Date of Award

2019-01-01

Degree Name

Doctor of Philosophy

Department

Engineering

Advisor(s)

Patricia A. Nava

Abstract

Warming trends and increasing temperatures have been observed and reported by federal agencies, such as the National Oceanic and Atmospheric Administration (NOAA). Extreme-weather events, especially hurricanes, tornadoes and winter storms, are among the highly devastating natural disasters responsible for massive and prolonged power outages in Electrical Transmission and Distribution Systems (ETDS). Moreover, the failure rate probability of any system component under extreme-weather tends to increase in the impacted geographic area. This Dissertation proposes an Artificial Intelligence (AI) Decision Support System that can predict damage in the ETDS and allow operators to mitigate disastrous extreme weather events. The document reports the results of the exploration of a novel method to integrate two main domains: the critical operation of the ETDS under natural disaster conditions; and data integration based on the sequence of steps in a Knowledge Discovery Framework (KDF). Machine Learning and Deep Learning approaches, including the spectrum of data mining, are incorporated in the KDF and used to perform the estimation, regression, and classification tasks. By means of two scenarios, a winter storm and a major hurricane, the proof of concept of the consolidation of the two domains, AI and ETDS, is demonstrated. The results of the methods are compared, as well as techniques and accuracy of the algorithms. Discussion includes descriptive statistics of the data analysis, conducted to understand each data set, and how they are related to each task. The results reveal a powerful tool, that incorporates disparate ideas and data, and increases the accuracy of predictions and classifications of extreme weather damage in the hypothetical cases presented. This is of importance to the operator decision support in order to solve problems in the area of critical operation of the Transmission and Distribution systems during extreme-weather events.

Language

en

Provenance

Received from ProQuest

File Size

177 pages

File Format

application/pdf

Rights Holder

Rossana Villegas

Share

COinS