Predictive system remediation

Patent metadata

Field	Value
Publication number	US-11860729-B2
Application number	US-202217705760-A
Country	US
Kind code	B2
Filing date	Mar 28, 2022
Priority date	Aug 6, 2019
Publication date	Jan 2, 2024
Grant date	Jan 2, 2024

Abstract

Techniques for predictive system remediation are disclosed. Based on attributes associated with applications of one or more system-selected remedial actions to one or more problematic system behaviors in a system (e.g., a database system), the system determines a predicted effectiveness of one or more future applications of a remedial action to a particular problematic system behavior, as of one or more future times. The system determines that the predicted effectiveness of the one or more future applications of the remedial action is positive but does not satisfy a performance criterion. Responsive to determining that the predicted effectiveness is positive but does not satisfy the performance criterion, the system generates a notification corresponding to the predicted effectiveness not satisfying the performance criterion. The system applies the remedial action to the particular problematic system behavior, despite already determining that the predicted effectiveness does not satisfy the one or more performance criteria.

First claim

What is claimed is:

1. One or more non-transitory machine-readable media storing instructions which, when executed by one or more processors, cause performance of operations comprising:
monitoring data to identify system behaviors;
identifying, during a first period of time, a first occurrence of a particular system behavior based on the monitored data;
predicting that the first occurrence of the particular system behavior will self-rectify;
responsive at least to predicting that the first occurrence of the particular system behavior will self-rectify: classifying the first occurrence of the particular system behavior as non-problematic;
identifying, during a second period of time, a second occurrence of the particular system behavior based on the monitored data;
predicting that the second occurrence of the particular system behavior will not self-rectify; and
responsive at least to predicting that the second occurrence of the particular system behavior will not self-rectify: classifying the second occurrence of the particular system behavior as problematic.

2. The one or more machine-readable media of claim 1 , wherein predicting that the first occurrence of the particular system behavior will self-rectify comprises predicting that the first occurrence of the particular system behavior will self-rectify at the end of a season corresponding to the first period of time.

3. The one or more machine-readable media of claim 1 , wherein the first occurrence of the particular system behavior is identified in response to determining that the particular system behavior deviates from an expected system behavior.

4. The one or more non-transitory machine-readable media of claim 1 , wherein the operations further comprise:
identifying a remedial action associated with the particular system behavior;
determining that applying the remedial action to the first occurrence of the particular system behavior is associated with a first predicted effectiveness; and
determining that applying the remedial action to the second occurrence of the particular system behavior is associated with a second predicted effectiveness that is greater than the first predicted effectiveness.

5. The one or more non-transitory machine-readable media of claim 4 , wherein the operations further comprise:
based on the first predicted effectiveness of applying the remedial action to the first occurrence of the particular system behavior, refraining from applying the remedial action to the first occurrence of the particular system behavior; and
based on the second predicted effectiveness of applying the remedial action to the second occurrence of the particular system behavior, applying the remedial action to the second occurrence of the particular system behavior.

6. The one or more non-transitory machine-readable media of claim 4 , wherein the operations further comprise:
determining the first predicted effectiveness by applying current system state data to a machine learning model configured to predict future effectiveness of remedial actions.

7. The one or more non-transitory machine-readable media of claim 6 , wherein the operations further comprise:
training the machine learning model to predict the future effectiveness of the remedial actions using a plurality of attributes associated with a plurality of applications of system-selected remedial actions to one or more problematic system behaviors in a database system.

8. The one or more non-transitory machine-readable media of claim 1 , wherein the first period of time corresponds to a first season, the first season being a peak season associated with a relatively high-system-resource-usage system behavior pattern, relative to a second season, and
wherein the second period of time corresponds to the second season, the second season being a non-peak season associated with a relatively low-system-resource-usage system behavior pattern, relative to the first season.

9. A method, comprising:
monitoring data to identify system behaviors;
identifying, during a first period of time, a first occurrence of a particular system behavior based on the monitored data;
predicting that the first occurrence of the particular system behavior will self-rectify;
responsive at least to predicting that the first occurrence of the particular system behavior will self-rectify: classifying the first occurrence of the particular system behavior as non-problematic;
identifying, during a second period of time, a second occurrence of the particular system behavior based on the monitored data;
predicting that the second occurrence of the particular system behavior will not self-rectify; and
responsive at least to predicting that the second occurrence of the particular system behavior will not self-rectify: classifying the second occurrence of the particular system behavior as problematic.

10. The method of claim 9 , wherein predicting that the first occurrence of the particular system behavior will self-rectify comprises predicting that the first occurrence of the particular system behavior will self-rectify at the end of a season corresponding to the first period of time.

11. The method of claim 9 , wherein the first occurrence of the particular system behavior is identified in response to determining that the particular system behavior deviates from an expected system behavior.

12. The method of claim 9 , further comprising:
identifying a remedial action associated with the particular system behavior;
determining that applying the remedial action to the first occurrence of the particular system behavior is associated with a first predicted effectiveness; and
determining that applying the remedial action to the second occurrence of the particular system behavior is associated with a second predicted effectiveness that is greater than the first predicted effectiveness.

13. The method of claim 12 , further comprising:
based on the first predicted effectiveness of applying the remedial action to the first occurrence of the particular system behavior, refraining from applying the remedial action to the first occurrence of the particular system behavior; and
based on the second predicted effectiveness of applying the remedial action to the second occurrence of the particular system behavior, applying the remedial action to the second occurrence of the particular system behavior.

14. The method of claim 12 , further comprising:
determining the first predicted effectiveness by applying current system state data to a machine learning model configured to predict future effectiveness of remedial actions.

15. The method of claim 14 , further comprising:
training the machine learning model to predict the future effectiveness of the remedial actions using a plurality of attributes associated with a plurality of applications of system-selected remedial actions to one or more problematic system behaviors in a database system.

16. The method of claim 9 , wherein the first period of time corresponds to a first season, the first season being a peak season associated with a relatively high-system-re source-usage system behavior pattern, relative to a second season, and
wherein the second period of time corresponds to the second season, the second season being a non-peak season associated with a relatively low-system-resource-usage system behavior pattern, relative to the first season.

17. A system comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
mon

Assignees

• Oracle Int Corp

Inventors

• Sutton Eric
• Garvey Dustin
• Salunke Sampanna Shahaji
• Shaft Uri

Classifications

• H02J7/70

  characterised by the mechanical construction · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06N3/092

  Reinforcement learning · CPC title

• G06N20/00

  Machine learning · CPC title