Discovering Decision Algorithm of Numerical Distance Relay Using Rough-Set-Theory-Based Data Mining

In this study a novel computational implementation technique of rough-set-theorybased data mining in analyzing the operation of a numerical distance protective relay, which is an integral part in the Knowledge Discovery in Database (KDD) process, is investigated. Fault diagnosis is one of the important components in power system operation. Whenever a circuit breaker opens due to a tripping instruction signal relayed by a protective relay, the relay tripping event including the disturbance which caused it must be analyzed by protection engineers to verify that the protection system operated correctly as preferred. However, due to the tremendous amount of raw data in the relay event report, it is an uphill task for a protection engineer to extract useful information for understanding the relay behavior governing the protection operation. Furthermore, in many recent works on power system event analysis, emphasis has been primarily aimed at “fault response analysis” using data from numerous IEDs rather than analysis on detailed validation and diagnosis of digital protective relay behavior using relay resident data. These protection operation analysis approaches have been geared towards protection system of a specific scale of power system such as a distribution system and a specific span of transmission system involving a collective set of IEDs. Most of these works focus on ‘system’ rather than ‘device’ in the protection operation analysis. With the application of rough set theory, the decision algorithm of a known numerical distance protective relay has been able to be

[1]  M. Kezunovic,et al.  Improving Real-time Fault Analysis and Validating Relay Operations to Prevent or Mitigate Cascading Blackouts , 2006, 2005/2006 IEEE/PES Transmission and Distribution Conference and Exhibition.

[2]  Mladen Kezunovic,et al.  An expert system for transmission substation event analysis , 1993 .

[3]  Gregory Piatetsky-Shapiro.  Data Mining and Knowledge Discovery: The Third Generation (Extended Abstract) , 1997, ISMIS.

[4]  A.A.M. Zin,et al.  COMTRADE-Based Fault Information System for TNB Substations , 2005, TENCON 2005 - 2005 IEEE Region 10 Conference.

[5]  J. Izykowski,et al.  Artificial Intelligent Application to Power System Protection , 2000 .

[6]  Abdul Halim Abu Bakar.  Disturbance analysis in TNB transmission system , 2001 .

[7]  John Mingers,et al.  Neural Networks, Decision Tree Induction and Discriminant Analysis: an Empirical Comparison , 1994 .

[8]  Desire L. Massart,et al.  Rough sets theory , 1999 .

[9]  Hong-Tzer Yang,et al.  A new neural networks approach to on-line fault section estimation using information of protective relays and circuit breakers , 1994 .

[10]  Ah-Hwee Tan,et al.  Cascade ARTMAP: integrating neural computation and symbolic knowledge processing , 1997, IEEE Trans. Neural Networks.

[11]  Te-sheng Li,et al.  A hybrid approach of rough set theory and genetic algorithm for fault diagnosis , 2005 .

[12]  Andrzej Skowron,et al.  Rough-Fuzzy Hybridization: A New Trend in Decision Making , 1999 .

[13]  M. Kezunovic,et al.  Fault analysis based on integration of digital relay and DFR data , 2005, IEEE Power Engineering Society General Meeting, 2005.

[14]  Huan Liu,et al.  Symbolic Representation of Neural Networks , 1996, Computer.

[15]  Mladen Kezunovic,et al.  Detect and classify faults using neural nets , 1996 .

[16]  M. Kezunovic,et al.  Verifying the Protection System Operation Using an Advanced Fault Analysis Tool Combined with the Event Tree Analysis , .

[17]  Hongjun Lu,et al.  Effective Data Mining Using Neural Networks , 1996, IEEE Trans. Knowl. Data Eng..

[18]  Peter Crossley,et al.  Substation event analysis using information from intelligent electronic devices , 2006 .

[19]  Renpu Li,et al.  Mining classification rules using rough sets and neural networks , 2004, Eur. J. Oper. Res..

[20]  A. P. Alves da Silva,et al.  Neural networks for fault location in substations , 1996 .

[21]  Wojciech Ziarko,et al.  Discovering attribute relationships, dependencies and rules by using rough sets , 1995, Proceedings of the Twenty-Eighth Annual Hawaii International Conference on System Sciences.

[22]  Mladen Kezunovic,et al.  AUTOMATED FAULT ANALYSIS USING INTELLIGENT TECHNIQUES AND SYNCHRONIZED SAMPLING , 2001 .

[23]  Zdzislaw Pawlak,et al.  Rough sets and intelligent data analysis , 2002, Inf. Sci..

[24]  Zdzislaw Pawlak,et al.  Some Issues on Rough Sets , 2004, Trans. Rough Sets.

[25]  Toshinori Munakata,et al.  Rule extraction from expert heuristics: A comparative study of rough sets with neural networks and ID3 , 2002, Eur. J. Oper. Res..

[26]  M. Kezunovic,et al.  Automated analysis of digital relay data based on expert system , 2005, 2005 IEEE Russia Power Tech.

[27]  S. K. Michael Wong,et al.  Rough Sets: Probabilistic versus Deterministic Approach , 1988, Int. J. Man Mach. Stud..

[28]  Z. Pawlak.  Rough set approach to knowledge-based decision support , 1997 .

[29]  Jerzy W. Grzymala-Busse,et al.  Rough Sets , 1995, Commun. ACM.

[30]  Andrzej Skowron,et al.  The Discernibility Matrices and Functions in Information Systems , 1992, Intelligent Decision Support.

[31]  M. T. Schilling,et al.  Fault location in electrical power systems using intelligent systems techniques , 2001 .

[32]  Janusz Zalewski,et al.  Rough sets: Theoretical aspects of reasoning about data , 1996 .

[33]  M. Kezunovic,et al.  NEW AUTOMATED FAULT ANALYSIS APPROACHES USING INTELLIGENT SYSTEM TECHNOLOGIES , 2001 .

[34]  Michael Y. Hu,et al.  An experimental evaluation of neural networks for classification , 1993, Comput. Oper. Res..

[35]  M. Negnevitsky,et al.  Neural networks approach to online identification of multiple failures of protection systems , 2005, IEEE Transactions on Power Delivery.