A Machine Learning Based Cyber Attack Detection Model for Wireless Sensor Networks in Microgrids

The increasing reliance on wireless sensor networks (WSNs) within microgrids has underscored the critical need for robust security mechanisms, given their susceptibility to various cyber-attacks. This study introduces a machine learning-based cyber-attack detection model tailored for WSNs in microgrids, utilizing a comprehensive dataset from Kaggle. Our model integrates a diverse set of algorithms, including Convolutional Neural Networks (CNN), Passive Aggressive Classifiers, Random Forest Classifiers, and XGBoost Classifiers, to ensure high accuracy and efficiency in detecting anomalies. By feeding the system with network data, it can accurately classify the network state as either normal or under one of three specific attack types: grayhole, blackhole, or flooding attack. This multifaceted approach not only enhances the detection capabilities but also contributes to the resilience of microgrids against sophisticated cyber threats, ensuring their reliable and secure operation.

Keywords: Wireless Sensor Networks, Cyber Attack Detection, Machine Learning, CNN, Passive Aggressive Classifier, Random Forest, XGBoost, Microgrids, Security