Graduation Semester and Year
Summer 2026
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Computer Science
Department
Computer Science and Engineering
First Advisor
Hao Che
Abstract
Long-distance quantum communication depends on distributing high-delity entanglement across quantum repeaters. Entangled states are fragile: they decohere in memory, are consumed when used, and lose delity after each swap. Quantum routing therefore diers from classical routing: an algorithm must decide not only the path, but when to generate, store, swap, and consume entanglement before they lose their usefulness. This dissertation studies scalable resource allocation and routing for quantum networks under delity, memory, and concurrency constraints. It rst addresses re- peater deployment with heuristics that nd near-optimal locations while cutting com- putation from days to seconds versus integer linear programming (ILP). It then stud- ies temporal reuse through caching and proactive swapping: by storing unused links and learning which segments will be needed in later time slots, reinforcement-learning methods raise request satisfaction over existing algorithms. The central contribution is QuRA, a reinforcement-learning routing framework for dierent operating regimes. In quality-limited networks, where usable entangle- iii ment is scarce, QuRA-Seq uses one deep reinforcement learning agent for delity- aware hop-by-hop decisions. As generation rates and demand grow, routing becomes capacity-limited: a sequential controller cannot consume entanglement before it de- coheres. For this regime, QuRA-Hive assigns one agent per request and coordinates next-hop decisions through QMIX-based multi-agent training. Across grid and real-world topologies, these methods improve scalability, run- time, and throughput while enforcing end-to-end delity. QuRA-Seq approaches ILP routing quality at far lower cost, and QuRA-Hive raises throughput under heavy demand while cutting link conicts versus uncoordinated parallel routing. Overall, scalable quantum networking requires routing that adapts to the limits of entangle- ment generation, memory decoherence, and shared resources.
Keywords
Quantum networks, Quantum routing, Reinforcement learning, Entanglement management, Quantum repeater deployment, Fidelity-aware routing
Disciplines
Digital Communications and Networking
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Islam, Tasdiqul, "Scalable Quantum Network Routing through Reinforcement Learning and Resource Optimization" (2026). Computer Science and Engineering Dissertations. 20.
https://mavmatrix.uta.edu/cse_dissertations2/20