Effect of Lightning Features on Predicting Outages Related to Thunderstorms in Distribution Grids

Date

2025-01-07

Authors

Kezunovic, Mladen
Baembitov, Rashid
Saranovic, Daniel
Karmacharya , Abinash
Obradovic, Zoran

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

2974

Ending Page

Alternative Title

Abstract

Power outages in the distribution grid profoundly impact everyday human activity and economic welfare, as numerous infrastructures rely on uninterrupted power for sustained operation. Over the past decade, there has been a significant focus on using machine learning (ML) to predict outage state of risk (SoR) in both research and applications. One of the main causes of outages is weather conditions causing equipment failure due to wear and tear, as well as lightning strikes, in this paper. Therefore, we analyzed the consequences of selecting various weather-related ML model features on the outage SoR. We first show the outage SoR prediction results with and without considering lightning features, and then rank the SoR prediction performance based on various other weather features.

Description

Keywords

Monitoring, Control, and Protection, lightning, machine learning, outage prediction, state of risk, weather

Citation

Extent

10

Format

Geographic Location

Time Period

Related To

Proceedings of the 58th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.