Nonparametric Tree‐Based Predictive Modeling of Storm Outages on an Electric Distribution Network

This article compares two nonparametric tree‐based models, quantile regression forests (QRF) and Bayesian additive regression trees (BART), for predicting storm outages on an electric distribution network in Connecticut, USA. We evaluated point estimates and prediction intervals of outage prediction...

Full description

Saved in:
Bibliographic Details
Published inRisk analysis Vol. 37; no. 3; pp. 441 - 458
Main Authors He, Jichao, Wanik, David W., Hartman, Brian M., Anagnostou, Emmanouil N., Astitha, Marina, Frediani, Maria E. B.
Format Journal Article
LanguageEnglish
Published United States Blackwell Publishing Ltd 01.03.2017
Subjects
Bayesian additive regression trees
Bayesian analysis
Blackouts
critical infrastructure outage modeling
Distribution management
electric distribution network
Electric utilities
Estimates
Forecasting techniques
Intervals
Mathematical models
Networks
Outages
Predictions
quantile regression forests
Regression analysis
Risk assessment
States
Storms
Studies
weather hazards
United States > US
Connecticut
ANW, USA, Connecticut
electric distribution network
weather hazards
Bayesian additive regression trees
quantile regression forests
critical infrastructure outage modeling
Online AccessGet full text

Cover

More Information
Summary:This article compares two nonparametric tree‐based models, quantile regression forests (QRF) and Bayesian additive regression trees (BART), for predicting storm outages on an electric distribution network in Connecticut, USA. We evaluated point estimates and prediction intervals of outage predictions for both models using high‐resolution weather, infrastructure, and land use data for 89 storm events (including hurricanes, blizzards, and thunderstorms). We found that spatially BART predicted more accurate point estimates than QRF. However, QRF produced better prediction intervals for high spatial resolutions (2‐km grid cells and towns), while BART predictions aggregated to coarser resolutions (divisions and service territory) more effectively. We also found that the predictive accuracy was dependent on the season (e.g., tree‐leaf condition, storm characteristics), and that the predictions were most accurate for winter storms. Given the merits of each individual model, we suggest that BART and QRF be implemented together to show the complete picture of a storm's potential impact on the electric distribution network, which would allow for a utility to make better decisions about allocating prestorm resources.
Bibliography:In residency as a long‐term visitor at National Center for Atmospheric Research (NCAR), Boulder, CO, USA.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0272-4332
1539-6924
DOI:10.1111/risa.12652