Electrical Power Quality Classification using Nested Ensemble Learning
International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 1 | Views: 280 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Research Paper | Data & Knowledge Engineering | India | Volume 13 Issue 1, January 2024 | Popularity: 4.3 / 10


     

Electrical Power Quality Classification using Nested Ensemble Learning

Supekar Unmesh Mahesh


Abstract: With recent technological advancements, Machine learning (ML), and Deep learning (DL)is one of the most promising approaches used widely to correctly categorize diverse Power Quality events. In this paper, an effort is made to demonstrate the implementation and utilization of nested ensemble machine learning algorithms and hybrid ANN-Deep ConvNet(Artificial Neural Network-Deep Convolutional Neural Network). Ensemble machine learning classifiers used in the paper for Power Quality Event Classification are Decision Tree, Random Forest, K-NearestNeighbour(KNN), LightGradient Boosting Machine(LGBM), & AdaBoost. They are combined using a Stacking Classifier to perform Nested Ensemble Machine Learning Power Quality classification. The Research also proposes a Deep learning-based hybrid approach of Ensembled ANN-Deep ConvNet for accurate classification of Power Quality events.The confusion matrix and Accuracy table have been used as a measure of performance in the paper.


Keywords: Electrical Power Quality, Ensemble Machine Learning, Ensemble learning, Deep Learning, Power Quality Classification, ANN-Deep ConvNet


Edition: Volume 13 Issue 1, January 2024


Pages: 353 - 358


DOI: https://www.doi.org/10.21275/SR24102232805



Make Sure to Disable the Pop-Up Blocker of Web Browser




Text copied to Clipboard!
Supekar Unmesh Mahesh, "Electrical Power Quality Classification using Nested Ensemble Learning", International Journal of Science and Research (IJSR), Volume 13 Issue 1, January 2024, pp. 353-358, https://www.ijsr.net/getabstract.php?paperid=SR24102232805, DOI: https://www.doi.org/10.21275/SR24102232805