In this work, a new data-driven fiber channel modeling method, generative adversarial network (GAN) is investigated to learn the distribution of fiber channel transfer function. Our investigation focuses on joint channel effects of attenuation, chromic dispersion, self-phase modulation (SPM), and amplified spontaneous emission (ASE) noise. To achieve the success of GAN for channel modeling, we modify the loss function, design the condition vector of input and address the mode collapse for the long-haul transmission. The effective architecture, parameters, and training skills of GAN are also displayed in the paper. The results show that the proposed method can learn the accurate transfer function of the fiber channel. The transmission distance of modeling can be up to 1000 km and can be extended to arbitrary distance theoretically. Moreover, GAN shows robust generalization abilities under different optical launch powers, modulation formats, and input signal distributions. Comparing the complexity of GAN with the split-step Fourier method (SSFM), the total multiplication number is only 2% of SSFM and the running time is less than 0.1 seconds for 1000-km transmission, versus 400 seconds using the SSFM under the same hardware and software conditions, which highlights the remarkable reduction in complexity of the fiber channel modeling.

中文翻译：

---

使用生成对抗网络进行快速准确的光纤通道建模

在这项工作中，研究了一种新的数据驱动的光纤通道建模方法，生成对抗网络（GAN）来学习光纤通道传递函数的分布。我们的研究侧重于衰减、色散、自相位调制 (SPM) 和放大自发辐射 (ASE) 噪声的联合通道效应。为了实现 GAN 在信道建模方面的成功，我们修改了损失函数，设计了输入的条件向量并解决了长途传输的模式崩溃问题。论文中还展示了 GAN 的有效架构、参数和训练技巧。结果表明，该方法能够准确地学习光纤通道的传递函数。建模传输距离可达1000公里，理论上可以扩展到任意距离。而且，GAN 在不同的光发射功率、调制格式和输入信号分布下显示出强大的泛化能力。将 GAN 的复杂度与分步傅立叶方法 (SSFM) 进行比较，总乘法次数仅为 SSFM 的 2%，1000 公里传输的运行时间小于 0.1 秒，而在相同条件下使用 SSFM 的运行时间为 400 秒硬件和软件条件，这突出了光纤通道建模复杂性的显着降低。