Page 507 - Decision Making Applications in Modern Power Systems

Pattern-recognition methods for decision-making Chapter | 17 467

chapter, it can be concluded that pattern-recognition-based functions provide
effective and, therefore, interesting alternatives to conventional protection
function or supplementary functions in conventional distance relays for solv-
ing different complex protection problems. Researches represent that the per-
formance of pattern-recognition-based functions can be considerably
improved by the combination of different preprocessing techniques rather
than the employment of only raw signals. Consequently, the generalization
capability of learned classifier or estimator models can increase. Recently,
the hardware implementation of pattern-recognition-based functions illus-
trates that these functions can be effectively employed in protection of trans-
mission line practically. However, to apply the functions to commercial
relays, more consideration is required. Recent advances in the hardware
implementation of ANN-based approaches make smart relay possible for the
future technology of relays. Moreover, an ANN can be implemented in a
reconfigurable orthogonal memory multiprocessor (REOMP) as a reconfigur-
able parallel computer architecture using FPGA. Rapid FPGA technology
enables the modular design concept based on the REOMP implementation in
a system-on-chip approach. Integration of pattern-recognition functions thus
develops a way toward the new generation of relays in smart protection
systems.

References
1. E. Micheli-Tzanakou, Supervised and Unsupervised Pattern Recognition: Feature
Extraction and Computational Intelligence, CRC Press, 1999.
2. R. Salat, S. Osowski, Accurate fault location in the power transmission line using support
vector machine approach, IEEE Trans. Power Syst. 19 (2) (2004) 979 986.
3. Z. Moravej, M. Pazoki, M. Khederzadeh, New smart fault locator in compensated line with
UPFC, Int. J. Electr. Power Energy Syst. 92 (2017) 125 135.
4. G. Benmouyal, Removal of DC-offset in current waveforms using digital mimic filtering,
IEEE Trans. Power Delivery 10 (2) (1995) 621 630.
5. A. Jamehbozorg, S. Mohammad Shahrtash, A decision-tree-based method for fault classifi-
cation in single-circuit transmission lines, IEEE Trans. Power Delivery 25 (4) (2010)
2190 2196.
6. A. Jamehbozorg, S.M. Shahrtash, A decision tree-based method for fault classification in
double-circuit transmission lines, IEEE Trans. Power Delivery 25 (4) (2010) 2184 2189.
7. M. Farshad, J. Sadeh, Accurate single-phase fault-location method for transmission lines
based on k-nearest neighbor algorithm using one-end voltage, IEEE Trans. Power Delivery
27 (4) (2012) 2360 2367.
8. P.F. Ribeiro, C.A. Duque, P.M. Ribeiro, A.S. Cerqueira, Power Systems Signal Processing
for Smart Grids, Wiley, 2013.
9. R.G. Stockwell, L. Mansinha, R.P. Lowe, Localization of the complex spectrum: the S
transform, IEEE Trans. Signal Process. 44 (4) (1996) 998 1001.
10. Z. Moravej, M. Khederzadeh, M. Pazoki, New combined method for fault detection, classi-
fication, and location in series-compensated transmission line, Electr. Power Compon. Syst.
40 (9) (2012) 1050 1071.