Power distribution network event correlation and analysis

• US 9,093,841 B2
• Filed: 02/16/2012
• Issued: 07/28/2015
• Est. Priority Date: 02/16/2012
• Status: Active Grant

• Current Assignee: GE Digital Holdings LLC (GE Vernova, Inc.)
• Original Assignee: General Electric Company
• Inventors: San Andres, Ramon Juan, Nigam, Atul
• Primary Examiner(s): HARTMAN JR, RONALD D
• Application Number:
  US13/398,196
• Publication Number:
  US 20130218354A1
• Time in Patent Office: 1,258 Days
• Field of Search: 700/286, 700292-294
• US Class Current: 1/1
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: H02J 13/00017 using optical fiber
• CPC Class Codes: H02J 2203/20 Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
• CPC Class Codes: H02J 3/00 Circuit arrangements for ac mains or ac distribution networks
• CPC Class Codes: Y02B 70/3225 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y02E 60/00 Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
• CPC Class Codes: Y04S 10/30 State monitoring, e.g. fault, temperature monitoring, insulator monitoring, corona discharge
• CPC Class Codes: Y04S 10/52 Outage or fault management, e.g. fault detection or location
• CPC Class Codes: Y04S 20/222 Demand response systems, e.g. load shedding, peak shaving
• CPC Class Codes: Y04S 40/20 Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Abstract

A method for power distribution network correlation and analysis includes receiving event data from a plurality of data sources, identifying an event of interest, retrieving, in a querying engine, the event data, correlating the event data and the event of interest and identifying one or more root causes of the event of interest.

Claims

1. A method for power distribution network correlation and analysis, the method comprising:

receiving event data of a plurality of events from a plurality of sources, wherein at least a portion of the event data is non-network data;

identifying, based at least in part on an analysis of the event data of the plurality of events, an event of interest and at least one event determined to be potentially related to the event of interest, wherein the event of interest and the at least one event determined to be potentially related to the event of interest are selected from the plurality of events, and wherein the at least one event determined to be potentially related to the event of interest occurred within a predetermined time period proximate to an occurrence of the event of interest;

retrieving, in a querying engine, event data of the event of interest and event data of the at least one event determined to be potentially related to the event of interest, wherein the event data of the event of interest and the event data of the at least one event determined to be potentially related to the event of interest are comprised in the received event data of the plurality of events;

correlating the event data of the event of interest and the event data of the at least one event determined to be potentially relevant to the event of interest to thereby correlate the event of interest and the at least one event determined to be potentially related to the event of interest; and

identifying one or more root causes of the event of interest based at least in part on analysis of the event data of the event of interest and the event data of the at least one event determined to be potentially relevant to the event of interest.

2. The method as claimed in claim 1 wherein the plurality of data sources includes at least one of power distribution network event data and related data.

3. The method as claimed in claim 1 wherein correlating the event data and the event of interest includes identifying event data that occurred during a time prior to and after the event of interest.

4. The method as claimed in claim 1 wherein the event data includes characteristics that match characteristics of the event of interest within predetermined thresholds.

5. The method as claimed in claim 1 further comprising assigning the event data a correlation value.

6. The method as claimed in claim 1 further comprising:

filtering the event data;

normalizing the event data; and

storing the event data in an event database.

7. The method as claimed in claim 6 wherein the event data is filtered to retrieve relevant data.

8. The method as claimed in claim 6 wherein the power distribution network event data is normalized to transform a plurality of data structure types to a single data structure type for the plurality of data sources.

9. A computer program product including a non-transitory computer readable medium storing instructions for causing a computer to implement a method for power distribution network correlation and analysis, the method comprising:

receiving event data of a plurality of events from a plurality of sources, wherein at least a portion of the event data is non-network data;

identifying, based at least in part on an analysis of the event data of the plurality of events, an event of interest and at least one event determined to be potentially related to the event of interest, wherein the event of interest and the at least one event determined to be potentially related to the event of interest are selected from the plurality of events, and wherein the at least one event determined to be potentially related to the event of interest occurred within a predetermined time period proximate to an occurrence of the event of interest;

retrieving, in a querying engine, event data of the event of interest and event data of the at least one event determined to be potentially related to the event of interest, wherein the event data of the event of interest and the event data of the at least one event determined to be potentially related to the event of interest are comprised in the received event data of the plurality of events;

correlating the event data of the event of interest and the event data of the at least one event determined to be potentially relevant to the event of interest to thereby correlate the event of interest and the at least one event determined to be potentially related to the event of interest; and

identifying one or more root causes of the event of interest based at least in part on analysis of the event data of the event of interest and the event data of the at least one event determined to be potentially relevant to the event of interest.

10. The computer program product as claimed in claim 9 wherein the plurality of data sources includes at least one of power distribution network event data and related data.

11. The computer program product as claimed in claim 9 wherein correlating the event data and the event of interest includes identifying event data that occurred during a time prior to and after the event of interest.

12. The computer program product as claimed in claim 9 wherein the event data includes characteristics that match characteristics of the event of interest within predetermined thresholds.

13. The computer program product as claimed in claim 9 wherein the method further comprises assigning the event data a correlation value.

14. The computer program product as claimed in claim 9 wherein the method further comprises:

filtering the event data;

normalizing the event data; and

storing the event data in an event database.

15. The computer program product as claimed in claim 14 wherein the event data is filtered to retrieve relevant data.

16. The computer program product as claimed in claim 14 wherein the power distribution network event data is normalized to transform a plurality of data structure types to a single data structure type for the plurality of data sources.

17. A system for power distribution network analysis, the system comprising:

an event database storing event data of a plurality of events from a plurality of filtered and normalized data sources, wherein the event data is filtered and normalized, and wherein at least a portion of the event data is non-network data;

a querying engine coupled to the event database configured to;

identify, based at least in part on an analysis of the event data of the plurality of events, an event of interest and at least one event determined to be potentially related to the event of interest, wherein the event of interest and the at least one event determined to be potentially related to the event of interest are selected from the plurality of events, and wherein the at least one event determined to be potentially related to the event of interest occurred within a predetermined time period proximate to an occurrence of the event of interest; and

retrieve event data of the event of interest and event data of the at least one event determined to be potentially related to the event of interest, wherein the event data of the event of interest and the event data of the at least one event determined to be potentially related to the event of interest are comprised in the received event data of the plurality of events;

a correlation engine coupled to the querying engine, and configured to correlate the event data of the event of interest and the event data of the at least one event determined to be potentially relevant to the event of interest to thereby correlate the event of interest and the at least one event determined to be potentially related to the event of interest;

and a root-cause analysis engine coupled to the correlation engine, and configured to discover patterns among the event of interest and the event data to identify one or more root-causes of the event of interest based at least in part on analysis of the event data of the event of interest and the event data of the at least one event determined to be potentially relevant to the event of interest.

18. The system as claimed in claim 17 wherein the plurality of data sources includes at least one of power distribution network event data and related data.

19. The system as claimed in claim 17 wherein the correlation engine is configured to identify event data that occurred during a time prior to and after the event of interest.

20. The system as claimed in claim 17 wherein the event data includes characteristics that match characteristics of the event of interest within predetermined thresholds.