Cyberattack Detection and Classification of Power Converters in Islanded Microgrids Using Deep Learning Approaches

Abstract

The integration of Internet of Things (IoT) technologies into islanded microgrids has increased their vulnerability to cyberattacks, particularly those targeting critical components such as power converters within an islanded AC microgrid. This study investigates the impact of False Data Injection (FDI) and Denial of Service (DoS) attacks on various power converters, including DC–DC boost converters, DC–AC converters, battery inverters, and DC–DC buck–boost converters, modeled in MATLAB/Simulink. A dataset of healthy and compromised operational parameters, including voltage and current, was generated under simulated attack conditions. To enhance system resilience, a deep learning-based detection and classification framework was proposed. After evaluating various deep learning models, including Deep Neural Networks (DNNs), Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Long Short-Term Memory (LSTM), and Feedforward Neural Networks (FNNs), the final system integrates an FNN for rapid attack detection and an LSTM model for accurate classification. Real-time simulation validation demonstrated a detection accuracy of 95% and a classification accuracy of 92%, with minimal computational overhead and fast response times. These findings emphasize the importance of implementing intelligent and efficient cybersecurity measures to ensure the secure and reliable operation of islanded microgrids against evolving cyberattacks.