Physics-Informed Neural Operator for Fast and Scalable Optical Fiber Channel Modelling in Multi-Span Transmission

Autor:	Song, Yuchen, Wang, Danshi, Fan, Qirui, Jiang, Xiaotian, Luo, Xiao, Zhang, Min
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Signal Processing Physics - Optics
Druh dokumentu:	Working Paper
Popis:	We propose efficient modelling of optical fiber channel via NLSE-constrained physics-informed neural operator without reference solutions. This method can be easily scalable for distance, sequence length, launch power, and signal formats, and is implemented for ultra-fast simulations of 16-QAM signal transmission with ASE noise. Comment: accepted by ECOC2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2208.08868 Zobrazit plný text záznamu View this record from Arxiv