Paper Type

Master's Thesis


College of Computing, Engineering & Construction

Degree Name

Master of Science in Electrical Engineering (MSEE)



NACO controlled Corporate Body

University of North Florida. School of Engineering

First Advisor

Dr. Touria El Mezyani

Second Advisor

Dr. Kreidl O Patrick

Third Advisor

Dr. Jutima Simsiriwong


The increasing prevalence of cyber-attacks poses a significant concern, particularly within critical infrastructures like the power system. Such attacks have the potential to cause substantial impacts on essential services, economic stability, and national security. Energy storage systems (ESS) are integral components of the power grid and are particularly vulnerable to cyber threats. These vulnerabilities can be exploited through various means, including two-way communication, web portals, and remote access.

Given the critical nature of ESS, the ability to detect and mitigate malicious cyber-attacks is imperative. Various methods can be employed for cyber-attack detection, including signature-based, anomaly-based, and behavior-based approaches. In this study, we focus on two distinct methodologies for anomaly detection related to cyber intrusions on ESS: a physics-based model utilizing a Kalman filter (KF) approach and a data-driven prediction approach employing machine learning (ML) tools.

The main aim of this research is to assess the vulnerability of ESS to cyber threats and evaluate the effectiveness of the KF and ML approaches for cyber protection. By comparing and contrasting these methodologies, we aim to gain insights into their respective strengths and weaknesses, ultimately contributing to enhancing the security of energy storage systems against cyber intrusions.