Classification of direct load control curves for performance evaluation

Hong-Tzer Yang, Shih Chieh Chen, Win Ni Tsai

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In evaluating the performance of direct load control (DLC) programs, an essential task is to classify the DLC curves into either the one complying with the program or not. This paper presents an efficient approach to clustering the DLC curves through a structure of self-organizing maps (SOM). Aiming at selecting significant features of DLC curves, methods of nonlinear principal component analysis (NLPCA) and periodic analysis are proposed for feature extraction. The dual multilayer neural networks (DMNN) model is employed in the proposed NLPCA method. In the periodic analysis method, the periodic characteristics of the DLC curves are investigated. In the SOM, Davies-Bouldin (DB) indexes and a k-means algorithm decide the best number of clusters to be classified. Through the proposed methods, the DLC curves are thus divided into the two categories by the SOM: DLC complying and DLC noncomplying loads. Results obtained from the comparison of six different approaches show that the clusters obtained from the proposed approach exhibit lowest degrees of misclassification for the practical data on Taiwan Power Company (TPC) DLC programs.

Original languageEnglish
Pages (from-to)811-817
Number of pages7
JournalIEEE Transactions on Power Systems
Volume19
Issue number2
DOIs
Publication statusPublished - 2004 May 1

Fingerprint

Self organizing maps
Principal component analysis
Multilayer neural networks
Feature extraction
Industry

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Yang, Hong-Tzer ; Chen, Shih Chieh ; Tsai, Win Ni. / Classification of direct load control curves for performance evaluation. In: IEEE Transactions on Power Systems. 2004 ; Vol. 19, No. 2. pp. 811-817.
@article{591e2608de4f40cd9fdf3a5d3fd99262,
title = "Classification of direct load control curves for performance evaluation",
abstract = "In evaluating the performance of direct load control (DLC) programs, an essential task is to classify the DLC curves into either the one complying with the program or not. This paper presents an efficient approach to clustering the DLC curves through a structure of self-organizing maps (SOM). Aiming at selecting significant features of DLC curves, methods of nonlinear principal component analysis (NLPCA) and periodic analysis are proposed for feature extraction. The dual multilayer neural networks (DMNN) model is employed in the proposed NLPCA method. In the periodic analysis method, the periodic characteristics of the DLC curves are investigated. In the SOM, Davies-Bouldin (DB) indexes and a k-means algorithm decide the best number of clusters to be classified. Through the proposed methods, the DLC curves are thus divided into the two categories by the SOM: DLC complying and DLC noncomplying loads. Results obtained from the comparison of six different approaches show that the clusters obtained from the proposed approach exhibit lowest degrees of misclassification for the practical data on Taiwan Power Company (TPC) DLC programs.",
author = "Hong-Tzer Yang and Chen, {Shih Chieh} and Tsai, {Win Ni}",
year = "2004",
month = "5",
day = "1",
doi = "10.1109/TPWRS.2004.825884",
language = "English",
volume = "19",
pages = "811--817",
journal = "IEEE Transactions on Power Systems",
issn = "0885-8950",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Classification of direct load control curves for performance evaluation. / Yang, Hong-Tzer; Chen, Shih Chieh; Tsai, Win Ni.

In: IEEE Transactions on Power Systems, Vol. 19, No. 2, 01.05.2004, p. 811-817.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification of direct load control curves for performance evaluation

AU - Yang, Hong-Tzer

AU - Chen, Shih Chieh

AU - Tsai, Win Ni

PY - 2004/5/1

Y1 - 2004/5/1

N2 - In evaluating the performance of direct load control (DLC) programs, an essential task is to classify the DLC curves into either the one complying with the program or not. This paper presents an efficient approach to clustering the DLC curves through a structure of self-organizing maps (SOM). Aiming at selecting significant features of DLC curves, methods of nonlinear principal component analysis (NLPCA) and periodic analysis are proposed for feature extraction. The dual multilayer neural networks (DMNN) model is employed in the proposed NLPCA method. In the periodic analysis method, the periodic characteristics of the DLC curves are investigated. In the SOM, Davies-Bouldin (DB) indexes and a k-means algorithm decide the best number of clusters to be classified. Through the proposed methods, the DLC curves are thus divided into the two categories by the SOM: DLC complying and DLC noncomplying loads. Results obtained from the comparison of six different approaches show that the clusters obtained from the proposed approach exhibit lowest degrees of misclassification for the practical data on Taiwan Power Company (TPC) DLC programs.

AB - In evaluating the performance of direct load control (DLC) programs, an essential task is to classify the DLC curves into either the one complying with the program or not. This paper presents an efficient approach to clustering the DLC curves through a structure of self-organizing maps (SOM). Aiming at selecting significant features of DLC curves, methods of nonlinear principal component analysis (NLPCA) and periodic analysis are proposed for feature extraction. The dual multilayer neural networks (DMNN) model is employed in the proposed NLPCA method. In the periodic analysis method, the periodic characteristics of the DLC curves are investigated. In the SOM, Davies-Bouldin (DB) indexes and a k-means algorithm decide the best number of clusters to be classified. Through the proposed methods, the DLC curves are thus divided into the two categories by the SOM: DLC complying and DLC noncomplying loads. Results obtained from the comparison of six different approaches show that the clusters obtained from the proposed approach exhibit lowest degrees of misclassification for the practical data on Taiwan Power Company (TPC) DLC programs.

UR - http://www.scopus.com/inward/record.url?scp=2542613720&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2542613720&partnerID=8YFLogxK

U2 - 10.1109/TPWRS.2004.825884

DO - 10.1109/TPWRS.2004.825884

M3 - Article

VL - 19

SP - 811

EP - 817

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

SN - 0885-8950

IS - 2

ER -