Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events

Climate change is increasing the occurrence of extreme weather events, such as intense windstorms, with a trend expected to worsen due to global warming. The growing intensity and frequency of these events are causing a significant number of failures in power distribution grids. However, understandi...

Full description

Saved in:
Bibliographic Details
Main Authors: Altan Unlu, Malaquias Peña
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Wind
Subjects:
Online Access:https://www.mdpi.com/2674-032X/4/4/17
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102356486258688
author Altan Unlu
Malaquias Peña
author_facet Altan Unlu
Malaquias Peña
author_sort Altan Unlu
collection DOAJ
description Climate change is increasing the occurrence of extreme weather events, such as intense windstorms, with a trend expected to worsen due to global warming. The growing intensity and frequency of these events are causing a significant number of failures in power distribution grids. However, understanding the nature of extreme wind events and predicting their impact on distribution grids can help and prevent these issues, potentially mitigating their adverse effects. This study analyzes a structured method to predict distribution grid disruptions caused by extreme wind events. The method utilizes Machine Learning (ML) models, including K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Decision Trees (DTs), Gradient Boosting Machine (GBM), Gaussian Process (GP), Deep Neural Network (DNN), and Ensemble Learning which combines RF, SVM and GP to analyze synthetic failure data and predict power grid outages. The study utilized meteorological information, physical fragility curves, and scenario generation for distribution systems. The approach is validated by using five-fold cross-validation on the dataset, demonstrating its effectiveness in enhancing predictive capabilities against extreme wind events. Experimental results showed that the Ensemble Learning, GP, and SVM models outperformed other predictive models in the binary classification task of identifying failures or non-failures, achieving the highest performance metrics.
format Article
id doaj-art-71cf829a6a39496286e9faf36ef8500c
institution Kabale University
issn 2674-032X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Wind
spelling doaj-art-71cf829a6a39496286e9faf36ef8500c2024-12-27T14:59:41ZengMDPI AGWind2674-032X2024-11-014434236210.3390/wind4040017Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological EventsAltan Unlu0Malaquias Peña1Department of Electrical & Computer Engineering, University of Connecticut, Storrs, CT 06268, USADepartment of Civil & Environmental Engineering, University of Connecticut, Storrs, CT 06268, USAClimate change is increasing the occurrence of extreme weather events, such as intense windstorms, with a trend expected to worsen due to global warming. The growing intensity and frequency of these events are causing a significant number of failures in power distribution grids. However, understanding the nature of extreme wind events and predicting their impact on distribution grids can help and prevent these issues, potentially mitigating their adverse effects. This study analyzes a structured method to predict distribution grid disruptions caused by extreme wind events. The method utilizes Machine Learning (ML) models, including K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM), Decision Trees (DTs), Gradient Boosting Machine (GBM), Gaussian Process (GP), Deep Neural Network (DNN), and Ensemble Learning which combines RF, SVM and GP to analyze synthetic failure data and predict power grid outages. The study utilized meteorological information, physical fragility curves, and scenario generation for distribution systems. The approach is validated by using five-fold cross-validation on the dataset, demonstrating its effectiveness in enhancing predictive capabilities against extreme wind events. Experimental results showed that the Ensemble Learning, GP, and SVM models outperformed other predictive models in the binary classification task of identifying failures or non-failures, achieving the highest performance metrics.https://www.mdpi.com/2674-032X/4/4/17extreme weather eventspower distribution gridsmachine learningline outage predictiongrid resilienceensemble learning
spellingShingle Altan Unlu
Malaquias Peña
Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events
Wind
extreme weather events
power distribution grids
machine learning
line outage prediction
grid resilience
ensemble learning
title Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events
title_full Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events
title_fullStr Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events
title_full_unstemmed Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events
title_short Assessment of Line Outage Prediction Using Ensemble Learning and Gaussian Processes During Extreme Meteorological Events
title_sort assessment of line outage prediction using ensemble learning and gaussian processes during extreme meteorological events
topic extreme weather events
power distribution grids
machine learning
line outage prediction
grid resilience
ensemble learning
url https://www.mdpi.com/2674-032X/4/4/17
work_keys_str_mv AT altanunlu assessmentoflineoutagepredictionusingensemblelearningandgaussianprocessesduringextrememeteorologicalevents
AT malaquiaspena assessmentoflineoutagepredictionusingensemblelearningandgaussianprocessesduringextrememeteorologicalevents