基于机器学习辅助物理受激拉曼散射模型的灵活拉曼放大器优化
信号处理
2022-06-16 v1 机器学习
摘要
研究了拉曼放大器优化问题。利用机器学习（ML）获得了拉曼增益系数的可微插值函数，从而允许对前向传播的拉曼泵浦进行梯度下降优化。随后，针对任意数据信道负载和跨段长度，优化了前向泵浦配置中任意数量泵浦的频率和功率。将前向传播模型与实验训练的向后泵浦拉曼放大器的ML模型相结合，以联合优化前向放大器泵浦的频率和功率以及后向放大器泵浦的功率。联合前向和后向放大器优化在无中继250 km传输中得到了验证。在4 THz上实现了<1 dB的增益平坦度。使用数值模拟器对优化后的放大器进行了验证。
引用
@article{arxiv.2206.07650,
title = {Flexible Raman Amplifier Optimization Based on Machine Learning-aided Physical Stimulated Raman Scattering Model},
author = {Metodi Plamenov Yankov and Francesco Da Ros and Uiara Celine de Moura and Andrea Carena and Darko Zibar},
journal= {arXiv preprint arXiv:2206.07650},
year = {2022}
}
备注
submitted to Journal of Lightwave Technology. Extended version of the previous conference paper M. Yankov, D. Zibar, A. Carena, and F. Da Ros, "Forward Raman amplifier optimization using machine learning-aided physical modeling," accepted, Optoelectronics and Communications Conference (OECC), 2022