Electronic Theses and Dissertations Archive

Date

2026

Document Type

Thesis

Degree Name

Master of Science

Department

Electrical & Computer Engineering

Committee Chair

Mohd. Ali

Committee Member

Alexander Headley

Committee Member

Madhusudhanan Balasubramanian

Abstract

As the global transition towards renewable energy accelerates, the integration of solar photovoltaic (PV) systems with Battery Energy Storage Systems (BESS) has become increasingly critical for maintaining grid stability and reliability. This thesis presents a physics-preserving machine learning framework designed for the detection and mitigation of cyberattacks in grid-integrated BESS-PV systems. The research addresses the growing concern surrounding cybersecurity threats that can compromise the functionality and safety of energy systems. We develop a comprehensive detection framework rooted in physical models that accurately represent the behavior of PV and BESS technology. Key contributions include the formulation of a dual attack modeling framework that encompasses False Data Injection (FDI) and Denial of Service (DoS) attack scenarios, complemented by physics-informed feature engineering that captures the unique operational constraints of PV and BESS. A novel Physics-Informed Isolation Forest Detection Algorithm is introduced, enhancing detection capabilities while ensuring the preservation of physical realities within the energy system. Simulation results demonstrate the effectiveness of the proposed framework in robustly detecting and mitigating attacks, thereby reinforcing the security of grid-integrated systems. The findings highlight practical implications for the implementation of cybersecurity strategies in renewable energy infrastructures, offering insights for future research and development in this pivotal area of electrical engineering.

Comments

Data is provided by the student.

Library Comment

Dissertation or thesis originally submitted to ProQuest/Clarivate.

Notes

Open Access.

Download

Share

COinS
 

Archival Statement

This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. This material is part of a digital archival collection and is not utilized for current University instruction, programs, or active public communication. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.