Machine Learning-Based Multiclass Anomaly Detection and Classification in Hybrid Active Distribution Networks

• Published in: IEEE access Vol. 12; pp. 120131 - 120141
• Main Authors: Chandio, Sadullah, Laghari, Javed Ahmed, Bhayo, Muhammad Akram, Koondhar, Mohsin Ali, Kim, Yun-Su, Graba, Besma Bechir, Touti, Ezzeddine
• Format: Journal Article
• Language: English
• Published: IEEE 2024
• Subjects: Accuracy; Anomaly detection; hybrid active distribution network; islanding detection; Machine learning; machine learning classifiers; Power distribution networks; Power system reliability; Power system stability; Reliability; Time-frequency analysis; Voltage control
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3445287

Anomaly detection in power systems is crucial for operational reliability and safety, often addressed through binary classification in existing research. However, a research gap exists in multiclass classification for enhanced reliability. To bridge this gap, this study employs four machine learning (ML) classifiers: Random Forest (RF), Decision Tree, Naive Bayes (NB), and Support Vector Machine (SVM) using comprehensive testing on a dataset comprising sixteen indices and their pair combinations (totaling 136 pairs). These classifiers, trained on a dataset derived from simulating a test system with hybrid DGs, exhibit superior anomaly detection, especially with the <inline-formula> <tex-math notation="LaTeX">\frac {dv}{dq}\& \frac {dv}{dp} </tex-math></inline-formula> pair. Among them, RF and DT classifier achieves precision, recall, and F score of unity and outperforming NB and SVM. The performance of the proposed RF and DT classifiers with <inline-formula> <tex-math notation="LaTeX">\frac {dv}{dq}\& \frac {dv}{dp} </tex-math></inline-formula> pair is compared with existing research papers in terms of accuracy and data division. The comparison shows that the proposed RF and DT classifiers with <inline-formula> <tex-math notation="LaTeX">\frac {dv}{dq}\& \frac {dv}{dp} </tex-math></inline-formula> pair achieve 100% accuracy even with 50% data division, whereas other techniques fail to achieve it even at 20% for testing and 80% for training. The study underscores the critical role of pair selection and classifier combinations in effective anomaly detection, facilitating the implementation of robust mitigating strategies for power system stability.