Shinto, Donnel (2024) Enhancing Security in Electric Vehicle Charging Stations Through Advanced Anomaly Detection Systems. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (468kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (681kB) | Preview |
Abstract
In response to the increase of electric vehicles (EVs), there has been rapid deployment of electric vehicle charging stations (EVCS) in order to serve the needs of sustainable transportation. But incorporating EVCS within power grids and network infrastructures creates potentially severe cybersecurity vulnerabilities. To address these challenges, this research develops a comprehensive anomaly detection framework based on machine learning approaches for boosting the security and reliability of EVCS. The study uses power consumption, network traffic, and hosts events datasets and classifies anomalies in binary and multiclass tasks using algorithms including Random Forest and K-Nearest Neighbours (KNN). Large amounts of preprocessing and feature selection were applied on the datasets. Results demonstrate that Random Forest outperforms KNN and is the most adaptable to feature reduction. KNN performs well in binary tasks but decreases in multiclass tasks. Analysis of host events data showed near perfect accuracy, indicating that removing predictive features can improve efficiency of models. This work contributes a novel scalable anomaly detection framework, provides understanding of the performance and importance of algorithms, and presents practical applications in EVCS security. The results improve resilience of charging infrastructures and motivate further research in the anomaly detection domain for critical systems.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Moldovan, Arghir Nicolae UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in Cyber Security |
Depositing User: | Ciara O'Brien |
Date Deposited: | 28 Jul 2025 11:18 |
Last Modified: | 28 Jul 2025 11:18 |
URI: | https://norma.ncirl.ie/id/eprint/8260 |
Actions (login required)
![]() |
View Item |