Knowledge discovery in database from substation for decision support

Intelligent electronic devices (IEDs) installed at the bay level in the substation are capable of providing certain control functions to the process level as well as store the useful information regarding the events occurring there. The amount of operational data collected by IEDs is generally beyond immediate requirements and far more than the human capability to analyse and interpret the information. The information stored needs to be fetched beforehand and presented to the users who can make best use of it for several other applications like control & protection, maintenance, planning and expansion of the power system. There is a need to reduce the database presented to the operator to analyse the particular fault situation and take decisions. Thus, there is need of the knowledge discovery system to extract important facts from such information or database so as to optimize the system for more efficient operation. The technique of knowledge extraction enhances the functionality of substation automation. In this paper an attempt has been made to extract useful information from the database collected from a 132/11kv distribution network and provide a decision support tool to enhance substation automation (SA) functionality of the system.

[1]  K. Boži,et al.  Core searching on rough sets , 2001, Proceedings of the 23rd International Conference on Information Technology Interfaces, 2001. ITI 2001..

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

[3]  P. Crossley,et al.  Modeling a substation in a distribution network: real time data generation for knowledge extraction , 2002, IEEE Power Engineering Society Summer Meeting,.

[4]  C.L. Hor,et al.  Analysis of substation data for knowledge extraction , 2005, IEEE Power Engineering Society General Meeting, 2005.

[5]  W.W.Y. Ng,et al.  Rule Induction from Numerical Data Based on Rough Sets Theory , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[6]  V.K. Chandna,et al.  Design, development, and commissioning of a supervisory control and data acquisition (SCADA) laboratory for research and training , 2004, IEEE Transactions on Power Systems.

[7]  Peter Crossley,et al.  Relay models for protection studies , 2003, 2003 IEEE Bologna Power Tech Conference Proceedings,.

[8]  P.A. Crossley,et al.  Building Knowledge for Substation-Based Decision Support Using Rough Sets , 2007, IEEE Transactions on Power Delivery.

[9]  Aleksander Øhrn,et al.  Discernibility and Rough Sets in Medicine: Tools and Applications , 2000 .

[10]  P.A. Crossley,et al.  Unsupervised event extraction within substations using rough classification , 2006, IEEE Transactions on Power Delivery.

[11]  Aleksander Øhrn ROSETTA Technical Reference Manual , 2001 .

[12]  J. D. McDonald,et al.  Substation automation. IED integration and availability of information , 2003 .

[13]  Chen-Fu Chien,et al.  Rough set theory for data mining for fault diagnosis on distribution feeder , 2004 .