Quantum networks, leveraging the principles of quantum mechanics, enable unconditionally secure communication and are emerging as a critical component of next-generation infrastructure. However, the scarcity of quantum network resources results in contention among requests for shared links and qubits. Such contention prolongs processing times and degrades resource utilization efficiency, which in turn leads to imbalanced completion times between high- and low-priority requests. This paper addresses the request scheduling problem by proposing DRL-QN, a scheduling framework based on Reinforcement Learning (RL) that optimizes scheduling sequences, reduces the completion time of network requests, and improves fairness. Specifically, to help the agent better perceive request contention and the network environment, request characteristics and network resources are described as the state, enabling accurate scheduling decisions. Furthermore, to ensure a balanced learning objective, the agent’s training is guided by a multi-objective reward function that simultaneously promotes low completion time and fairness. Extensive simulations demonstrate that the proposed DRL-QN method significantly reduces network completion time by 16.22%–21.25% compared with existing schemes, while achieving fairness comparable to the fairness-optimal method and improving by approximately 6.79%–13.61% over other approaches.
Quantum networks, leveraging the principles of quantum mechanics, enable unconditionally secure communication and are emerging as a critical component of next-generation infrastructure. However, the scarcity of quantum network resources results in contention among requests for shared links and qubits. Such contention prolongs processing times and degrades resource utilization efficiency, which in turn leads to imbalanced completion times between high- and low-priority requests. This paper addresses the request scheduling problem by proposing DRL-QN, a scheduling framework based on Reinforcement Learning (RL) that optimizes scheduling sequences, reduces the completion time of network requests, and improves fairness. Specifically, to help the agent better perceive request contention and the network environment, request characteristics and network resources are described as the state, enabling accurate scheduling decisions. Furthermore, to ensure a balanced learning objective, the agent’s training is guided by a multi-objective reward function that simultaneously promotes low completion time and fairness. Extensive simulations demonstrate that the proposed DRL-QN method significantly reduces network completion time by 16.22%–21.25% compared with existing schemes, while achieving fairness comparable to the fairness-optimal method and improving by approximately 6.79%–13.61% over other approaches.
Abstract Entanglement-based quantum networks require intelligent routing mechanisms that not only maximize fidelity and connectivity but also ensure service differentiation under varying traffic conditions. In this work, we propose a novel QoS-aware traffic modeling and scheduling framework integrated into a reinforcement learning-based quantum routing agent. Unlike prior approaches that assume deterministic or uniform request arrival patterns, our model introduces stochastic and bursty traffic scenarios using Erlang and ON/OFF distributions to emulate realistic quantum workloads. Each entanglement request is assigned a set of QoS attributes, including fidelity requirements, time-to-live constraints, and priority levels. We then extend the reward function of the agent to consider deadline compliance and resource efficiency in addition to fidelity. Through simulation, we compare the proposed method against state-of-the-art baselines, including DQRA and Proactive RL, under both best-effort and QoS-prioritized scheduling modes. Results demonstrate that our approach maintains higher success rates and lower latency for high-priority requests, while preserving entanglement fidelity and efficient resource allocation across varying network loads. This study highlights the importance of integrating QoS mechanisms into quantum routing to support scalable and differentiated quantum services
Quantum entanglement is the cornerstone of quantum network communication, yet the qubit resources required to establish it are severely limited. Moreover, users within the network impose strict delay constraints on entanglement requests due to various factors, such as the real-time requirements of upper-layer applications or the finite coherence time of userside quantum memories. Consequently, effectively scheduling scarce qubit resources to serve these time-sensitive requests presents a significant challenge. This difficulty is exacerbated by the partial observability of quantum systems and the time-varying nature of qubit generation rates, rendering traditional scheduling algorithms ineffective. Furthermore, while Deep Reinforcement Learning (DRL) offers a promising avenue for quantum network optimization, existing research primarily focuses on network-layer routing, overlooking the finer-grained entanglement scheduling problem subject to strict delay and resource constraints. To bridge this gap, we propose the Deep Quantum Request Scheduler (DQRS), a novel DRL-based algorithm designed to maximize service quality under these dual constraints. Specifically, DQRS integrates a spatio-temporal branching architecture and virtual action slots within an ActorCritic framework. This design enables robust scheduling with continuous actions while adaptively managing fluctuating qubit budgets. Extensive simulation results demonstrate that DQRS achieves up to 44 % performance improvement over traditional methods and a 4 % gain compared to state-of-the-art DRL benchmarks across various resource constraints and observability settings, validating the robustness of the proposed approach.
Quantum networks must deliver end-to-end entanglement whose fidelity meets application requirements, which typically requires entanglement purification along multi-hop paths. Existing scheduling approaches either purify at the link level or optimize end-to-end fidelity for a static set of requests, and do not capture concurrent requests competing for network resources over time. This paper studies concurrent entanglement purification scheduling in a time-slotted quantum network with heterogeneous links, in which requests compete for link capacity and quantum memories, and each request may be served by multiple parallel paths for increased reliability. We formulate a mixed-integer linear programming (MILP) scheduler that maximizes the number of scheduled requests, with max-min path allocation as a fairness criterion, and develop reinforcement learning (RL) schedulers based on DQN, PPO, and SAC, whose rewards balance request success against Bell-pair consumption. Simulations under varying network load, topologies and target fidelity thresholds show that the RL schedulers achieve the highest success rates, improving on MILP by up to 6% and on Progressive Filling and Greedy heuristics by 16.5% and 19.5% respectively, at the cost of higher Bell pair consumption and the deferral of a small fraction of requests. MILP, in contrast, achieves the highest fairness and the lowest Bell pair consumption in most scenarios.
Abstract Quantum communication plays a key role in enabling distributed Noisy Intermediate-Scale Quantum (NISQ) systems; however, practical quantum networks are often affected by link fluctuations, limited quantum resources, and entanglement degradation. These factors make reliable routing and scheduling difficult, particularly in large-scale and dynamically changing environments. Classical methods such as Historical Weighted Fidelity Routing (HWFR) and Dynamic Multi-Priority Quantum Scheduling (DMPQS) generally perform well only when network conditions remain stable, and their performance degrades when entanglement success rates vary or relay nodes become congested. A major challenge therefore lies in operating under uncertain and time-varying fidelity conditions. Most existing approaches focus on either routing or scheduling in isolation and do not explicitly consider future fidelity variations, which can lead to inefficient resource usage and increased end-to-end latency. In this work, we propose a Deep Reinforcement Learning-based Quantum Communication Optimization Framework (DRL-QCOF) that jointly addresses routing and scheduling. The framework employs a Bi-LSTM-based Quantum Fidelity Prediction Network (QFPN) to estimate future link fidelity F_"pred" (t)from time-series features including link length, noise coefficient, entanglement success probability, and relay utilization. These predictions are then used by a Deep Reinforcement Learning-based Adaptive Quantum Scheduling Agent (DRAQS-Agent), implemented using an Actor–Critic architecture with a continuous reward formulation, to guide routing and scheduling decisions across distributed nodes. Simulation results indicate that the proposed approach improves the average link fidelity to a maximum of 0.88, compared to 0.78–0.86 achieved by existing methods. The end-to-end latency is reduced from 104 ms to 83 ms, while baseline schemes remain above 110 ms under the same conditions. In addition, the average response time is reduced to approximately 147 ms, resource utilization increases to 71–83%, and the success ratio improves from 93% to 97%, resulting in improved end-to-end reliability. The cumulative reward stabilizes at around 16.0, with convergence observed within 300 training episodes, and the achieved throughput reaches 118–121 entangled pairs per second, confirming the effectiveness of the proposed framework in dynamic NISQ network scenarios.
Quantum networks represent promising foundations for secure communication, distributed quantum computing, and advanced quantum-enabled services. However, their deployment faces practical challenges including limited quantum resources, short coherence times, and environmental disturbances. Effective end-to-end entanglement request scheduling is critical to addressing these challenges, as it directly affects resource utilization and network reliability. Although end-to-end entanglement service rate is one of the representative performance measures in the quantum networks, the explicit optimization of the rate under the realistic constraints is relatively unexplored in the previous studies. This paper proposes an offline reinforcement learning (RL)-based scheduling framework, employing a decision transformer integrated with graph attention networks, to specifically optimize service rates within practical operational constraints, such as the single-time-slot usage limitation of quantum links. Our approach adaptively leverages network topology and operational dynamics to enhance scheduling decisions. Simulation studies conducted on the NetSquid platform across four quantum network topologies demonstrate that our model consistently outperforms both a conventional rule-based method and a baseline offline RL method in terms of service rate, while preserving fidelity and maintaining delays within acceptable levels. These results confirm the effectiveness of the proposed method for practical quantum network management.
ABSTRACT Quantum computing has entered the noisy intermediate‐scale quantum (NISQ) era, where limited qubit numbers, short coherence times, and high error rates pose significant challenges to reliable large‐scale execution. Efficient scheduling and resource allocation across heterogeneous quantum hardware are therefore crucial for maximizing system throughput, fidelity, and fairness. In this work, we propose a hardware‐aware reinforcement learning framework for quantum task scheduling in distributed NISQ systems. Our design explicitly models qubit‐level variability, including connectivity degree, coherence times, error rates, and throughput, while integrating task‐level constraints such as deadlines, priorities, and concurrency requirements. We formulate the scheduling problem as a constrained optimization task and instantiate it as a Markov decision process (MDP), enabling reinforcement learning agents to learn adaptive strategies. Specifically, we implement deep Q‐network (DQN) and proximal policy optimization (PPO) agents, and compare them against heuristic and random baselines. Experimental results demonstrate that PPO consistently outperforms DQN and heuristic methods, achieving higher task completion rates, fewer deadline violations, and more robust adaptation across different reward configurations. This work bridges quantum hardware modeling with reinforcement learning‐based scheduling, providing a practical pathway for resource optimization in distributed quantum computing environments.