We propose an optimization algorithm to improve the design and performance of quantum communication networks. When physical architectures become too complex for analytical methods, numerical simulation becomes essential to study quantum network behavior. Although highly informative, these simulations involve complex numerical functions without known analytical forms, making traditional optimization techniques that assume continuity, differentiability, or convexity inapplicable. Additionally, quantum network simulations are computationally demanding, rendering global approaches like Simulated Annealing or genetic algorithms, which require extensive function evaluations, impractical. We introduce a more efficient optimization workflow using machine learning models, which serve as surrogates for a given objective function. We demonstrate the effectiveness of our approach by applying it to three well-known optimization problems in quantum networking: quantum memory allocation for multiple network nodes, tuning an experimental parameter in all physical links of a quantum entanglement switch, and finding efficient protocol settings within a large asymmetric quantum network. The solutions found by our algorithm consistently outperform those obtained with our baseline approaches -- Simulated Annealing and Bayesian optimization -- in the allotted time limit by up to 18\% and 20\%, respectively. Our framework thus allows for more comprehensive quantum network studies, integrating surrogate-assisted optimization with existing quantum network simulators.

翻译：我们提出一种优化算法，用于改进量子通信网络的设计与性能。当物理架构变得过于复杂而无法采用解析方法时，数值模拟对于研究量子网络行为变得至关重要。尽管这些模拟能提供丰富信息，但它们涉及没有已知解析形式的复杂数值函数，使得传统优化技术（假设连续性、可微性或凸性）不再适用。此外，量子网络模拟计算成本高昂，使得需要大量函数评估的全局方法（如模拟退火或遗传算法）在实际中难以实施。我们引入一种更高效的优化工作流，利用机器学习模型作为给定目标函数的代理。我们通过将该方法应用于量子网络中的三个经典优化问题来证明其有效性：多网络节点的量子存储器分配、量子纠缠交换机所有物理链路中实验参数的调优，以及大型非对称量子网络中高效协议设置的寻优。在限定时间内，我们的算法所找到的解决方案始终优于基线方法（模拟退火和贝叶斯优化）的结果，分别高出高达18%和20%。因此，我们的框架能够实现更全面的量子网络研究，将代理辅助优化与现有量子网络模拟器相结合。