ROBUSTNESS OF MACHINE LEARNING FOR POWER SYSTEMS
Loading...
Authors
Kozak, Elana P.
Subjects
machine learning
robustness
neural network
power grid
robustness
neural network
power grid
Advisors
Kang, Wei
Martinsen, Thor
Date of Issue
2022-06
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The applications of machine learning are broad and useful for a variety of industry and military objectives, but are the current methods robust? Robustness requires more than accuracy in ideal conditions; it means the system is resistant to perturbations in the data, both from natural and adversarial causes. This research aims to analyze the robustness of neural networks used for power-grid fault classifications. We focus on data generated from simulations of the classical 9-bus model; however, these methods and results can be extended to more complex microgrids, such as those found on naval ships, submarines, and bases. First, we measure the effects of random and adversarial noise on the testing data and compare three network types. Then we test different structures by varying the number of nodes and layers. Finally, we test whether adding noise to the training data can improve robustness. Before machine learning methods are adopted on submarines, we must first understand their weaknesses and potential for error. This research provides the foundation for how to test robustness, where neural networks are at risk from random or adversarial noise, and how to modify networks to improve their robustness.
Type
Thesis
Description
Series/Report No
NPS Outstanding Theses and Dissertations
Department
Applied Mathematics (MA)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release. Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.