Islanding Detection in Power Distribution Systems Using a Hybrid Machine Learning Approach
Open Access
- 19 October 2026
- journal article
- Published by Institution of Engineering and Technology (IET) in Vector: The Journal of Engineering
- Vol. 2027 (1)
Abstract
The increasing integration of distributed generation units, especially synchronous generators, into modern power systems emphasises the critical need for reliable islanding detection methods. This paper proposes a hybrid islanding detection approach that combines passive monitoring of multiple electrical parameters—such as negative sequence voltage, generator field voltage, and the rate of change of positive sequence impedance—with intelligent machine learning techniques. To enhance detection accuracy, the approach incorporates feature standardisation, Adaptive Synthetic Sampling for data augmentation, Recursive Feature Elimination for optimal feature selection, and a stacking ensemble integrating XGBoost and Random Forest models. The method is evaluated under various network conditions, including load switching, capacitor bank operations, faults, and islanding events, using a modified IEEE 34‐bus distribution system. Simulation results demonstrate that the proposed hybrid method achieves high accuracy, robustness, and generalisability across diverse operating conditions, making it a promising solution for reliable islanding detection in distribution networks.Keywords
This publication has 23 references indexed in Scilit:
- Microgrid Islanding Detection Using D-PMU and Phase Angle Analysis of Negative Sequence ImpedanceIEEE Access, 2025
- Review Study on Recent Advancements in Islanding Detection and Diagnosis in Microgrids Using Signal Processing and Machine Learning TechniquesElectric Power Components and Systems, 2024
- A communication-less islanding detection scheme for hybrid distributed generation systems using recurrent neural networkInternational Journal of Electrical Power & Energy Systems, 2023
- An Intelligent Deep Convolutional Neural Networks-Based Islanding Detection for Multi-DG SystemsIEEE Access, 2022
- A review on distributed generation impacts on electric power systemInternational Journal of Hydrogen Energy, 2022
- Islanding detection based on impedance estimation using small signal injectionInternational Journal of Electrical Power & Energy Systems, 2022
- An intelligent islanding detection of distribution networks with synchronous machine DG using ensemble learning and canonical methodsIET Generation, Transmission & Distribution, 2021
- The Elements of Statistical Learning2009
- Gene Selection for Cancer Classification using Support Vector MachinesMachine Learning, 2002
- Random ForestsMachine Learning, 2001