Advanced methods of signal processing for Power Quality assessment Álvaro Jiménez Montero, Agustín Agüera Pérez, Juan José González de la Rosa, José Carlos Palomares Salas, José María Sierra Fernandez and Olivia Florencias Oliveros   2017/04/25

Abstrac

The aim of this work is by using artificial neural networks (ANNs) compare six regression algorithms supported by 14 power-quality features, based on higher-order statistics (HOS). In addition, we have combined time and frequency domain estimators to deal with non-stationary measurement sequences; the final target is to implement the system in a smart grid to guarantee compatibility between all the equipment connected. The main results were based on spectral kurtosis measurements, which easily adapt to the impulsive nature of the power quality events. Through these results we have verified that the developed technique is capable of offering interesting results at classifying power quality (PQ) disturbance.
We can conclude that using radial basis networks, generalized regression and multilayer perceptron, we have obtained the best results mainly due to the non-linear nature of data.

Authors and affiliations

Álvaro Jiménez Montero(1,2), Agustín Agüera Pérez(1,2), Juan José González de la Rosa(1,2), José Carlos Palomares Salas(1,2), José María Sierra Fernandez(1,2) and Olivia Florencias Oliveros(1,2)
1. Department of Automation Engineering, Electronics and Computer Architecture, Cadiz University. Algeciras-Cádiz (Spain)
2. Research Group PAIDI-TIC-168: Computational Instrumentation and Industrial Electronics (ICEI), Algeciras-Cádiz, (Spain)

Key word

Artificial neural networks (ANN), Power Quality (PQ), High-order statistics (HOS), Spectral kurtosis, Smart Grids (SG).

References

[1] MHJ Bollen, S Bahramirad, A Khodaei, in Proceedings o the 2014 IEEE 16th International Conference on Harmonics and Quality of Power (ICHQP). Is there a place for power quality in the smart grid? (University Politehnica of Bucharest Romania, 2014), pp. 713–717 2.
[2] Y Xiao, Communication and networking in smart grids. (CRC Press, Broken Sound Parkway NW, Suite 300, 2012)
[3] WK Reder, IEEE smart grid. Part 2: a grand vision for smart grid. Technical report. IEEE (2014). http://smartgrid.ieee.org/education
[4] MHJ Bollen, IY-H Gu, PGV Axelberg, E Styvaktakis, Classification of underlying causes of power quality disturbances: deterministic versus statistical methods. EURASIP J. Adv. Signal Process. 2007(1), 1–17 (2007)
[5] YH Gu, MHJ Bollen, Time-frequency and time-scale domain analysis of voltage disturbances. IEEE Trans. Power Deliv. 15(4), 1279–1283 (2000)
[6] MV Ribeiro, CAG Marques, CA Duque, AS Cerqueira, JLR Pereira, Detection of disturbances in voltage signals for power quality analysis using HOS. EURASIP J. Adv. Signal Process. 2007(1), 1–13 (2007)
[7] MV Ribeiro, JLR Pereira, Classification of single and multiple disturbances in electric signals. EURASIP J. Adv. Signal Process. 2007(1), 1–18 (2007)
[8] A Agüera-Pérez, JC Palomares-Salas, JJG de la Rosa, JM Sierra-Fernández, D Ayora-Sedeño, A Moreno-Muñoz, Characterization of electrical sags and swells using higher-order statistical estimators. Measurement. 44(Issue 8), 1453–1460 (2011)
[9] ON Gerek, DG Ece, Power-quality event analysis using higher order cumulants and quadratic classifiers. IEEE Trans. Power Deliv. 21(2), 883–889 (2006)
[10] DG Ece, ON Gerek, Power quality event detection using joint 2D wavelet subspaces. IEEE Trans. Instrumentation Meas. 53(4), 1040–1046 (2004)
[11] S Santoso, WM Grady, EJ Powers, J Lamoree, SC Bhatt, Characterization of distribution power quality events with fourier and wavelet transforms. IEEE Trans. Power Deliv. 15(1), 247–254 (2000)
[12] JJG de la Rosa, JM Sierra-Fernández, A Agüera-Pérez, JC Palomares-Salas, A Moreno-Muñoz, An application of the spectral kurtosis to characterize power quality events. Electrical Power Energy Syst. 49, 386–398 (2013)
[13] JJG de la Rosa, JM Sierra-Fernández, A Agüera-Pérez, JC Palomares-Salas,A Jiménez-Montero, A Moreno-Muñoz, in Proceedings on the IEEE International Workshop on the Applied Measurements for Power Systems (AMPS), vol. 1. Power quality events’ measurement criteria based in higher-order statistics: towards new measurement indices (IEEE Aachen, Germany, 2013), pp. 73–79
[14] JJG de la Rosa, A Agüera-Pérez, JC Palomares-Salas, JM Sierra-Fernández, A Moreno-Muñoz, A novel virtual instrument for power quality surveillance based in higher-order statistics and case-based reasoning. Measurement. 45(7), 1824–1835 (2012)
[15] JC Palomares-Salas, JJG de la Rosa, A Agüera-Pérez, A Moreno-Muñoz, Intelligent methods for characterization of electrical power quality signals using higher order statistical features. Przeglad Elektrotechniczny. 2012(8), 236–243 (2012)
[16] DD Ferreira, CAG Marques, JM de Seixas, AS Cerqueira, MV Ribeiro, CA Duque, Exploiting Higher-Order Statistics Information for Power Quality Monitoring. (InTech Open Science, 2011). http://intechopen.com
[17] S Haykin, Neural Networks. (Englewood Cliffs, NJ, 1994)
[18] J Sola, J Sevilla, Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Transa. Nuclear Sci. 44(3), 1464–1468 (1997)