Abstract

Generation of harmonics and the existence of waveform pollution in power system networks are important problems facing the power utilities. The increased use of nonlinear devices in industry has resulted in direct increase of harmonic distortion in the industrial power system in recent years. Interaction between loads and sources in a power distribution network is a complex process and often not possible to explain analytically without making assumptions. The determination of true harmonic current distortion of a load is further complicated by the fact that the supply voltage waveform at the point of common coupling (PCC) is rarely a pure sinusoid. This paper proposes a neural network based method to find a way of distinguishing between load contributed harmonics and supply harmonics, without disconnecting any load from the network. A neural network structure with memory is used to model the admittance of the nonlinear load. Once training is achieved, the neural network predicts the true harmonic current of the load if it could be supplied with a clean sine wave. The main advantage of this method is that only waveforms of voltages and currents have to be measured and is applicable for single phase as well as multiphase loads. This could be integrated into a commercially available power quality instrument or be fabricated as a standalone instrument that could be installed in substations of large customer loads, or used as a hand-held clip on instrument.

Department(s)

Electrical and Computer Engineering

Sponsor(s)

Duke Power Company
National Electric Energy Testing Research and Applications Center

Keywords and Phrases

Point of Common Coupling (PCC); Neural networks (Computer science)

International Standard Serial Number (ISSN)

0885-8993

Document Type

Article - Journal

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 2007 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jan 2007

Download

Full Text Link

Share

 
COinS