Electrical and Computer Engineering ETDs

Publication Date

Spring 5-15-2023


Cyber-physical systems (CPS) transform how humans interact with technology by integrating sensing, computation, networking, and control with physical processes to facilitate smart services and innovative applications in our environments. Recent advances in CPS have led to rapid growth in the amount of information constantly generated by people, systems, and processes. Most of this information, however, is underutilized due to the lack of efficient information utilization and decision-making techniques. Also, the increasing interconnectivity of CPSs presents security risks that, if left unaddressed, could be highly disruptive to systems, processes, and economies. In this dissertation, we present a study and proposal of novel solutions to the problems of security and decision-making in Cyber-physical systems using advanced theoretical concepts such as Reinforcement Learning and Contract Theory.

Reinforcement Learning (RL) was studied and applied due to its suitability and applicability to real-time intrusion detection in adversarial environments with constantly changing traffic and attack patterns. RL’s ’trial-and-error’ method of learning also makes it well-suited for intelligent decision-making applications in unfamiliar environments. Additionally, Contract theory was adopted due to its “employer-employee” dynamic of capturing system interactions, which allows us to accurately model the relationships between the various entities involved in the examined contexts.

We evaluate our introduced approaches through in-depth empirical studies and demonstrate their cutting-edge performance using detailed results across a range of application domains, such as: (I) Deep Reinforcement Learning-Based Network Intrusion Detection Systems for Industrial Control Systems, (ii) Reinforcement Learning-based Demand Response Management in SmartGrid Systems with Prosumers, (iii) Network Economics-based Crowdsourcing in UAV-assisted Smart Cities Environments, and (iv) Smart Energy Harvesting for Internet of Things Networks.


Reinforcement Learning, SCADA, Demand Response Management, Industrial Control Systems, Intrusion Detection System, Smart Grid

Document Type




Degree Name

Computer Engineering

Level of Degree


Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Eirini Eleni Tsiropoulou

Second Committee Member

Jim Plusquellic

Third Committee Member

Lei Yang

Fourth Committee Member

Symeon Papavassiliou

Available for download on Thursday, May 15, 2025