Fast fiber nonlinearity compensation method for PDM coherent optical transmission systems based on the Fourier neural operator.

Abstract

Fiber nonlinearity compensation (NLC) is likely to become an indispensable component of coherent optical transmission systems for extending the transmission reach and increasing capacity per fiber. In this work, we introduce what we believe to be a novel fast black-box neural network model based on the Fourier neural operator (FNO) to compensate for the chromatic dispersion (CD) and nonlinearity simultaneously. The feasibility of the proposed approach is demonstrated in uniformly distributed as well as probabilistically-shaped 32GBaud 16/32/64-ary quadrature amplitude modulation (16/32/64QAM) polarization-division-multiplexed (PDM) coherent optical communication systems. The experimental results demonstrate that about 0.31 dB Q-factor improvement is achieved compared to traditional digital back-propagation (DBP) with 5 steps per span for PDM-16QAM signals after 1600 km standard single-mode fiber (SSMF) transmission at the optimal launched power of 4 dBm. While, the time consumption is reduced from 6.04 seconds to 1.69 seconds using a central processing unit (CPU), and from 1.54 seconds to only 0.03 seconds using a graphic processing unit (GPU), respectively. This scheme also reveals noticeable generalization ability in terms of launched power and modulation format.