SELF-LEARNING INTEGRITY MANAGEMENT SYSTEM AND RELATED METHODS

• US 20090063390A1
• Filed: 11/13/2008
• Published: 03/05/2009
• Est. Priority Date: 09/27/2006
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: Integrien Corp. (Broadcom, Inc.)
• Inventors: Marvasti, Mazda A.
• Granted Patent: US 7,801,703 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

An integrity management system predicts abnormalities in complex systems before they occur based upon the prior history of abnormalities within the complex system. A topology of the nodes of a complex system is generated and data is collected from the system based on predetermined metrics. In combination with dynamic thresholding, fingerprints of the relevant nodes within a complex system at various time intervals prior to the occurrence of the abnormality are captured and weighted. The fingerprints can then be applied to real-time data provide alerts of potential abnormality prior to their actual occurrence.

Claims

1. A dynamic thresholding system comprising, in combination:

a data collection module that collects metric data and stores the metric data;

a model execution engine for analyzing the metric data based on at least one model in an analytics model library and at least one analytics model library rule to form a transformed metric data set;

a dynamic threshold generator for determining at least one dynamic threshold for a metric from the transformed metric data set of a historical time period.

2. The system of claim 1, further comprising a data type determination module.

3. The system of claim 1, wherein new dynamic thresholds are determined at predetermined time intervals.

4. The system of claim 1, further comprising an event prediction module.

5. The system of claim 1, further comprising a resolution module.

6. A dynamic thresholding system comprising, in combination:

at least one dynamically determined threshold associated with a metric, the dynamically determined threshold being changed at set intervals based on the metric'"'"'s observed data for a historical time period; and

a subsystem for detecting trend states, the trend state occurring when any dynamically determined threshold is exceeded continuously for a time period;

wherein when the subsystem detects a trend, an alert state is activated.

7. The dynamic thresholding system of claim 6, wherein a fingerprint is captured when the dynamic thresholding system observes a trend.

8. The dynamic thresholding system of claim 6, further comprising at least one hard threshold.

9. A method comprising:

collecting data from a metric and storing the data;

transforming the data with at least one model from an analytics model library and at least one model library rule and storing the transformed data in a set of historical transformed data;

determining a dynamic threshold for the metric using the set of historical transformed data;

modifying the dynamic threshold periodically to reflected more recent historical transformed data.

10. The method of claim 9, further comprising comparing the data to a dynamic threshold existing at about the same time period in which the data is collected.

11. The method of claim 9, further comprising comparing the transformed data to a dynamic threshold existing at about the same time period in which the data is collected.

12. The method of claim 9, further comprising determining the type of the data.

13. The method of claim 10, further comprising triggering an alert state when the value of the data exceeds the dynamic threshold for a predetermined period of time.

14. The method of claim 13, wherein the alert state is triggered when the value of the data exceeds a hard threshold.

15. The method of claim 11, further comprising triggering an alert state when the value of the transformed data exceeds the dynamic threshold for a predetermined period of time.

16. The method of claim 15, wherein the alert state is triggered when the value of the transformed data exceeds a hard threshold.