Deep Learning and Machine Learning for Enhanced Anomaly Detection in EVSE systems

Pandey, Shivangi (2025) Deep Learning and Machine Learning for Enhanced Anomaly Detection in EVSE systems. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (474kB) | Preview

Abstract

The increasing digitization and connectivity of Electric Vehicle Charging Systems (EVCS) have made them vulnerable to a variety of cyberattacks. This research introduces a comprehensive anomaly detection framework that employs Deep Neural Networks (DNNs) and traditional Machine Learning (ML) algorithms to enhance cybersecurity in Electric Vehicle Supply Equipment (EVSE) environments. The research evaluates the performance of four individual models, Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), and DNN to detect both benign and malicious communication patterns between EVSE and charging management systems. Accuracy, precision, recall, F1-score, Area Under the Curve (AUC), and execution time are used as evaluation metrics. On balanced data, the DNN model achieved the highest performance with an accuracy of 99.86 % and AUC of 0.9986, followed by RF with 87.6 % accuracy and 0.8762 AUC. GB achieved 78.4 % accuracy, while SVM showed the weakest performance with only 53.1% accuracy and 0.5312 AUC. DNN also maintained low execution time (1.53s) and robust generalization. The findings highlight the effectiveness of DNN and classical ML models in detecting anomalies within EVSE systems and provide a foundation for improving security in future EVCS deployments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cortes Mendoza, Jorge Mario UNSPECIFIED
Uncontrolled Keywords:	EVCS; EVSE; Deep Neural Network; Support Vector Machine; Gradient Boosting; Random Forest
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing 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 Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	30 Mar 2026 11:22
Last Modified:	30 Mar 2026 11:22
URI:	https://norma.ncirl.ie/id/eprint/9250

Actions (login required)

View Item