coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations for predicting resource consumption in cloud infrastructures, the operations comprising:
receiving event data from one or more enterprise data sources, the event data comprising an interaction between an enterprise and a cloud infrastructure;
determining that an event associated with the event data is a known event by matching the event with an existing event entry in a matching table using a matching format comprising at least one of a class of the event, an average memory allocation consumed, and an average processing units consumed;
retrieving resource consumption information associated with the event; and
providing a resource consumption schedule to the cloud infrastructure, the resource consumption schedule indicating discrete values of a future demand using different levels of probability of the future demand, the future demand being associated with resources expected to be consumed during execution of the event that are quantified based on a stepwise refinement of a time, at which or during which the event is to be executed.

Assignees

• Schaad Andreas
• Sap Se

Inventors

• Schaad Andreas

Classifications

• H04L67/1097

  for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title

• H04L41/069

  using logs of notifications; Post-processing of notifications · CPC title

• H04L41/147

  for predicting network behaviour · CPC title

• G06F9/5072 Primary

  Grid computing · CPC title

• H04L67/325

  Electricity · mapped topic