Enhancement of power system data debugging using GSA-based data-mining technique

In this paper, a gap-statistic-algorithm (GSA)-based data-mining technique is applied to enhance the data debugging in power system operations. In the proposed approach, the GSA technique is embedded into a neural network frame in anticipation of improving the detection capability of bad data. Thanks to the clustering capability exhibited by GSA in which the number of clusters can be optimally determined, the proposed approach becomes highly effective to localize the group of abnormal data. This proposed approach has been tested through the data collected from different scenarios made on an IEEE 30-bus system and 118-bus systems. Test results reveal the feasibility of the method for the data diagnosis applications.

[1]  Sakti P. Ghosh.  Statistical Relational Databases: Normal Forms , 1991, IEEE Trans. Knowl. Data Eng..

[2]  George H. John,et al.  Stock Selection Using Rule Induction , 1996, IEEE Expert.

[3]  R. Balasubramanian,et al.  Bad Data Processing in Power System State Estimation by Direct Data Deletion and Hypothesis Tests , 1987 .

[4]  Johannes Gehrke,et al.  Mining Very Large Databases , 1999, Computer.

[5]  B Kovalerchuk,et al.  Consistent knowledge discovery in medical diagnosis. , 2000, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[6]  L. Wehenkel,et al.  Data mining , 1999 .

[7]  K. E. Bollinger,et al.  Applications of data mining for power systems , 1997, CCECE '97. Canadian Conference on Electrical and Computer Engineering. Engineering Innovation: Voyage of Discovery. Conference Proceedings.

[8]  Xindong Wu.  Fuzzy interpretation of discretized intervals , 1999, IEEE Trans. Fuzzy Syst..

[9]  H. Salehfar,et al.  A neural network preestimation filter for bad-data detection and identification in power system state estimation , 1995 .

[10]  Edwin P. D. Pednault,et al.  Probabilistic estimation-based data mining for discovering insurance risks , 1999, IEEE Intell. Syst..

[11]  Hans-Peter Kriegel,et al.  Visualization Techniques for Mining Large Databases: A Comparison , 1996, IEEE Trans. Knowl. Data Eng..

[12]  M.A. El-Sharkawi,et al.  Ancillary techniques for neural network applications , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[13]  Anthony Zaknich,et al.  Introduction to the modified probabilistic neural network for general signal processing applications , 1998, IEEE Trans. Signal Process..

[14]  Josiane Mothe,et al.  TetraFusion: information discovery on the Internet , 1999, IEEE Intell. Syst..

[15]  So Young Sohn,et al.  Meta Analysis of Classification Algorithms for Pattern Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  C. Apte,et al.  Data mining: an industrial research perspective , 1997 .

[17]  George N. Korres,et al.  A reduced model for bad data processing in state estimation , 1991 .

[18]  A. P. Alves da Silva,et al.  Data visualisation and identification of anomalies in power system state estimation using artificial neural networks , 1997 .

[19]  Boming Zhang,et al.  A recursive measurement error estimation identification method for bad data analysis in power system state estimation , 1991 .

[20]  Ilya W. Slutsker.  Bad Data Identification in Power System State Estimation Based on Measurement Compensation and Linear Residual Calculation , 1989, IEEE Power Engineering Review.