Research Interests
My research centers on Quantum Network Routing and Resource Scheduling. I design intelligent control planes that utilize Deep Reinforcement Learning (DRL) to navigate physical constraints like fidelity decay and entanglement swapping. By moving beyond static routing methodologies, I develop dynamic, fidelity-aware algorithms that enable scalable, multi-request pathfinding for the future Quantum Internet. A few of my specific interests include:
- Routing and Resource scheduling in Quantum Networks
- Deployment of Quantum Networks
- Distributed Systems
- Reinforcement Learning
Ongoing Projects
- DQRL based Parallel Routing in Quantum Nerworks: Parallel decision making for Routing in QUantum Netowrks
- Adaptive Entanglement Generation (AEG): Designed a resource management framework that uses Reinforcement Learning to intelligently select which links to entangle and cache for future use
Past Projects
-
QuRA: Reinforcement Learning Based Routing:: A fidelity-aware routing algorithm using Deep Q-Learning to optimize entanglement distribution in quantum networks, achieving up to 90% higher success rates than traditional methods.
-
Proactive Entanglement Swapping: A framework that enhances quantum routing protocols (REPS and SEER) by caching unused entanglements and using Deep Q-Learning to proactively swap links on high-demand segments, improving connection success rates by up to 61%.
-
GHZ-Based Quantum Key Distribution: Proposed and simulated a novel QKD scheme that transmits only a single qubit to establish multi-bit keys using Multi-Qubit Greenberger-Horne-Zeilinger (GHZ) states.
-
Scalable Quantum Repeater Deployment Modeling: Created heuristic algorithms (Multi-Center and Single-Center Approaches) to determine optimal locations for quantum repeaters in large-scale networks like SURFnet and ESnet.