Classifying Dynamics Events Using Neural Network and Wavelets for Current Power Systems

DOI

10.2991/icecee-15.2015.44How to use a DOI?

Keywords

Dynamics Events; Power System; Neural Network; Wavelet Analysis

Abstract

In this paper, we propose a novel methodology that classify the power system dynamics events patterns using neural network and wavelet through studying one single variable at a network bus. DWT allows the identification of components of the LFEO (low-frequency electromechanical oscillations), their frequencies, and magnitudes. Following the determination of the energy components' share of the studied signal using Parseval’s theory and discrete wavelet transform, we get the input data. A total of five classes of disturbances, three different wavelet functions, and two different variables are tested. The experimental results emostrates that our methodology could classify different power disturbance types efficiently.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yingli Shu
PY  - 2015/06
DA  - 2015/06
TI  - Classifying Dynamics Events Using Neural Network and Wavelets for Current Power Systems
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 195
EP  - 198
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.44
DO  - 10.2991/icecee-15.2015.44
ID  - Shu2015/06
ER  -