EUVIMEDEUVIMED entdecken
Crossref

PQD Detection & Classification Using Unsupervised Clustering Method Using DBSCAN

Bakar. Ali Shaik, B. V. Vasantha Rao, B. Deepthi, M. Sowmya

INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 14.04.2026 · 10 (04) · 1-9

DOI: 10.55041/ijsrem60156 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 14.04.2026. Verfasst von Bakar. Ali Shaik und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The researchers present a new approach to identify power quality disturbances through unsupervised clustering which uses DBSCAN as its primary analytical techniques. The system uses machine learning models to predict RMS values which enables users to identify different types of power quality disturbances through their unique patterns. The researchers apply scaling preprocessing to the data before they use Random Forest and XGBoost regression models to forecast RMS values. The Random Forest and XGBoost models execute the classification process which determines whether PQD events belong to the "Good" or "Poor" categories. The researchers apply DBSCAN because DBSCAN identifies noise and detects non-linear clusters. The researchers use standard evaluation metrics to assess model performance which includes R² and RMSE and accuracy measurements. The research achieves high accuracy and precision in PQD classification with nearly flawless regression outcomes and exceptional clustering performance. The solution delivers a powerful solution for real-time power quality monitoring which supports the development of sophisticated intelligent grid systems. The study enhances machine learning capabilities for power systems monitoring through its application in fault detection and anomaly classification. Keywords: PQD, Unsupervised Clustering, DBSCAN, Power Quality Disturbances, RMS Prediction, Machine Learning, Random Forest, XGBoost, Clustering, Real-Time Monitoring.

Zitieren

APA

Shaik, B. A., Rao, B. V. V., Deepthi, B., & Sowmya, M. (2026). PQD Detection & Classification Using Unsupervised Clustering Method Using DBSCAN. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem60156

Vancouver

Shaik BA, Rao BVV, Deepthi B, Sowmya M. PQD Detection & Classification Using Unsupervised Clustering Method Using DBSCAN. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem60156

BibTeX
@article{Shaik2026,
  author = {Shaik, Bakar. Ali and Rao, B. V. Vasantha and Deepthi, B. and Sowmya, M.},
  title = {PQD Detection & Classification Using Unsupervised Clustering Method Using DBSCAN},
  journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
  year = {2026},
  volume = {10},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijsrem60156}
}
Kostenlos starten →