Adaptive Entanglement Generation for Quantum Routing

2025-05-13

AI Summary

To address the challenge of establishing end-to-end entanglement in long-distance quantum networks—where resource constraints and low entanglement swapping success rates severely limit performance—this paper proposes a real-time adaptive quantum routing framework. Methodologically, it introduces a novel two-phase optimization mechanism: “caching unused entanglement” combined with “proactive swapping,” and is the first to integrate deep reinforcement learning (DRL) into quantum routing. The DRL agent jointly models dynamic routing decisions, entanglement-lifetime-aware caching, and proactive swapping on high-demand path segments. Compared to conventional linear programming approaches, the framework achieves a 20× speedup in computation time; its caching strategy improves throughput by 10–15% over existing algorithms; and with proactive swapping enabled, request success probability increases by up to 52.55%. The solution thus significantly balances real-time responsiveness and entanglement delivery reliability.

Technology Category

• Planning, Routing, and Scheduling: Routing
• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

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%.

Problem

• Optimizing entanglement generation in quantum networks efficiently
• Reducing delay in real-time quantum routing decisions
• Improving success rates via entanglement caching and proactive swapping

Innovation

• Reinforcement learning optimizes quantum link entanglement.
• Caching entangled links boosts routing performance.
• Proactive swapping increases request success rate.