2019/11/11 by Sambit Dash, Dash, Sambit, Umamani Subudhi +1
Engineering · #Energy Load and Power Forecasting #FOS: Electrical engineering #Power Quality and Harmonics #Power Transformer Diagnostics and Insulation #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.04661
openalex publication_date 2019/11/11 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this paper a technique for detection of multiple power quality (PQ) events\nis illustrated. An algorithm based on wavelet transform and Random Forest based\nclassifier is proposed in this paper. The developed technique is implemented on\n11 different power quality events consisting of single stage power quality\nevents such as sag, swell, flicker, interruption and multi stage power quality\nevents such as harmonics combined with sag, swell, flicker, interruption. PQ\nevents are simulated in MATLAB using standard IEEE-1159 standard. Significant\nfeatures of PQ events are extracted using wavelet transform and used to train\nrandom forest based classifier. The efficiency of Random Forest Based\nclassifier is compared with other widely used machine learning algorithms such\nas K-Nearest Neighbour (KNN) and Support Vector Machine (SVM). From confusion\nmatrix of different algorithms it is concluded that Random Forest shows\nsuperior classification accuracy as compared to SVM and KNN.\n