Bad data analysis in power system measurement estimation using complex artificial neural network based on the extended complex Kalman filter

Chien Hung Huang, Chien-Hsing Lee, Kuang Rong Shih, Yaw Juen Wang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper proposes a method for bad data analysis in power system measurement estimation using complex artificial neural network (CANN) based on the extended complex Kalman filter (ECKF). The proposed algorithm is better in noise immunity since the link weighting in the CANN can be automatically adjusted with trained data through the ECKF. Moreover, the CANN is quite suitable for complex training data such as complex power in a power system since its input and output performs a nonlinear mapping. Four systems including a 6-bus system, the IEEE 30-bus system, IEEE 118-bus system, and a practical system are used as examples to verify the feasibility of the ECKF-CANN approach. Results show the proposed algorithm has increased sensitivity in identifying gross measurement errors with respect to the standard ANN.

Original languageEnglish
Pages (from-to)1082-1100
Number of pages19
JournalEuropean Transactions on Electrical Power
Volume20
Issue number8
DOIs
Publication statusPublished - 2010 Nov 1

Fingerprint

Electric power system measurement
Kalman filters
Power System
Kalman Filter
Artificial Neural Network
Data analysis
Neural networks
Measurement errors
Nonlinear Mapping
Immunity
Gross
Measurement Error
Weighting
Verify

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

@article{6f8c8880d0ac442a84f168ccf307498d,
title = "Bad data analysis in power system measurement estimation using complex artificial neural network based on the extended complex Kalman filter",
abstract = "This paper proposes a method for bad data analysis in power system measurement estimation using complex artificial neural network (CANN) based on the extended complex Kalman filter (ECKF). The proposed algorithm is better in noise immunity since the link weighting in the CANN can be automatically adjusted with trained data through the ECKF. Moreover, the CANN is quite suitable for complex training data such as complex power in a power system since its input and output performs a nonlinear mapping. Four systems including a 6-bus system, the IEEE 30-bus system, IEEE 118-bus system, and a practical system are used as examples to verify the feasibility of the ECKF-CANN approach. Results show the proposed algorithm has increased sensitivity in identifying gross measurement errors with respect to the standard ANN.",
author = "Huang, {Chien Hung} and Chien-Hsing Lee and Shih, {Kuang Rong} and Wang, {Yaw Juen}",
year = "2010",
month = "11",
day = "1",
doi = "10.1002/etep.386",
language = "English",
volume = "20",
pages = "1082--1100",
journal = "International Transactions on Electrical Energy Systems",
issn = "1430-144X",
publisher = "John Wiley and Sons Ltd",
number = "8",

}

Bad data analysis in power system measurement estimation using complex artificial neural network based on the extended complex Kalman filter. / Huang, Chien Hung; Lee, Chien-Hsing; Shih, Kuang Rong; Wang, Yaw Juen.

In: European Transactions on Electrical Power, Vol. 20, No. 8, 01.11.2010, p. 1082-1100.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Bad data analysis in power system measurement estimation using complex artificial neural network based on the extended complex Kalman filter

AU - Huang, Chien Hung

AU - Lee, Chien-Hsing

AU - Shih, Kuang Rong

AU - Wang, Yaw Juen

PY - 2010/11/1

Y1 - 2010/11/1

N2 - This paper proposes a method for bad data analysis in power system measurement estimation using complex artificial neural network (CANN) based on the extended complex Kalman filter (ECKF). The proposed algorithm is better in noise immunity since the link weighting in the CANN can be automatically adjusted with trained data through the ECKF. Moreover, the CANN is quite suitable for complex training data such as complex power in a power system since its input and output performs a nonlinear mapping. Four systems including a 6-bus system, the IEEE 30-bus system, IEEE 118-bus system, and a practical system are used as examples to verify the feasibility of the ECKF-CANN approach. Results show the proposed algorithm has increased sensitivity in identifying gross measurement errors with respect to the standard ANN.

AB - This paper proposes a method for bad data analysis in power system measurement estimation using complex artificial neural network (CANN) based on the extended complex Kalman filter (ECKF). The proposed algorithm is better in noise immunity since the link weighting in the CANN can be automatically adjusted with trained data through the ECKF. Moreover, the CANN is quite suitable for complex training data such as complex power in a power system since its input and output performs a nonlinear mapping. Four systems including a 6-bus system, the IEEE 30-bus system, IEEE 118-bus system, and a practical system are used as examples to verify the feasibility of the ECKF-CANN approach. Results show the proposed algorithm has increased sensitivity in identifying gross measurement errors with respect to the standard ANN.

UR - http://www.scopus.com/inward/record.url?scp=78649657353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649657353&partnerID=8YFLogxK

U2 - 10.1002/etep.386

DO - 10.1002/etep.386

M3 - Article

VL - 20

SP - 1082

EP - 1100

JO - International Transactions on Electrical Energy Systems

JF - International Transactions on Electrical Energy Systems

SN - 1430-144X

IS - 8

ER -