Linear discriminate analysis and k-nearest neighbor based diagnostic analytic of harmonic source identification

The diagnostic analytic of harmonic source is crucial research due to identify and diagnose the in power system. This paper presents a comparison machine learning (ML) algorithm known as linear discriminate analysis (LDA) k-nearest neighbor (KNN) identifying diagnosing sources. Voltage current features that estimated from time-frequency representation (TFR) S-transform are used input for ML. Several unique cases location considered, whereas voltage (HV) (HC) type-load process. To best ML, each ML executed 10 times prevent any overfitting result performance criteria measured consist accuracy, precision, geometric mean, specificity, sensitivity, F measure calculated.