PQD classifier based on higher-order statistics and total harmonic distortion Jesús-Manuel González-Bueno, José-Carlos Palomares-Salas, Juan-José González-de-la-Rosa,Olivia Florencias-Oliveros, José-María Sierra-Fernández, Manuel-Jesús Espinosa-Gavira and Agustín Agüera-Pérez   2019/07/15

Abstract

Higher-Order Statistics (HOS) have been frequently applied in Power Quality Disturbance (PQD) analysis as a reliable tool for event detection. This paper outlines a technique based on mean, variance and zero-lag third and fourth cumulants – skewness and kurtosis – along with the Total
Harmonic Distortion (THD) index for PQD detection. These statistics are obtained in order to characterize a waveform by a feature vector. A two-layer feed-forward neural network is then
used to classify inputs (feature vectors) into a set of PQD categories. The impact of frame duration and number of hidden neurons is analyzed. The network is trained, validated and tested with synthetically-generated PQD waveforms obtained from parameter-controlled equations. As a first approach, five PQD categories are considered: sag, swell, interruption, impulsive transient and oscillatory transient. A promising overall classification rate of 99.7 % is achieved which allows future
analysis with more PQD categories and/or a noisy context.

Authors and affiliations

Jesús-Manuel González-Bueno, José-Carlos Palomares-Salas, Juan-José González-de-la-Rosa,Olivia Florencias-Oliveros, José-María Sierra-Fernández, Manuel-Jesús Espinosa-Gavira and Agustín Agüera-Pérez

University of Cádiz. Research Group PAIDI-TIC 168 – Computational Instrumentation and Industrial Electronics
Dept. of Automation Engineering, Electronics, Architecture and Computer Networks Engineering School of Algeciras (Spain)

Key words

Higher-Order Statistics (HOS); Total Harmonic Distortion (THD); Feed-Forward Neural Network; Power Quality
Disturbance (PQD).

References

[1] M. V. Ribeiro, C. A. G. Marques, C. A. Duque, A. S. Cerqueira, and J. L. R. Pereira, “Detection of Disturbances
in Voltage Signals for Power Quality Analysis Using HOS,” EURASIP Journal on Advances in Signal Processing, vol. 2007, no. 1, Dec. 2007.
[2] S. Khokhar, A. A. B. Mohd Zin, A. S. B. Mokhtar, and M. Pesaran, “A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances,” Renewable
and Sustainable Energy Reviews, vol. 51, pp. 1650–1663, Nov. 2015.
[3] J. Diego Silva Guedes, D. Diego Ferreira, B. Henrique Groenner Barbosa, C. Augusto Duque, and A. Santiago
Cerqueira, “Non-Intrusive Appliance Load Identification Based on Higher-Order Statistics,” IEEE Latin America
Transactions, vol. 13, no. 10, pp. 3343–3349, Oct. 2015.
[4] O. Florencias-Oliveros, J.-J. González-de-la-Rosa, A. Agüera-Pérez, and J. C. Palomares-Salas, “Discussion on
Reliability and Power Quality in the Smart Grid: a prosumer approach of a time scalable index,” Renewable Energy and Power Quality Journal, vol. 1, pp. 108–113, Apr. 2018.
[5] J. J. González de la Rosa, A. M. Muñoz, A. Gallego, R. Piotrkowski, and E. Castro, “Higher-order characterization
of power quality transients and their classification using competitive layers,” Measurement, vol. 42, no. 3, pp. 478–
484, Apr. 2009.
[6] Institute of Electrical and Electronics Engineers, IEEE recommended practice for monitoring electric power
quality. New York: Institute of Electrical and Electronics Engineers, 2009.
[7] A. Swami, “System Identification Using Cumulants,” Ph.D. dissertation, USC SIPI Report 140, Dep. Elec. Eng.-
Syst., Univ. Southern California, Los Angeles, CA, 1988.
[8] J. M. Mendel, “Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results
and some applications,” Proceedings of the IEEE, vol. 79, no. 3, pp. 278–305, Mar. 1991.
[9] A. Papoulis, Probability, random variables, and stochastic processes, 3rd ed. New York: McGraw-Hill, 1991.
[10] J. A. R. Fonollosa, “Sample cumulants of stationary processes: asymptotic results,” IEEE Transactions on
Signal Processing, vol. 43, no. 4, pp. 967–977, Apr. 1995.
[11] J. F. Kenney and E. S. Keeping, Mathematics of statistics, vol. 2, 2 vols. Van Nostrand company, 1947.
[12] S. Khokhar, A. A. M. Zin, A. S. Mokhtar, and N. Ismail, “MATLAB/Simulink based modeling and simulation of
power quality disturbances,” 2014, pp. 445–450.
[13] K. Manimala, K. Selvi, and R. Ahila, “Hybrid soft computing techniques for feature selection and parameter
optimization in power quality data mining,” Applied Soft Computing, vol. 11, no. 8, pp. 5485–5497, Dec. 2011.
[14] S. Khokhar, A. A. Mohd Zin, A. S. Mokhtar, and N. Zareen, “Automatic pattern recognition of single and multiple power quality disturbances,” Australian Journal of Electrical and Electronics Engineering, vol. 13, no. 1, pp. 43–53, Jan. 2016.
[15] A. M. Gaouda, S. H. Kanoun, M. M. A. Salama, and A. Y. Chikhani, “Pattern Recognition Applications for Power
System Disturbance Classification,” IEEE Power Engineering Review, vol. 22, no. 1, pp. 69–70, 2002.
[16] W. R. A. Ibrahim and M. M. Morcos, “Artificial Intelligence and Advanced Mathematical Tools for Power
Quality Applications: A Survey,” IEEE Transactions on Power Delivery, vol. 17, no. 2, p. 6, 2002.
[17] I. Monedero, C. Leon, J. Ropero, A. Garcia, J. M. Elena, and J. C. Montano, “Classification of Electrical
Disturbances in Real Time Using Neural Networks,” IEEE Transactions on Power Delivery, vol. 22, no. 3, pp. 1288–
1296, Jul. 2007.