Electrical and Computer Engineering ETDs

Publication Date

Fall 12-12-2020

Abstract

Modern electric power systems, power system protections and controls have experienced a significant change, thanks to the introduction of new technologies, such as microprocessors, GPS, communication, etc. These technologies brought an increased amount of measured-data and information flow on power grids. Adaptive protection systems have been introduced to increase the reliability, selectivity, and sensitivity of the traditional protection systems. An adaptive protection system highly relies on the communication system infrastructure to identify the latest status of power grid (e.g., circuit topology or generation level of distributed energy resources). However, when the communication links to some of the equipment are outaged due to physical damages or cyberattacks, the adaptive protection system may lose its awareness over the status of the system. Therefore, it is of paramount value to estimate the circuit status using the available healthy communicated data. This thesis proposes the use of machine learning algorithms to estimate circuit topology when the communication links to the tie breakers are outaged. Doing so, the adaptive protection system can identify the correct protection settings corresponding to the estimated circuit topology. The effectiveness of proposed approach is verified on a test system.

Keywords

Adaptive Protection System, Circuit Topology, Machine Learning, Support Vector Machin

Sponsors

Sandia National Laboratories

Document Type

Thesis

Language

English

Degree Name

Electrical Engineering

Level of Degree

Masters

Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Dr. Ali Bidram

Second Committee Member

Dr. Matthew J. Reno

Third Committee Member

Dr. Manel Martinez-Ramon

Fourth Committee Member

Dr. Jane Lehr

Download

Share

COinS