Cho Hyung Joon, Lippiatt Daniel, Thomas Varghese A, Varughese Siddharth, Searcy Steven, Richter Thomas, Tibuleac Sorin, Ralph Stephen E
Opt Express. 2022 Jan 17;30(2):2693-2710. doi: 10.1364/OE.443585.
We demonstrate accurate estimation of generalized optical signal to noise ratio (GOSNR) for wavelength division multiplexed fiber communication systems using an experimentally trained multi-tasking convolutional neural network while simultaneously estimating linear and nonlinear noise contributions. Using dual-polarized 32-GBaud 16QAM DWDM links we extract learnable features from constellation density matrices and accurately estimate GOSNR while simultaneously estimating linear and nonlinear contributions. Estimation of the OSNR, OSNR and GOSNR are demonstrated with < 0.5 dB mean absolute error. We also assess the universality of our model within the regime of metro networks by cross-training with data from such links comprised of different fiber types. We demonstrate a path to a practical universal training method that includes additional link parameters. The methods do not require contiguous high-speed sampling, additional hardware nor transmission of special symbols or patterns and are readily implemented in deployed systems.
我们展示了使用经过实验训练的多任务卷积神经网络对波分复用光纤通信系统的广义光信噪比（GOSNR）进行精确估计，同时估计线性和非线性噪声贡献。利用双偏振32GBaud 16QAM DWDM链路，我们从星座密度矩阵中提取可学习特征，并在同时估计线性和非线性贡献的情况下精确估计GOSNR。OSNR、OSNR和GOSNR的估计平均绝对误差小于0.5dB。我们还通过使用来自不同光纤类型的此类链路的数据进行交叉训练，评估了我们模型在城域网范围内的通用性。我们展示了一种通往实用通用训练方法的途径，该方法包括额外的链路参数。这些方法不需要连续的高速采样、额外的硬件，也不需要传输特殊符号或模式，并且可以很容易地在已部署的系统中实现。
