Topology-Based Machine-Learning for Modeling Power-System Responses to Contingencies

This is the companion dataset to the presentation NREL/PR-6A20-77485, which was presented at the 2020 Joint Statistical Meeting on August 3, 2020. Developed for the machine-learning predictive modeling of power-system responses to disruptions, it contains results of power-system contingency analyses along with graph and topology measurements under each contingency scenario of the power system.
2 Data Resources
Name Size Type Resource Description History
partial-results-20200731.zip 82.81 MB Archive ZIP file containing the metadata, the power-system graph, and the results of the power-system simulations and graph/topology measurements.
full-results-20200829a.zip 199.41 MB Archive ZIP file containing the metadata, the power-system graph, and the results of the power-system simulations and graph/topology measurements.
Keywords
power system
graph theory
topological data analysis
simulation
machine learning
resilience
Submitted
•  Aug  • 01 2020
NREL
Brian W Bush
7202586728
Center 6A20
ORCID iD 0000-0003-2864-7028
Author Information
Brian Bush, Strategic Energy Analysis Center, ORCID iD: 0000-0003-2864-7028
Cite This Dataset
Bush, Brian. 2020. "Topology-Based Machine-Learning for Modeling Power-System Responses to Contingencies." NREL Data Catalog. Golden, CO: National Renewable Energy Laboratory. Last updated: September 16, 2022.
About This Dataset
146
NREL/PR-6A20-77485
Public
09/16/2022
Facilities
High Performance Computing Center (HPC)
Funding Organization
NREL Internal (LDRD, BD)
Research Areas
Computational Science
Energy Analysis
License
View License