Overcoming fiber nonlinearity is one of the most challenging tasks in optical fiber links and it is a major limiting factor for extending their capacity. Digital backward propagation (DBP) method can be used to mitigate nonlinear transmission impairments  , but its complexity prevents any real-time implementation in these systems. On the other hand, it has been recently shown that deep neural networks can provide a good approximation of DBP at lower computational cost  . In this work, we continue the investigation of the proposed deep convolutional neural network (DCNN)  for long-haul WDM transmission systems. We study the effect of the number of neural network layers on the efficiency of nonlinear distortion compensation.
|Title of host publication||The European Conference on Lasers and Electro-Optics, CLEO/Europe 2021|
|Publisher||The Optical Society|
|Number of pages||1|
|Publication status||Published - 30 Sep 2021|
|Event||2021 European Conference on Lasers and Electro-Optics, CLEO/Europe 2021 - Virtual, Online, Germany|
Duration: 21 Jun 2021 → 25 Jun 2021
|Name||Optics InfoBase Conference Papers|
|Conference||2021 European Conference on Lasers and Electro-Optics, CLEO/Europe 2021|
|Period||21/06/21 → 25/06/21|
Bibliographical noteFunding Information:
The work was supported by the Russian Science Foundation (Grant No. 17-72-30006).