Machine Learning Based Power Quality Disturbance Classification Under Varying Fundamental Frequency Conditions for Islanding of a Microgrid
Abstract: The integration of renewable energy sources into modern power systems is increasing in a rapid manner. With their integration into the grid and many other power electronics devices, the rise in Power Quality Disturbances (PQDs) is posing as a major issue in improving the performance of smart grids and microgrid systems. Due to the intermittency of renewable energy sources, the fundamental frequency of power systems fluctuate, stemming different PQDs. In this work, we present a comparative analysis of four different machine learning classification algorithms, namely Support Vector Machine (SVM), k-Nearest Neighbours (KNN), Random Forest (RF), and Naive Bayes (NB), in classifying different types of single-stage and multiple-stage PQDs. We generated a dataset consisting of 29 types of PQDs, while taking into consideration the variation of fundamental frequency. We note that variation of fundamental frequency can significantly affect the classification accuracy of the machine learning models. We introduced different levels of noise (20dB to 40dB) to the PQD data to mimic real-life scenarios. We used the Linear Discriminant Analysis (LDA), which is a supervised learning technique, for dimensionality reduction and feature extraction. Our results show that the classification accuracy decreases as the noise level is increased gradually, and that a decrease in the classification accuracy is possible when the variation of the fundamental frequency is taken into account.
Submission Length: Regular submission (no more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=9EEIqgbcrb
Changes Since Last Submission: The template was not followed 100% in the previous submission, and therefore, the submission was desk-rejected by the Editor-in-Chief. We followed the template accurately in this submission.
Assigned Action Editor: ~Roman_Garnett1
Submission Number: 3067
Loading