Support-vector machine and naïve bayes based diagnostic analytic of harmonic source identification

Abstract

A harmonic source diagnostic analytic is a vital to identify the location and type of harmonic source in the power system. This paper introduces a comparison of machine learning (ML) algorithm which are support vector machine (SVM) and naïve bayes (NB). Voltage and current features are used as the input for ML are extracted from time-frequency representation (TFR) of S-transform. Several unique cases of harmonic source location are considered, whereas harmonic voltage and harmonic current source type-load are used in the diagnosing process. To identify the best ML, the performance measurement of the propose method including accuracy, specificity, sensitivity, and F-measure are calculated. The adequacy of the proposed methodology is tested and verified on IEEE 4-bust test feeder and each ML algorithm is executed for 10 times due to different partitions and to prevent any overfitting result.