Entanglement Request Scheduling in Quantum Networks Using Deep Q-Network

TL;DR

This paper introduces a Deep Q-Network based scheduling method to optimize delay and fairness in quantum repeater networks, addressing limitations of existing models and simulations.

Contribution

It presents a novel DQN-based scheduling approach and a dynamic network model that better captures quantum network behaviors.

Findings

DQN outperforms Greedy, Proportional fair, and FIFO scheduling schemes.

The dynamic network model includes quantum simulations, topologies, and user behaviors.

The method effectively balances delay minimization and fairness in entanglement requests.

Abstract

In this paper, a novel Deep Q-Network (DQN) based scheduling method to optimize delay time and fairness among entanglement requests in quantum repeater networks is proposed. The scheduling of requests determines which pairs of end nodes should be entangled during the current time slot, while other pairs are placed in a queue for future slots. However, existing research on quantum networking often relies on simple statistical models to capture the behavior of quantum hardware, such as the failure rate of establishing entanglement. Moreover, current quantum simulators do not support network behaviors, including handling, pending, and dropping requests. To bridge the gap between quantum deployments and network behaviors, in this paper a dynamic network model is presented, encompassing quantum simulations, random topologies, and user modeling. The DQN based scheduling scheme allows us to balance the conflicting objectives of minimizing delay time and maximizing fairness among these entanglement requests. The proposed technique was evaluated using simulations, with results showing that the proposed DQN achieves higher performance compared to Greedy, Proportional fair and FIFO scheduling schemes.