论文标题
柔性拉曼放大器优化基于机器学习辅助物理刺激的拉曼散射模型
Flexible Raman Amplifier Optimization Based on Machine Learning-aided Physical Stimulated Raman Scattering Model
论文作者
论文摘要
研究了拉曼放大器优化的问题。使用机器学习（ML）获得了Raman增益系数的可区分插值函数，该功能允许对前向传播拉曼泵的梯度下降优化。然后，针对任意数据通道负载和跨度长度优化了向前泵送配置中任意数量的泵的频率和功率。向前倾斜的拉曼放大器的实验训练的ML模型将正向传播模型结合在一起，以共同优化向前放大器泵的频率和功率以及向后放大器泵的功率。展示了连接前后的放大器优化，用于250 km的未经疗法的传输。超过4 THz的增益平坦度为$ <$ 1〜 dB。使用数值模拟器验证了优化的放大器。
The problem of Raman amplifier optimization is studied. A differentiable interpolation function is obtained for the Raman gain coefficient using machine learning (ML), which allows for the gradient descent optimization of forward-propagating Raman pumps. Both the frequency and power of an arbitrary number of pumps in a forward pumping configuration are then optimized for an arbitrary data channel load and span length. The forward propagation model is combined with an experimentally-trained ML model of a backward-pumping Raman amplifier to jointly optimize the frequency and power of the forward amplifier's pumps and the powers of the backward amplifier's pumps. The joint forward and backward amplifier optimization is demonstrated for an unrepeatered transmission of 250 km. A gain flatness of $<$ 1~dB over 4 THz is achieved. The optimized amplifiers are validated using a numerical simulator.
