Enhancing Anomaly Detection in Electric Vehicle Supply Equipment (EVSE) Networks Using Classical and Ensemble Learning Approaches

Electric Vehicle Supply Equipment (EVSE) networks, integral to modern transportation systems, are vulnerable to cyber threats due to integration into smart grids and IoT ecosystems. EVSE network A represents a traditional, centralized EV charging infrastructure, whereas EVSE network B denotes a distributed, decentralized charging network with varying levels of connectivity. This research investigates the security landscape of EVSE networks A and B, focusing on the detection and classification of network attacks. Through meticulous comparative analysis, the research highlights the effectiveness of Ensemble Learning over Classical learning models in improving attack classification precision. This approach enhances the precision of attack detection by leveraging diverse algorithms and data sources to mitigate security risks effectively.