UTILITY RESOURCE ASSET MANAGEMENT SYSTEM

• US 20160343093A1
• Filed: 07/22/2016
• Published: 11/24/2016
• Est. Priority Date: 01/24/2014
• Status: Active Grant

• Current Assignee: Telvent USA LLC (Schneider Electric SE)
• Original Assignee: Telvent USA LLC (Schneider Electric SE)
• Inventors: RILAND, Chad, MURALIDHARAN, Shylesh, LEICK, Don, WAGNER, Robert, PETRECCA, Danny, HIGGINS, Scott
• Granted Patent: US 11,017,485 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G06Q 50/06 Energy or water supply

Abstract

The UTILITY RESOURCE ASSET MANAGEMENT SYSTEM APPARATUSES, METHODS AND SYSTEMS (“URAMS”) transform weather, terrain, and utility asset parameter data via URAMS components into damage predictions with confidence metrics, alerts, and asset allocation and response plans.

Claims

1. A processor-implemented method for utility threat modeling and resource allocation, comprising:

receiving fixed-location utility asset data for a given region;

receiving geographic and ecological data for the given region;

receiving historical weather data for the given region;

receiving historical fixed-location utility asset functionality data for the given region;

generating, via a processor, aggregate utility asset polygon data, the generation of the aggregate utility asset polygon data including;

identifying unique feeders, and for each feeder, selecting specified conductors in a specified feeder segment, determining an aggregate polygon buffer around conductor features, selecting network connected assets, selecting non-network connected assets based on the polygon buffer, updating polygon attributes with related asset information from the network connected assets and non-network connected assets to generate utility asset polygon data, and reducing the number of vertices and polygon complexity to provide aggregate utility asset polygon data;

generating via a processor a predictive fixed-location utility outage determination based on the fixed-location utility asset data, the geographic and ecological data, the historical weather data, historical fixed-location utility asset functionality data, and aggregate utility asset polygon data;

receiving current weather data for the region;

determining a future fixed-location utility asset functionality prediction result using the predictive fixed-location utility outage determination based on the current weather data as input to the predictive fixed-location utility outage determination in order to generate a prediction output;

outputting the predicted current utility asset functionality result to a user via an electronic interface;

receiving real-time fixed-location utility asset functionality data for the region;

dynamically altering the predictive fixed-location utility outage determination based on the real-time fixed-location utility asset functionality data;

determining a second current utility asset functionality prediction result with the dynamically-altered predictive fixed-location utility outage determination; and

outputting the second current utility asset functionality result to the user via an electronic interface.

2. The processor-implemented method of claim 1, further comprising:

receiving mobile utility asset data for a given region; and

determining mobile asset allocation parameters based on at least one utility asset functionality result.

3. The processor-implemented method of claim 2, wherein the mobile utility asset data comprises at least one of mobile asset type, asset number, asset current location, and asset status.

4. The processor-implemented method of claim 1, wherein the fixed-location utility asset data comprises at least one of asset type, asset number, asset geo-location, asset status, and asset attributes.

5. The processor-implemented method of claim 1, wherein the ecological data comprises at least one of soil moisture information, vegetation information, vegetation management practices.

6. The processor-implemented method of claim 1, wherein the historical weather data comprises historical storm data including at least one of storm type and storm attributes.

7. The processor-implemented method of claim 1, wherein the historical weather data comprises historic natural disaster data, and the historic natural disaster data includes at least one of hurricane data, tornado data, earthquake data, and flood data.

8. The processor-implemented method of claim 1, wherein the historical fixed-location utility asset functionality data comprises data about utility asset losses and malfunctions.

9. The processor-implemented method of claim 1, wherein generating the predictive fixed-location utility outage determination is generated via machine learning algorithm with online learning to train the predictive fixed-location utility outage determination using the fixed-location utility asset data, the geographic and ecological data, and the historical weather and historical fixed-location utility asset functionality data as inputs.

10. The processor-implemented method of claim 1, wherein the current weather data comprises data regarding current storms and/or natural disasters, and the data regarding current storms and/or natural disasters includes at least one of intensity, current wind speeds, lightning strikes, turbulence, current rainfall, current temperature, current pressure, and/or current humidity.

11. A processor-implemented method for providing a predictive utility asset damage and response interface, comprising:

receiving fixed-location utility asset data for a given area;

receiving historical fixed-location utility asset damage data associated with the fixed-location utility asset data;

receiving geographic data and ecological data for the given area;

receiving historical weather data for the given area;

accessing at least one damage model;

defining a utility asset map based on the fixed-location utility asset data, the geographic data, and the ecological data;

receiving current weather data for the area;

generating via a processor a predictive utility asset damage forecast using the at least one damage model and based on the utility asset map, the historical fixed-location utility asset damage data, the historical weather data, and the current weather data;

determining confidence metric data for the utility asset damage forecast;

integrating the confidence metric data with the predictive utility asset damage forecast to define an initial predictive utility asset damage forecast with integrated confidence metric data; and

outputting the predictive utility asset damage forecast with integrated confidence metric data as a dynamically scalable utility asset map overlay for presentation to at least one user via an electronic interface.

12. The method of claim 11, wherein determining confidence metric data for the utility asset damage forecast is based on iterative processing of the at least one damage model.

13. The method of claim 11, further comprising:

receiving real-time fixed-location utility asset damage data for the area;

updating the initial utility asset damage forecast with integrated confidence metric data based on the real-time fixed-location utility asset damage data; and

outputting an updated dynamically scalable utility asset map overlay.

14. The method of claim 11, wherein defining a utility asset map includes:

generating aggregate utility asset polygon data, the generation of the aggregate utility asset polygon data comprising;

identifying unique feeders, and for each feeder, selecting specified conductors in a specified feeder segment, determining an aggregate polygon buffer around conductor features, selecting network connected assets, selecting non-network connected assets based on the polygon buffer, updating polygon attributes with related asset information from the network connected assets and non-network connected assets to generate utility asset polygon data, and reducing the number of vertices and polygon complexity to provide aggregate utility asset polygon data.

15. The processor-implemented method of claim 11, further comprising:

receiving simulation scenario data, the simulation scenario data including a plurality of scenario parameter values; and

updating the initial utility asset damage forecast with integrated confidence metric data based on the plurality of scenario parameter values.

16. The processor-implemented method of claim 15, further comprising

outputting an updated dynamically scalable utility asset map overlay based on the plurality of scenario parameter values, wherein the updated dynamically scalable utility asset map overlay illustrates differences in the predictive utility asset damage forecast and confidence metric data as variables changes over time.

17. The processor-implemented method of claim 15, further comprising

outputting an updated dynamically scalable utility asset map overlay based on the plurality of scenario parameter values, wherein the updated dynamically scalable utility asset map overlay illustrates differences between the initial predictive utility asset damage forecast with integrated confidence metric data and the updated dynamically scalable utility asset map overlay based on the plurality of scenario parameter values.

18. The processor-implemented method of claim 17, further comprising:

generating a proposed utility crew deployment plan based on man-hour estimates for storm response effort based on differences between the initial predictive utility asset damage forecast with integrated confidence metric data and the updated dynamically scalable utility asset map overlay.

19. The processor-implemented method of claim 17, further comprising:

accessing a current utility crew deployment plan;

determining an updated proposed utility crew deployment plan based on the plurality of scenario parameter values the current utility crew deployment plan.

20. The processor-implemented method of claim 18, further comprising:

accessing key archival comparison metrics associated with data used to generate the dynamically scalable utility asset map overlay;

using the key archival comparison metrics to identify at least one historically similar damage event crew deployment, and return to service characteristics from a historical performance database; and

determining a performance score for the current event as compared to the historical event.