Theses and Dissertations

ORCID

0009-0000-5483-1756

Advisor

Chaudhary, Vini

Committee Member

Trawick, George

Committee Member

Perkins, Andy

Date of Degree

8-12-2026

Original embargo terms

Visible MSU Only 6 months

Document Type

Graduate Thesis - Campus Access Only

Major

Cybersecurity & Operations

Degree Name

Master of Science (M.S.)

College

James Worth Bagley College of Engineering

Department

Department of Computer Science and Engineering

Abstract

The rapid advancement of quantum computing necessitates robust networking solutions to enable distributed quantum computing and quantum key distribution. A key challenge in such networks is selecting reliable routing paths for establishing high-fidelity end-to-end entanglement between source and destination nodes. Existing quantum routing approaches often assume deterministic decoherence characteristics of quantum memories, which is unrealistic in practice. In this work, we model node-level decoherence as a bounded stochastic process using a truncated Gaussian distribution, capturing inherent randomness while maintaining stationary statistical properties. This introduces uncertainty in path quality without temporal drift. To address this, we formulate the routing problem as a multi-armed bandit (MAB) and extend it to a contextual multi-armed bandit (CMAB) framework that leverages network context, such as path and node features, to improve learning efficiency. Simulation results demonstrate that CMAB achieves faster convergence and higher cumulative reward, resulting in improved end-to-end entanglement fidelity compared to standard MAB approaches.

Download

Share

COinS