Studying Power Outage Across United States and Predicting Future Restorations - EAGLE-I Explorer’s Solution to Challenge 7 for SMCDC2023

Project information

  • Paper:
    Fillers T., Maddox, J., Ologbonyo, J., and Talukdar, B. SMC 2023 Data Challenge: EAGLE-I Explorers Solution for Challenge 7. Smoky Mountains Computational Sciences and Engineering Conference (SMCDC2023).
  • Read the Paper
  • Paper in Publisher's Site
  • BibTeX: 
                          @inproceedings{inproceedings,
                        author = {Fillers, Thomas and Maddox, John and Ologbonyo, Joshua and Talukdar, Bilas},
                        year = {2023},
                        month = {10},
                        pages = {},                
                        title = {Studying Power Outage Across United States and Predicting Future Restorations - EAGLE-I Explorer’s Solution to Challenge 7 for SMCDC2023},
                        doi = {10.17605/OSF.IO/ZM48R}
                        }

Abstract

This paper investigates five different questions regarding power outage data from across the United States at the county level. This data was collected through the Environment for the Analysis of Geo-Located Energy Information (EAGLE-I) platform at Oak Ridge National Laboratory (ORNL). Studying the power outage trends of different geographical areas can prove beneficial for accurate future outage forecasting and restoration time prediction. Hence, these studies could be very useful to the emergency services to devise and improve power grid disruption plans. We perform a time-series analysis of the data sets to find restoration times and possible patterns, look for potential correlations between different data sets such as severe weather events, discuss methods to identify any abnormal power outage events, and predict both missing and future power outage data.