Performance studies of evolutionary transfer learning for end-to-end QoT estimation in multi-domain optical networks [Invited]
Performance studies of evolutionary transfer learning for end-to-end QoT estimation in multi-domain optical networks [Invited]
复制标题
进化迁移学习在多域光网络端到端QoT估计中的性能研究[邀请]
DOI：
10.1364/jocn.409817
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Xiaoliang Chen;Che-Yu Liu;R. Proietti;S. Yoo
中科院分区：
文献类型：
--
作者：
Xiaoliang Chen;Che-Yu Liu;R. Proietti;S. Yoo
针对多域弹性光网络（MD-EONs）中可扩展传输质量（QoT）估计问题，提出了一种进化迁移学习方法（evolution - tl）。evoll - tl利用基于代理的MD-EON架构，支持代理平面（端到端）和域级（本地）机器学习功能之间的协作学习，同时确保每个域的自治。我们设计了一种遗传算法来优化神经网络架构和在源任务和目标任务之间传递的权重集。我们通过三个案例研究评估了evoll - tl的性能，考虑了(i)不同路径长度（就所穿越的光纤链路数量而言）、（ii）不同调制格式和（iii）不同设备条件（通过向放大器引入不同级别的波长特定衰减来模拟）的光路QoT估计任务。结果表明，该方法可将所需训练数据的平均数量减少高达$13× $13×，同时达到95%以上的估计精度。
This paper proposes an evolutionary transfer learning approach (Evol-TL) for scalable quality-of-transmission (QoT) estimation in multi-domain elastic optical networks (MD-EONs). Evol-TL exploits a broker-based MD-EON architecture that enables cooperative learning between the broker plane (end-to-end) and domain-level (local) machine learning functions while securing the autonomy of each domain. We designed a genetic algorithm to optimize the neural network architectures and the sets of weights to be transferred between the source and destination tasks. We evaluated the performance of Evol-TL with three case studies considering the QoT estimation task for lightpaths with (i) different path lengths (in terms of the numbers of fiber links traversed), (ii) different modulation formats, and (iii) different device conditions (emulated by introducing different levels of wavelength-specific attenuation to the amplifiers). The results show that the proposed approach can reduce the average amount of required training data by up to $13 \times$13× while achieving an estimation accuracy above 95%.