HÜSEYİN ERİŞTİ, VEDAT TÜMEN, ÖZAL YILDIRIM, BELKIS ERİŞTİ, YAKUP DEMİR

Automatic classification of harmonic data using $k$-means and least square support vector machine

In this paper, an effective classification approach to classify harmonic data has been proposed. In the proposed classifier approach, harmonic data obtained through a 3-phase system have been classified by using $k$-means and least square support vector machine (LS-SVM) models. In order to obtain class details regarding harmonic data, a $k$-means clustering algorithm has been applied to these data first. The training of the LS-SVM model has been realized with the class details obtained through the $k$-means algorithm. To increase the efficiency of the LS-SVM model, the regularization and kernel parameters of this model have been determined with a grid search method and the training phase has been realized. Backpropagation neural network and J48 decision tree classifiers have been applied to the same data and results have been obtained for the purpose of comparing the performance of the LS-SVM model. The real data obtained from the output of distribution system have been used to assess the performance of the proposed classifier system. The obtained results and comparisons suggest that the proposed classifier system approach is quite efficient at classifying harmonic data.

Anahtar Kelimeler:

Harmonic, measurement, data mining, LS-SVM, $k$-means

Automatic classification of harmonic data using $k$-means and least square support vector machine

Keywords:

Harmonic, measurement, data mining, LS-SVM, $k$-means,

PDF

___

McGranagahn M. Trends in power quality monitoring. IEEE Power Eng Rev J 2001; 21: 3–9.
Yang J, Yu C, Liu C. A new method for power signal harmonic analysis. IEEE T Power Deliver 2005; 20: 1235–1239.
Gu IYH, Bollen MHJ. Estimating interharmonics by using sliding-window ESPRIT. IEEE T Power Deliver 2008; 23: 13–23.
¨Ozg¨onenel O, Terzi ¨UK, Khan A. A hybrid approach for power quality. Turk J Electr Eng Co 2012; 20: 854–869.
Eri¸sti H, Demir Y. The feature selection based power quality event classification using wavelet transform and logistic model tree. Przegl¸ad Elektrotechniczny 2012: 43–48.
Joorabian M, Mortazavi SS, Khayyami AA. Harmonic estimation in a power system using a novel hybrid least squares-Adaline algorithm. Electr Power Syst Res 2009; 79: 107–116.
Sachin K, Singh SN. Fast harmonic estimation of stationary and time-varying signals using EA-AWNN. IEEE T Instr Meas 2013; 62: 335–343.
K¨ose N, Salor ¨O, Leblebicio˘glu K. Interharmonics analysis of power signals with fundamental frequency deviation using Kalman filtering. Electr Power Syst Res 2010; 80: 1145–1153.
Asheibi A, Stirling D, Sutanto D. Analyzing harmonic monitoring data using supervised and unsupervised learning. IEEE T Power Deliver 2009; 24: 293–301.
Asheibi A, Stirling D, Sutanto D. Determination of the optimal number of clusters in harmonic data classification. In: Harmonics and Quality of Power ICHQP; 28 September–1 October 2008; Wollongong, Australia. New York, NY, USA: IEEE. pp. 1–6.
Catterson VM, Bahadoorsingh S, Rudd S, McArthur SDJ, Rowland SM. Identifying harmonic attributes from online partial discharge data. IEEE T Power Deliver 2011; 26: 1811–1819.
Negnevitsky M, Ringrose M. Monitoring multiple harmonic sources in power systems using neural networks. In: 2005 IEEE Power Tech; 27–30 June 2005; St. Petersburg, Russia. New York, NY, USA: IEEE. pp. 1–6.
Kantardzic, M. Data Mining: Concepts, Models, Methods, and Algorithms . Chichester, UK: John Wiley & Sons, 20 Han J, Kamber M, Pei J. Data Mining Concepts and Techniques. Waltham, MA, USA: Morgan Kaufmann, 2006.
MacQueen JB. Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Symposium on Math, Statistics, and Probability. Berkeley, CA, USA: University of California Press, 1967. pp. 281–297.
Kalyani S, Swarup KS. Particle swarm optimization based k -means clustering approach for security assessment in power systems. Expert Syst Appl 2011; 38: 10839–10846.
Zalik KR. An eﬃcient k-means clustering algorithm. Pattern Recogn Lett 2008; 29: 1385–1391.
Suykens JAK, Vandewalle J. Least squares support vector machine classifiers. Neural Process Lett 1999; 9: 293–300.
IEC. IEC Standard for Electromagnetic Compatibility (EMC)—Part 4-30: Testing and Measurement Techniques— Power Quality Measurement Methods, IEC 61000-4-30. Geneva, Switzerland: IEC, 2008.
Quinlan JR. C4.5: Programs for Machine Learning. San Mateo, CA, USA: Morgan Kaufmann Publishers, 1993.