Fault classification and reconfiguration of distribution systems using equivalent capacity margin method

Abstract

This paper investigates the capability of support vector machines (SVM) for prediction of fault classification and the use of the concept of equivalent capacity margin (ECM) for restoration of the power system. The SVM, as a novel type of machine learning based on statistical learning theory, achieves good generalization ability by adopting a structural risk minimization (SRM) induction principle aimed at minimizing a bound on the generalization error of a model rather than the minimization of the error on the training data only. Here, the SVM has been used as a classification. The inputs of the SVM model are power and voltage values. An equation has been developed for the prediction of the fault in the power system based on the developed SVM model. The next steps of this paper are the restoration and reconfiguration by using the ECM concept, the development of a code, and the testing of the results with various load outages, which have been executed for a 12 load system.

Keywords

support vector machines (SVM) / structural risk minimization (SRM) / equivalent capacity margin (ECM) / restoration / fault classification

References

[1] IEEE Committee. Power system restoration—A task force report. IEEE Transactions on Power Systems, 2001, PWRS-2(2): 271-277

[2] de Mello F P, Westcott J C. Steam plant startup and control in system restoration. IEEE Transactions on Power Systems, 1994, 9(1): 93-101

[3] IEEE Committee. Special considerations in power system restoration. IEEE Transactions on Power Systems, 1992, 7(4): 1419-1427

[4] Nagata T, Hatakeyama S, Yasuoka M, Sasaki H. An efficient method for power distribution system restoration based on mathematical programming and operation strategy. In: Proceedings of International Conference on Power System Technology, 2000, 3: 1545-1550

[5] Morelato A L, Monticelli A J. Heuristic search approach to distribution system restoration. IEEE Transactions on Power Delivery, 1989, 4(4): 2235-2241

[6] Ockwell G L. Implementation of network reconfiguration for Taiwan power company. In: Proceedings of IEEE PES General Meeting. Norcross, GA, USA, 2003

[7] Staszesky D M, Craig D, Befus C. Advanced feeder automation is here. IEEE Power Energy Magazine, 2005, 3(5): 56-63

[8] Fan J Y, Zhang X L. Feeder automation within the scope of substation automation. In: Proceedings of Power System Conference and Exposition. Atlanta, USA, 2006

[9] Susheela Devi V, Anandalingam G. Optimal restoration of power supply in large distribution systems in developing countries. IEEE Transactions on Power Delivery, 1995, 10(1): 430-438

[10] Wu J S, Tomsovic K L, Chen C S. A heuristic search approach to feeder switching operations for overload, faults, unbalanced flow and maintenance. IEEE Transactions on Power Delivery, 1991, 6(4): 1579-1586

[11] Taylor T, Lubkeman D. Implementation of heuristic search strategies for distribution feeder reconfiguration. IEEE Transactions on Power Delivery, 1990, 5(1): 239-246

[12] Moon Y H, Cho B H, Park H, Ryu H M, Ha B N, Lim S I. Fault restoration algorithm using fast tracing technique based on the tree-structured database for the distribution automation system. In: Proceedings of IEEE PES Summer Meeting. Garden Grove, USA, 2000, 411-415

[13] Liu C, Lee S J, Venkata S S. An expert system operation aid for restoration and loss reduction of distribution systems. IEEE Transactions on Power Systems, 1988, 3(2): 619-626

[14] Huang C M. Multi-objective service restoration of distribution systems using fuzzy cause-effect networks. IEEE Transactions on Power Systems, 2003, 18(2): 867-874

[15] Hsiao Y T, Chien C Y. Enhancement of restoration service in distribution systems using a combination fuzzy-GA method. IEEE Transactions on Power Systems, 2000, 15(4): 1394-1400

[16] Ke Y L. Distribution feeder reconfiguration for load balancing and service restoration by using g-nets inference mechanism. IEEE Transactions on Power Delivery, 2004, 19(3): 1426-1433

[17] Wu J S. A petri-net algorithm for multiple contingencies of distribution system operation. IEEE Transactions on Power Systems, 1998, 13(3): 1164-1171

[18] Zhou Q, Shirmohammadi D, Liu W E. Distribution feeder reconfiguration for service restoration and load balancing. IEEE Transactions on Power Systems, 1997, 12(2): 724-729

[19] Yang F, Li Z, Donde V, Wang Z Y, Stoupis J. Graph theory-based feeder automation logic for low-end controller application. In: Proceedings of Power & Energy Society General Meeting. Raleigh, USA, 2009, 1-7

[20] Kothari D P, Nagrath I J. Modern power system analysis. 2004, http://tocs.ulb.tu-darmstadt.de/210460784.pdf

Acknowledgements

This paper was supported by the management of VIT University.

Appendix A

Switch	Max capacity/amp	Current flowing/amp	Switch status
R1	800	743	Closed
R2	800	729	Closed
R3	800	718	Closed
R4	800	550	Closed
R5	800	535	Closed
R6	800	0	Open
R7	800	70	Closed
R8	800	82	Closed
R9	800	0	Open
R10	800	105	Closed
R11	800	0	Open
R12	800	121	Closed
R13	800	0	Open
R14	800	140	Closed
R15	800	155	Closed
R16	800	0	Open
R17	800	170	Closed

Appendix B (Training data)

0.058333	0.045833	0.358333	0.0625	1
1	1	-1	1	1
0.291667	0.4375	0.504167	0.583333	0.645833
1	1	1	1	1

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg