Islanding detection in photovoltaic (PV) integrated microgrids plays a crucial role in ensuring the stability and safety of distributed power systems. Traditional islanding detection methods often rely on predefined thresholds or frequency/voltage deviation measurements, which may prove inadequate in complex and dynamic microgrid environments. This paper proposes a novel approach utilizing Deep Convolutional Neural Networks (DCNNs) for islanding detection in PV-integrated microgrids. The 1D islanding and non-islanding signals are converted to 2D image using constant Q transform, which fed as input to DCNN.The harnessing capabilities of DCNN is to automatically extract hierarchical features from raw 2D image. The proposed method aims to enhance the accuracy and robustness of islanding detection, even in scenarios with fluctuating solar generation and load dynamics. Extensive simulations are conducted to evaluate the performance of the proposed DCNN-based approach under various operating conditions, demonstrating its effectiveness in accurately detecting islanding events while minimizing false alarms. The results highlight the potential of DCNNs as a promising tool for enhancing the reliability and safety of PV integrated microgrid based on constant $Q$ transform.
Islanding detection in PV-integrated microgrid using Deep convolutional neural Network and Constant Q Transform
2024-07-31
654984 byte
Conference paper
Electronic Resource
English
Probabilistic Neural Network Based Islanding Detection in Distributed Generation
Online Contents | 2011
|Emergency Vehicle Detection Using Deep Convolutional Neural Network
Springer Verlag | 2022
|Structural Damage Detection using Deep Convolutional Neural Network and Transfer Learning
Springer Verlag | 2019
|