Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEEE Conference on Computer Communications (INFOCOM)

AEPA: Adaptive Entanglement Pre-Allocation for Low-Latency Quantum Repeater Networks

Hao Chen, Baoxia Du, Ruidong Li

Published May 18, 2026• 0 citations
Publisher

Abstract

Quantum repeater networks rely on timely and high-fidelity entanglement, yet conventional on-demand schemes initiate entanglement generation only after receiving request, leading to substantial time-to-service (TTS) delays due to generation and purification processes. Pre-generating entanglement pairs can mitigate such delay, but determining appropriate per-link preparation levels remains challenging: excessive preparation wastes quantum memory and accelerates decoherence, whereas insufficient preparation causes shortages along frequently used paths. To address this issue, we propose AEPA, an adaptive entanglement pre-allocation framework that employs Deep Reinforcement Learning (DRL) to dynamically adjust link-level pre-generation targets based on traffic patterns, topology characteristics, inventory states, and expiration indicators. AEPA maintains fresh entanglement on heavily used links while avoiding unnecessary generation on lightly loaded ones, thereby reducing TTS and improving overall resource-utilization efficiency. Experiments using a Time-to-Live (TTL)–based repeater model indicate that AEPA can achieve competitive performance across diverse traffic conditions, offering approximately 10–25 % higher success rates, 40–70% lower latency, and 10–25% better memory-efficiency compared with several baseline strategies.

DOI
10.1109/infocom59046.2026.11571752

Related papers

Adaptive Entanglement Generation for Quantum Routing

Tasdiqul Islam, Arifuzzaman, Md, Engin Arslan

Entanglement generation in long-distance quantum networks is a difficult process due to resource limitations and the probabilistic nature of entanglement swapping. To maximize success probability, existing quantum routing algorithms employ computationally expensive solutions (e.g., linear programming) to determine which links to entangle and use for end-to-end entanglement generation. Such optimization methods, however, cannot meet the delay requirements of real-world quantum networks, necessitating swift yet efficient real-time optimization models. In this paper, we propose reinforcement learning (RL)-based models to determine which links to entangle and proactively swap to meet connection requests. We show that the proposed RL-based approach is 20x faster compared to linear programming. Moreover, we show that one can take advantage of the longevity of entanglements to (i) cache entangled links for future use and (ii) proactively swap entanglement on high-demand path segments, thereby increasing the likelihood of request success. Through comprehensive simulations, we demonstrate that caching unused entanglements leads to a 10-15% improvement in the performance of state-of-the-art quantum routing algorithms. Complementing caching with proactive entanglement swapping further enhances the request success rate by up to 52.55%.

arXiv:2505.08958•May 13, 2025•1 citation

SLA-Aware Quantum Entanglement Distribution in Multi-Slice 6G Networks

Haitham H. Esmat, L. Liu

Next-generation 6G networks are expected to support diverse services with strict latency and fidelity requirements, making network slicing and quantum communication key enablers for secure and high-performance connectivity. In this paper, we address service-level agreement (SLA)-aware quantum entanglement distribution across multiple network slices, where each slice has distinct SLAs specifying latency and entanglement fidelity constraints. We consider various entanglement distribution configurations, including ground-to-ground stations, ground-to-UAVs, and ground-to-UAV-to-LEO satellites, and account for the availability of UAVs, satellites, and network resources. To dynamically select the optimal configuration for each slice while performing entanglement swapping along chosen routes, we propose a deep reinforcement learning (DRL) framework that balances SLA satisfaction and resource efficiency. Numerical results show that the proposed DRL-based approach effectively adapts to network dynamics, achieving near-optimal slice performance in latency and entanglement fidelity, and outperforming conventional static allocation strategies.

IEEE Vehicular Technology Conference•Sep 1, 2026•0 citations

QoS-Aware Reinforcement Learning Routing for Entanglement Networks

Diego Medeiros De Abreu, Antônio Abelém

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

•Jan 22, 2026•0 citations

Threshold-Based Memory Resource Allocation for Entanglement Distribution in Quantum Communication Networks

Zihao Wang, Yu Liu, Xiaosong Yu

Efficient quantum memory management is a critical challenge for large-scale entanglement distribution networks, where the probabilistic nature of entanglement generation and finite memory coherence time often cause asynchronous link completion and severe resource blocking. To address this problem, we propose a Threshold-Driven Dual-Mode Allocation (TDDMA) scheme that adaptively switches between pre-allocation and ondemand allocation according to a configurable success-probability threshold. The algorithm dynamically classifies links into highreliability and low-reliability categories. High-success-probability links are pre-allocated at the beginning of each attempt to guarantee continuity, while soft links allocate memory only when entanglement generation succeeds, releasing unused memories immediately after failure. This dual-mode mechanism effectively balances reliability and utilization by minimizing idle occupation without compromising end-to-end success probability. We develop a simulation framework on 64 -node grid and ring topologies to evaluate the proposed scheme. Results show that TDDMA achieves up to$\mathbf{4 5. 7 \%}$lower blocking probability and$\mathbf{7 - 8 \%}$higher effective memory utilization compared with the static End-to-End Reservation Allocation (EERA) baseline. Moreover, TDDMA demonstrates robust adaptability under varying traffic loads and link success distributions, maintaining stable performance even near network saturation.

IEEE International Conference on Computer and Communications (ICCC)•Dec 12, 2025•0 citations

Reinforcement Learning Based Proactive Entanglement Swapping for Quantum Networks

Tasdiqul Islam, Md Arifuzzaman, Engin Arslan

Entanglement generation and swapping is a difficult process due to probabilistic nature of quantum mechanics. To overcome this issue, existing quantum routing algorithms try to create entanglement on multiple paths between source and destination. Although it is possible to save entangled qubits on unused links using quantum memories, the quantum routing algorithms discard them and try creating new entanglement in each time slot. In this work, we leverage the longevity of entanglement and introduce two enhancements to improve the performance of existing routing algorithms: (i) The generation and caching of entanglements across multiple time slots, and (ii) the proactively executing entanglement swapping for frequently utilized links, increasing the success rate of future requests. Since entanglement caching reduces available quantum memory on quantum repeaters, we apply reinforcement learning to identify the optimal set of segments that are likely to be used in the future. Through comprehensive simulations, we demonstrate that caching unused entanglements lead to 10 - 15% improvement on the performance of quantum routing algorithms REPS and SEER. Complementing the caching with reinforcement learning based proactively entanglement swapping leads to further performance improvements. Specifically, using Q-Learning to decide on which segments to proactively swap leads to 52.55% and 41.79% improvement for REPS and SEER algorithms, respectively. Deep Q-Learning outperforms Q-Learning with 61.43% and 48.27% improvements rates.

International Conference on Quantum Communications, Networking, and Computing (QCNC)•Jul 1, 2024•11 citations

Learning-Based Entanglement Generation for Quantum Routing

Tasdiqul Islam, Rasman Mubtasim Swargo, Md Arifuzzaman

Entanglement generation in long-distance quantum networks is challenging because resources are limited and entanglement swapping is probabilistic. To maximize the rate of successful requests, existing quantum routing algorithms often rely on computationally expensive methods such as Integer Linear Programming (ILP) to determine which links to entangle and use for end-to-end entanglement generation. However, these approaches fail to meet the latency requirements of real-world quantum networks. In this study, we propose a Reinforcement Learning (RL)-based model that determines which links to entangle in each time slot, replacing the slow ILP-based link-selection phase used in prior algorithms. The proposed Deep Q-learning model is up to 19.2× faster than linear programming in link-selection while maintaining comparable routing performance. The RL link-selection model alone matches ILP in request success rate; combining RL link selection with entanglement caching and proactive swapping raises throughput by up to 52.55% over ILP. Overall, our approach achieves success rates exceeding state-of-the-art solutions while reducing execution time by more than an order of magnitude. Experiments on a synthetic 50-node Waxman topology and the real-world 54-node SURFnet core topology confirm that these gains generalize across network structures, providing a practical path toward scalable quantum routing.

•Aug 17, 2026•0 citations
Quantum repeater networks rely on timely and high-fidelity entanglement, yet conventional on-demand schemes initiate entanglement generation only after receiving request, leading to substantial time-to-service (TTS) delays due to generation and purification processes. Pre-generating entanglement pairs can mitigate such delay, but determining appropriate per-link preparation levels remains challenging: excessive preparation wastes quantum memory and accelerates decoherence, whereas insufficient preparation causes shortages along frequently used paths. To address this issue, we propose AEPA, an adaptive entanglement pre-allocation framework that employs Deep Reinforcement Learning (DRL) to dynamically adjust link-level pre-generation targets based on traffic patterns, topology characteristics, inventory states, and expiration indicators. AEPA maintains fresh entanglement on heavily used links while avoiding unnecessary generation on lightly loaded ones, thereby reducing TTS and improving overall resource-utilization efficiency. Experiments using a Time-to-Live (TTL)–based repeater model indicate that AEPA can achieve competitive performance across diverse traffic conditions, offering approximately 10–25 % higher success rates, 40–70% lower latency, and 10–25% better memory-efficiency compared with several baseline strategies.
Entanglement generation in long-distance quantum networks is a difficult process due to resource limitations and the probabilistic nature of entanglement swapping. To maximize success probability, existing quantum routing algorithms employ computationally expensive solutions (e.g., linear programming) to determine which links to entangle and use for end-to-end entanglement generation. Such optimization methods, however, cannot meet the delay requirements of real-world quantum networks, necessitating swift yet efficient real-time optimization models. In this paper, we propose reinforcement learning (RL)-based models to determine which links to entangle and proactively swap to meet connection requests. We show that the proposed RL-based approach is 20x faster compared to linear programming. Moreover, we show that one can take advantage of the longevity of entanglements to (i) cache entangled links for future use and (ii) proactively swap entanglement on high-demand path segments, thereby increasing the likelihood of request success. Through comprehensive simulations, we demonstrate that caching unused entanglements leads to a 10-15% improvement in the performance of state-of-the-art quantum routing algorithms. Complementing caching with proactive entanglement swapping further enhances the request success rate by up to 52.55%.
Next-generation 6G networks are expected to support diverse services with strict latency and fidelity requirements, making network slicing and quantum communication key enablers for secure and high-performance connectivity. In this paper, we address service-level agreement (SLA)-aware quantum entanglement distribution across multiple network slices, where each slice has distinct SLAs specifying latency and entanglement fidelity constraints. We consider various entanglement distribution configurations, including ground-to-ground stations, ground-to-UAVs, and ground-to-UAV-to-LEO satellites, and account for the availability of UAVs, satellites, and network resources. To dynamically select the optimal configuration for each slice while performing entanglement swapping along chosen routes, we propose a deep reinforcement learning (DRL) framework that balances SLA satisfaction and resource efficiency. Numerical results show that the proposed DRL-based approach effectively adapts to network dynamics, achieving near-optimal slice performance in latency and entanglement fidelity, and outperforming conventional static allocation strategies.
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
Efficient quantum memory management is a critical challenge for large-scale entanglement distribution networks, where the probabilistic nature of entanglement generation and finite memory coherence time often cause asynchronous link completion and severe resource blocking. To address this problem, we propose a Threshold-Driven Dual-Mode Allocation (TDDMA) scheme that adaptively switches between pre-allocation and ondemand allocation according to a configurable success-probability threshold. The algorithm dynamically classifies links into highreliability and low-reliability categories. High-success-probability links are pre-allocated at the beginning of each attempt to guarantee continuity, while soft links allocate memory only when entanglement generation succeeds, releasing unused memories immediately after failure. This dual-mode mechanism effectively balances reliability and utilization by minimizing idle occupation without compromising end-to-end success probability. We develop a simulation framework on 64 -node grid and ring topologies to evaluate the proposed scheme. Results show that TDDMA achieves up to45.7%\mathbf{4 5. 7 \%}45.7%lower blocking probability and7−8%\mathbf{7 - 8 \%}7−8%higher effective memory utilization compared with the static End-to-End Reservation Allocation (EERA) baseline. Moreover, TDDMA demonstrates robust adaptability under varying traffic loads and link success distributions, maintaining stable performance even near network saturation.
Entanglement generation and swapping is a difficult process due to probabilistic nature of quantum mechanics. To overcome this issue, existing quantum routing algorithms try to create entanglement on multiple paths between source and destination. Although it is possible to save entangled qubits on unused links using quantum memories, the quantum routing algorithms discard them and try creating new entanglement in each time slot. In this work, we leverage the longevity of entanglement and introduce two enhancements to improve the performance of existing routing algorithms: (i) The generation and caching of entanglements across multiple time slots, and (ii) the proactively executing entanglement swapping for frequently utilized links, increasing the success rate of future requests. Since entanglement caching reduces available quantum memory on quantum repeaters, we apply reinforcement learning to identify the optimal set of segments that are likely to be used in the future. Through comprehensive simulations, we demonstrate that caching unused entanglements lead to 10 - 15% improvement on the performance of quantum routing algorithms REPS and SEER. Complementing the caching with reinforcement learning based proactively entanglement swapping leads to further performance improvements. Specifically, using Q-Learning to decide on which segments to proactively swap leads to 52.55% and 41.79% improvement for REPS and SEER algorithms, respectively. Deep Q-Learning outperforms Q-Learning with 61.43% and 48.27% improvements rates.
Entanglement generation in long-distance quantum networks is challenging because resources are limited and entanglement swapping is probabilistic. To maximize the rate of successful requests, existing quantum routing algorithms often rely on computationally expensive methods such as Integer Linear Programming (ILP) to determine which links to entangle and use for end-to-end entanglement generation. However, these approaches fail to meet the latency requirements of real-world quantum networks. In this study, we propose a Reinforcement Learning (RL)-based model that determines which links to entangle in each time slot, replacing the slow ILP-based link-selection phase used in prior algorithms. The proposed Deep Q-learning model is up to 19.2× faster than linear programming in link-selection while maintaining comparable routing performance. The RL link-selection model alone matches ILP in request success rate; combining RL link selection with entanglement caching and proactive swapping raises throughput by up to 52.55% over ILP. Overall, our approach achieves success rates exceeding state-of-the-art solutions while reducing execution time by more than an order of magnitude. Experiments on a synthetic 50-node Waxman topology and the real-world 54-node SURFnet core topology confirm that these gains generalize across network structures, providing a practical path toward scalable quantum routing.