Implementing Artificial Intelligence Techniques for Enhanced Islanding Detection in Photovoltaic Systems
Keywords:
Islanding Detection, Photovoltaic Systems, Artificial Intelligence, Machine Learning, Deep Learning, MATLAB, Grid SafetyAbstract
The widespread adoption of photovoltaic (PV) systems in the electricity grid has highlighted the crucial
significance of efficient islanding detection procedures in guaranteeing safety, dependability, and adherence to
grid standards. Islanding is the condition in which a section of the electrical grid runs independently from the
main power source, which can possibly create hazards for both equipment and workers. Conventional detection
systems frequently encounter difficulties in terms of both speed and accuracy, especially when operating in lessthan-ideal situations.A hybrid model that synergistically combines the capabilities of machine learning
algorithms and signal processing techniques to improve the accuracy and precision of islanding detection. The
model utilizes a two-step procedure: in the first step, it utilizes signal attributes derived from the output of the
PV system to provide preliminary detection signals. The signals are further examined by a deep learning
algorithm, specifically a convolutional neural network (CNN), which has been trained on an extensive dataset
that encompasses a diverse array of islanding and non-islanding situations. This dataset includes different load
and generation balances. The purpose of this analysis is to arrive at a conclusive decision. This paper presents a
new method for detecting islanding in photovoltaic (PV) systems, utilizing the capabilities of artificial
intelligence (AI) approaches. The method is studied and confirmed using MATLAB software.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













