AI Enhanced Design for Resilient Cyber-Physical Systems
| dc.contributor.advisor | Huang, Stephen | |
| dc.contributor.committeeMember | Eick, Christoph F. | |
| dc.contributor.committeeMember | Yan, Feng | |
| dc.contributor.committeeMember | Laszka, Aron | |
| dc.creator | Kadir, S M Salah Uddin | |
| dc.creator.orcid | 0009-0003-5507-5456 | |
| dc.date.accessioned | 2024-01-26T19:38:54Z | |
| dc.date.created | December 2023 | |
| dc.date.issued | 2023-12 | |
| dc.date.updated | 2024-01-26T19:38:55Z | |
| dc.description.abstract | This dissertation comprehensively explores the transformative potential of integrating artificial intelligence (AI) into the design framework of cyber-physical systems (CPS), thereby enhancing their resilience within the realms of power systems, transportation, and security. In the face of escalating complexities and dynamic threats confronting contemporary infrastructure, the imperative for adaptable and robust CPS design has risen to paramount significance. Within power systems, the operational dynamics of the power grid encounter extreme events that necessitate human operators to make decisions under stressful conditions characterized by elevated cognitive loads. Addressing decision-making challenges during adverse dynamic events requires the integration of intelligent and proactive control mechanisms. During wildfire incidents, effective power system operation demands proactive management strategies rooted in resiliency, encompassing actions like load shedding, line switching, and resource allocation that are attuned to wildfire dynamics and failure propagation. However, the sheer multitude of possible line and load-switching actions within extensive systems during events renders traditional prediction-driven and stochastic methods computationally unfeasible, often resulting in the adoption of greedy algorithms by operators. This dissertation tackles this challenge by formulating the proactive control problem as a Markov decision process and solving it using a Deep Reinforcement Learning approach. An integrated testbed is introduced, simulating the spatiotemporal propagation of wildfires and proactive power system operations. The efficacy of this methodology is assessed through experimentation on the IEEE 24-node system deployed on a hypothetical terrain. Empirical findings demonstrate its potential in aiding operators to mitigate load loss during extreme events, reducing power flow through lines earmarked for de-energization, and dynamically adjusting load demands by redistributing power flow through alternative lines. By enabling swift response and recovery mechanisms, AI substantially augments the power system's capacity to endure such environmental challenges. Similarly, the dissertation underscores AI's potential in enhancing the security of cyber-physical systems. By employing techniques such as remote attestation and game theory, this research elevates the security profile of such systems, reinforcing their resilience against potential threats. Collectively, this dissertation sheds light on the considerable contributions of AI to CPS design, fostering adaptability, efficiency, and security across diverse contexts. | |
| dc.description.department | Computer Science, Department of | |
| dc.format.digitalOrigin | born digital | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | Portions of this document appear in: Salah Uddin Kadir, S. Majumder, A. Srivastava, A. Chhokra, H. Neema, A. Dubey, A. Laszka. Reinforcement Learning based Proactive Control for Enabling Power Grid Resilience to Wildfire. IEEE Transactions on Industrial Informatics. 2023. DOI: https://www.doi.org/10.1109/TII.2023.3263500; and in: Shanto Roy, Salah Uddin Kadir, Yevgeniy Vorobeychik, and Aron Laszka (2021). Strategic Remote Attestation: Testbed for Internet-of-Things Devices and Stackelberg Security Game for Optimal Strategies. GameSec 2021. DOI: https://doi.org/10.1007/978-3-030-90370-1_15 | |
| dc.identifier.uri | https://hdl.handle.net/10657/16193 | |
| dc.language.iso | eng | |
| dc.rights | The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. UH Libraries has secured permission to reproduce any and all previously published materials contained in the work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s). | |
| dc.subject | Artificial Intelligence | |
| dc.subject | Cyber-Physical Systems | |
| dc.subject | Dissertation | |
| dc.title | AI Enhanced Design for Resilient Cyber-Physical Systems | |
| dc.type.dcmi | text | |
| dc.type.genre | Thesis | |
| dcterms.accessRights | The full text of this item is not available at this time because the student has placed this item under an embargo for a period of time. The Libraries are not authorized to provide a copy of this work during the embargo period. | |
| local.embargo.lift | 2025-12-01 | |
| local.embargo.terms | 2025-12-01 | |
| thesis.degree.college | College of Natural Sciences and Mathematics | |
| thesis.degree.department | Computer Science, Department of | |
| thesis.degree.discipline | Computer Science | |
| thesis.degree.grantor | University of Houston | |
| thesis.degree.level | Doctoral | |
| thesis.degree.name | Doctor of Philosophy |