Optimization, Machine Learning, and Networking Solutions for Cyber-Physical Systems - Dissertation

Aug 5, 2026

Upload by Eden

Cyber-Physical Systems (CPS) integrate sensing, computation, and actuation through networked architectures to support intelligent, context-aware applications across domains. Persistent barriers include reliable low-latency communication and efficient data processing under resource constraints and dynamic conditions, especially in rural or remote deployments with limited or unreliable infrastructure. The dissertation develops optimization and inference algorithms for Software-Defined Networks (SDN), using reinforcement learning and network tomography for efficient routing, and targets smart agriculture. It introduces efficient rural data collection, edge intelligence for resource-aware processing, and data-driven decision support to optimize farming resources. For agricultural monitoring, UAV-based frameworks (DRONE and CROP) reduce energy and operating costs while maintaining accuracy, validated on a drone testbed with UV irradiance sensors. To handle disconnected settings, iCrop+ combines on-device AI with deep learning via LoRa for crop disease detection, improving monitoring and enabling remote processing.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages146

Reading Time6 h 8 min

AccessFree to download

Abstract of Dissertation

Optimization and inference in SDN

Smart agriculture applications and data collection

UAV-based crop monitoring frameworks

LoRa-based crop disease detection (iCrop+)

University of Kentucky UKnowledge | Theses and Dissertations--Computer Science | Computer Science | | --- | --- | 2025 Optimization, Machine Learning, and Networking Solutions for Cyber-Physical Systems Xu Tao University of Kentucky, [xu.tao@uky.edu](xu.tao@uky.edu)[ ](xu.tao@uky.edu)[Author ORCID Identifier:](Author ORCID Identifier:)[ ](Author ORCID Identifier:)[https://orcid.org/0009-0002-9393-2028](https://orcid.org/0009-0002-9393-2028) Digital Object Identifier: [https://doi.org/10.13023/etd.2025.72](https://doi.org/10.13023/etd.2025.72) Right click to open a feedback form in a new tab to let us know how this document benefits you. Recommended Citation Tao, Xu, "Optimization, Machine Learning, and Networking Solutions for Cyber-Physical Systems" (2025) . Theses and Dissertations--Computer Science. 150. [https://uknowledge.uky.edu/cs_etds/150](https://uknowledge.uky.edu/cs_etds/150) This Doctoral Dissertation is brought to you for free and open access by the Computer Science at UKnowledge. It has been accepted for inclusion in Theses and Dissertations--Computer Science by an authorized administrator of UKnowledge. For more information, [please contact](please contact UKnowledge@lsv.uky.edu)[ UKnowledge@lsv.uky.edu](please contact UKnowledge@lsv.uky.edu), [rs_kbnotifs-acl@uky.edu](rs_kbnotifs-acl@uky.edu). STUDENT AGREEMENT: I represent that my thesis or dissertation and abstract are my original work. Proper attribution has been given to all outside sources. I understand that I am solely responsible for obtaining any needed copyright permissions. I have obtained needed written permission statement(s) from the owner(s) of each third-party copyrighted matter to be included in my work, allowing electronic distribution (if such use is not permitted by the fair use doctrine) which will be submitted to UKnowledge as Additional File. I hereby grant to The University of Kentucky and its agents the irrevocable, non-exclusive, and royalty-free license to archive and make accessible my work in whole or in part in all forms of media, now or hereafter known. I agree that the document mentioned above may be made available immediately for worldwide access unless an embargo applies. I retain all other ownership rights to the copyright of my work. I also retain the right to use in future works (such as articles or books) all or part of my work. I understand that I am free to register the copyright to my work. REVIEW, APPROVAL AND ACCEPTANCE The document mentioned above has been reviewed and accepted by the student’s advisor, on behalf of the advisory committee, and by the Director of Graduate Studies (DGS), on behalf of the program; we verify that this is the final, approved version of the student’s thesis including all changes required by the advisory committee. The undersigned agree to abide by the statements above. Xu Tao, Student Dr. Simone Silvestri, Major Professor, Director of Graduate Studies Optimization, Machine Learning, and Networking Solutions for Cyber-Physical Systems DISSERTATION A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the College of Engineering at the University of Kentucky By Xu Tao Lexington, Kentucky Director: Dr. Simone Silvestri Associate Professor of Computer Science Lexington, Kentucky 2025 Copyright© Xu Tao 2025 ABSTRACT OF DISSERTATION Optimization, Machine Learning, and Networking Solutions for Cyber-Physical Systems Cyber-Physical Systems (CPS) represent a transformative paradigm that integrates sensing, computation, and actuation through networked systems to enable intelligent, context-aware applications across various domains. Despite their growing potential, CPS still face critical challenges, particularly in maintaining reliable, low-latency communication and eﬀicient data processing in resource-constrained and dynamic environments. These challenges are further magnified in rur

FAQs

What key problems does the dissertation address in cyber-physical systems?

It focuses on maintaining reliable, low-latency communication and efficient data processing in resource-constrained, dynamic environments, with additional difficulties in rural or remote deployments.

How does the work improve network performance in software-defined networks?

It develops optimization and inference algorithms for SDN, leveraging reinforcement learning and network tomography to enable efficient routing.

What solutions are proposed for smart agriculture in limited-connectivity rural farms?

It presents UAV-based data collection frameworks (DRONE and CROP) for precise crop monitoring and introduces iCrop+, a LoRa-based crop disease detection system that supports remote processing when broadband is unavailable.

Aug 5, 2026

Upload by Eden