IP Library › Granted Patent US 12,355,239
Granted Patent B2
US 12,355,239 · App. 17/381,863 · Granted Jul 8, 2025

Spatial power outage estimation for natural hazards leveraging optimal synthetic power networks

Inventors: Seth David Guikema (Ann Arbor, MI); Chengwei Zhai (Sunnyvale, CA); Anna White (Ann Arbor, MI); Thomas Ying-Jeh Chen (Silver Spring, MD)
Assignee: THE REGENTS OF THE UNIVERSITY OF MICHIGAN
H02J3/001G06N20/00G06Q50/06H02J2203/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,355,239
App. No.
17/381,863
Granted
Jul 8, 2025
Kind
B2
Abstract

The following relates generally to calculating estimated power outages during a natural disaster event. In this regard, some embodiments create a synthetic network of a power infrastructure of a geographic area by: determining a location of a power substation; determining a location of a customer; determining a location of a power line linking the power substation to the customer; and determining if the power line is overhead or underground. Some embodiments then use the created synthetic network to simulate an event to calculate the estimated power outages during the event.

Claims (57)

1. A computer system for calculating estimated power outages, the computer system comprising one or more processors configured to:

create a synthetic network of a power infrastructure of a geographic area by:

determining a location of a power substation;

determining a location of a customer;

determining a power line: (i) linking the determined location of the power substation to the determined location of the customer, and (ii) based on an assumption that the power line is located along a road; and

determining whether the determined power line is overhead or underground by: (i) retrieving at least one characteristic of a building, wherein the building is (a) associated with the customer, and (b) corresponds to the road, and (ii) determining whether the determined power line is overhead or underground based on the retrieved at least one characteristic of the building; and

simulate an event to calculate the estimated power outages during the event including setting a location of the power line to a location along the road, wherein the calculation of the estimated power outages is based on the determination of whether the power line is overhead or underground.

2. The computer system of claim 1 , wherein the one or more processors are further configured to make the determination of if the power line is overhead or underground by training a machine learning algorithm by using a year that a building was built as an input to the machine learning algorithm.

3. The computer system of claim 1 , wherein the one or more processors are further configured to make the determination of whether the power line is overhead or underground by training a random forest algorithm by using a year that a building was built as an input to the random forest algorithm.

4. The computer system of claim 1 , wherein the power line is a first power line, and wherein the one or more processors are further configured to make the determination of whether the power line is overhead or underground by training a machine learning algorithm by using a type of a nearest power line to the first power line as a response variable.

5. The computer system of claim 1 , wherein the one or more processors are further configured to make the determination of whether the power line is overhead or underground by training a machine learning algorithm by using at least one of:

a value of a building;

a finished lot size;

parcel lot size; or

a tax assessment.

6. The computer system of claim 1 , wherein the event includes at least one of:

an earthquake;

a windstorm;

a flood; or

a hurricane.

7. The computer system of claim 1 , wherein the one or more processors are further configured to simulate the event to calculate the estimated power outages during the event by using a fragility function.

8. The computer system of claim 1 , wherein the one or more processors are further configured to make the determination of whether the power line is overhead or underground by training a machine learning algorithm by using all of:

a value of a building;

a finished lot size;

parcel lot size; and

a tax assessment.

9. The computer system of claim 1 , wherein the at least one characteristic includes all of:

a value of the building;

a finished lot size corresponding to the building;

parcel lot size corresponding to the building; and

a tax assessment of the building.

10. A computer-implemented method for calculating estimated power outages, the method comprising:

creating a synthetic network of a power infrastructure of a geographic area by:

determining a location of a power substation;

determining a location of a customer;

determining a power line: (i) linking the determined location of the power substation to the determined location of the customer, and (ii) based on an assumption that the power line is located along a road; and

determining that the determined power line is underground by: (i) retrieving at least one characteristic of a building, wherein the building is (a) associated with the customer, and (b) corresponds to the road, and (ii) determining that the determined power line underground based on the retrieved at least one characteristic of the building; and

simulating an event to calculate the estimated power outages during the event including setting a location of the power line to a location along the road, wherein the calculation of the estimated power outages is based on the determination that the power line is underground.

11. The computer-implemented method of claim 10 , wherein event is a high wind event, and wherein the determination that the power line is underground decreases a probability of an estimated power outage of the estimated power outages.

12. The computer-implemented method of claim 10 , wherein the determination that the power line is underground includes training a machine learning algorithm by using a year that a building was built as an input to the machine learning algorithm.

13. The computer-implemented method of claim 10 , wherein the determination that the power line is underground includes training a random forest algorithm by using a year that a building was built as an input to the random forest algorithm.

14. The computer-implemented method of claim 10 , wherein the power line is a first power line, and wherein the determination that the power line is underground includes training a machine learning algorithm by using a type of a nearest power line to the first power line as a response variable.

15. A computer system for calculating estimated power outages, the computer system comprising one or more processors configured to:

create a synthetic network of a power infrastructure of a geographic area by creating a plurality of clusters, wherein each cluster of the plurality of clusters includes a substation and a plurality of buildings, and wherein each cluster is created based on a network distance from a building of the plurality of buildings of the cluster to the substation of the cluster; and

simulate an event to calculate the estimated power outages during the event including setting a location of a power line to a location along a road, wherein the calculation of the estimated power outages is based on the created synthetic network; and

wherein the one or more processors are further configured to:

create the synthetic network of the power infrastructure by, for at least one cluster of the plurality of clusters, determining:

a power line linking a building of the plurality of buildings of the at least one cluster to the substation of the cluster; and

if the power line is overhead or underground by: (i) retrieving at least one characteristic of a building, wherein the building is (a) associated with a customer, and (b) corresponds to the road, and (ii) determining if the determined power line is overhead or underground based on the retrieved at least one characteristic of the building; and

wherein the calculation of the estimated power outages is further based on the determination of if the power line is overhead or underground.

16. The computer system of claim 15 , wherein the one or more processors are further configured to create the synthetic network by, for each cluster of the plurality of clusters, apply one of:

a Steiner Tree (ST);

a K-mean clustering Steiner Tree (ST-K-mean); or

a shortest path (SP).

17. The computer system of claim 15 , wherein the one or more processors are further configured to make the determination of if the power line is overhead or underground by training a machine learning algorithm by using a year that a building was built as an input to the machine learning algorithm.

18. The computer system of claim 15 , wherein the one or more processors are further configured to make the determination of if the power line is overhead or underground by training a random forest algorithm by using a year that a building was built as an input to the random forest algorithm.

19. The computer system of claim 15 , wherein the power line is a first power line, and wherein the one or more processors are further configured to make the determination of if the power line is overhead or underground by training a machine learning algorithm by using a type of a nearest power line to the first power line as a response variable.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 10, 2025
From: GUIKEMA, SETH DAVID; ZHAI, CHENGWEI; WHITE, ANNA; CHEN, THOMAS YING-JEH
To: THE REGENTS OF THE UNIVERSITY OF MICHIGAN
Reel/Frame 070800/0120 →
Continuity (2)
Provisional Application 63056478 · Jul 24, 2020
Related Publication 20220029418A1 · Jan 27, 2022
References Cited (57)
US 7046841B1 · Dow · 2006 [cited by examiner]
US 7739138B2 · Chauhan · 2010 [cited by examiner]
US 8589201B2 · Nielsen · 2013 [cited by examiner]
US 9297723B1 · Hofmann · 2016 [cited by examiner]
US 9360588B2 · Young · 2016 [cited by examiner]
US 10444806B2 · Brockman · 2019 [cited by examiner]
US 11144835B2 · Anagnostou · 2021 [cited by examiner]
US 11263538B1 · Minarovic · 2022 [cited by examiner]
US 11709870B2 · Worster · 2023 [cited by examiner]
US 11954907B2 · Gupta · 2024 [cited by examiner]
US 20120022713A1 · Deaver, Sr. · 2012 [cited by examiner]
US 20120127161A1 · Wallbom · 2012 [cited by examiner]
US 20130096976A1 · Alpert · 2013 [cited by examiner]
US 20140257913A1 · Ball · 2014 [cited by examiner]
US 20150123664A1 · Olsson · 2015 [cited by examiner]
US 20180247001A1 · Liu · 2018 [cited by examiner]
US 20190019398A1 · Hender · 2019 [cited by examiner]
US 20190138995A1 · Currin · 2019 [cited by examiner]
US 20200097618A1 · Agouridis · 2020 [cited by examiner]
US 20200379824A1 · Chongfuangprinya · 2020 [cited by examiner]
US 20210248693A1 · Riland · 2021 [cited by examiner]
US 20210373063A1 · Gundel · 2021 [cited by examiner]
US 20220138467A1 · Eastman · 2022 [cited by examiner]
US 20220375219A1 · Gupta · 2022 [cited by examiner]
US 20230186621A1 · Gupta · 2023 [cited by examiner]
JP 5088628B2 · 2012 [cited by examiner]
WO WO2018013148A1 · 2018 [cited by applicant]
JP-5088628-B2 (Dec. 2012) machine translation. [cited by examiner]
Second Written Opinion for International Application No. PCT/US2021/042459, mailing date Jun. 14, 2022. [cited by applicant]
Birchfield et al., Grid Structural Characteristics as Validation Criteria for Synthetic Networks. IEEE Transactions on Power Systems, 32(4):3258-3265 (2017). [cited by applicant]
Birchfield et al., Statistical Considerations in the Creation of Realistic Synthetic Power Grids for Geomagnetic Disturbance Studies. IEEE Transactions on Power Systems, 32(2):1502-1510 (2017). [cited by applicant]
Campbell, Weather-Related Power Outages and Electric System Resiliency, Congressional Research Service Report for Congress, 18 pp. (2012). [cited by applicant]
Darestani et al., Multi-dimensional wind fragility functions for wood utility poles, Engineering Structures, 183:937-948 (2019). [cited by applicant]
Davidson et al., Electric Power Distribution System Performance in Carolina Hurricanes. Natural Hazards Review, 4(1):36-45 (2003). [cited by applicant]
Guikema et al., Hybrid data mining-regression for infrastructure risk assessment based on zero-inflated data, Reliability Engineering and System Safety, 99:178-182 (2012). [cited by applicant]
Guikema et al., Predicting hurricane power outages to support storm response planning, 2:1364-73 (Nov. 2014). [cited by applicant]
Guikema et al., Prestorm Estimation of Hurricane Damage to Electric Power Distribution Systems. Risk Analysis, 30(12):1744-1752 (2010). [cited by applicant]
Guikema et al., Statistical models of the effects of tree trimming on power system outages. IEEE Transactions on Power Delivery, 21(3), 1549-1557 (2006). [cited by applicant]
Han et al., Estimating the Spatial Distribution of Power Outages during Hurricanes in the Gulf Coast Region, Reliability Engineering & System Safety, vol. 94, No. 2, pp. 199-210 (2009). [cited by applicant]
International Application No. PCT/US2021/042459, International Search Report and Written Opinion, mailed Nov. 5, 2021. [cited by applicant]
Kezunovic et al., Predicting Spatiotemporal Impacts of Weather on Power Systems Using Big Data Science, Data Science and Big Data: An Environment of Computational Intelligence, pp. 265-299 (2017). [cited by applicant]
Kircher et al., HAZUS Earthquake Loss Estimation Methods, Natural Hazards Review, 7(2): 45-59 (2006). [cited by applicant]
Liu et al., Statistical forecasting of electric power restoration times in hurricanes and ice storms. IEEE Transactions on Power Systems, 22(4):2270-9 (2007). [cited by applicant]
Miranda et al., Genetic algorithms in optimal multistage distribution network planning, IEEE Transactions on Power Systems, 9(4):1927-33 (1994). [cited by applicant]
Nateghi et al., Power Outage Estimation for Tropical Cyclones: Improved Accuracy with Simpler Models, Risk Analysis, 34(6):1069-78 (2014). [cited by applicant]
Nine of the Worst Power Outages in United States History. Retrieved from Electric Choice, Downloaded from the Internet at: <<https://www.electricchoice.com/blog/worst-power-outages-in-united-states-history/>>, Eisenbach… [cited by applicant]
Pahwa et al., Abruptness of cascade failures in power grids, Scientific Reports, 4, Article No. 3694 (2014). [cited by applicant]
Salman et al., Age-dependent fragility and life-cycle cost analysis of wood and steel power distribution poles subjected to hurricanes. Structure and Infrastructure Engineering, 12(8): 890-903 (2016). [cited by applicant]
Schultz et al., A random growth model for power grids and other spatially embedded infrastructure networks, The European Physical Journal Special Topics, 223(12):2593-610 (2014). [cited by applicant]
Shafieezadeh et al., Age-dependent fragility models of utility wood poles in power distribution networks against extreme wind hazards, IEEE Transactions on Power Delivery, 29(1):131-9 (2014). [cited by applicant]
Shashaani et al., Multi-Stage Prediction for Zero-Inflated Hurricane Induced Power Outages, IEEE Access, 6:62432-49 (2018). [cited by applicant]
Soltan et al., Generation of synthetic spatially embedded power grid networks. IEEE Power and Energy Society General Meeting, published 2015. [cited by applicant]
Valenzuela et al., Planning of a Resilient Underground Distribution Network Using Georeferenced Data. Energies, 12(4): 644 (2019). [cited by applicant]
Vanzi, Seismic reliability of electric power networks: Methodology and application, Structural Safety, 18(4):311-327 (1996). [cited by applicant]
Vickery et al., HAZUS-MH Hurricane Model Methodology. II: Damage and Loss Estimation. Natural Hazards Review, 7(2), 94-103 (2006). [cited by applicant]
Yuan et al., Robust Optimization-Based Resilient Distribution Network Planning Against Natural Disasters, IEEE Transactions on Smart Grid, 7(6):2817-26 (2016). [cited by applicant]
Winkler et al., Performance assessment of topologically diverse power systems subjected to hurricane events, Reliability Engineering & System Safety, 95(4):323-36 (2010). [cited by applicant]