Real-Time Islanding Detection in Microgrids Using RVFLN: A Case Study on IEEE 13-Bus System


Akil Y., BOYNUEĞRİ A. R., Yilmaz M., Haydaroǧlu C.

14th International Conference on Renewable Energy Research and Applications, ICRERA 2025, Vienna, Avusturya, 27 - 30 Ekim 2025, ss.152-156, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/icrera66237.2025.11284043
  • Basıldığı Şehir: Vienna
  • Basıldığı Ülke: Avusturya
  • Sayfa Sayıları: ss.152-156
  • Anahtar Kelimeler: IEEE 13-bus, Islanding detection, microgrid, RVFLN
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

Ensuring operational stability in hybrid power systems requires fast and reliable islanding detection methods, especially with the increasing integration of distributed generation units in microgrids. This study presents a novel realtime islanding detection approach based on Random Vector Functional Link Networks (RVFLN). The method leverages advanced feature extraction techniques, including Dynamic Harmonic Profiles (DHP) and Energy Decay Rates (EDR), using current and voltage measurements to effectively distinguish islanding modes from normal grid-connected operations. The proposed model is validated on the IEEE 13-bus test system simulated in a Real-Time Digital Simulator (RTDS). Results show that the RVFLN-based method achieves superior accuracy (> 95%), high precision (97.5%), and fast detection time (0.05 s) compared to conventional machine learning models. These findings demonstrate the potential of the proposed method for real-time protection and stability enhancement in modern hybrid microgrids.