Fiber Transmission Model with Parameterized Inputs based on GPT-PINN Neural Network

TL;DR

This paper introduces a parameterized fiber transmission model using GPT-PINN neural networks that efficiently predicts solutions for various bit rates without retraining, enhancing computational speed and physical accuracy.

Contribution

It develops a universal, parameterized fiber transmission model based on GPT-PINN that eliminates the need for re-training for different input conditions.

Findings

Model accurately predicts fiber transmission for 2Gbps to 50Gbps.

Reduces computational effort compared to traditional models.

Maintains physical consistency across different parameters.

Abstract

In this manuscript, a novelty principle driven fiber transmission model for short-distance transmission with parameterized inputs is put forward. By taking into the account of the previously proposed principle driven fiber model, the reduced basis expansion method and transforming the parameterized inputs into parameterized coefficients of the Nonlinear Schrodinger Equations, universal solutions with respect to inputs corresponding to different bit rates can all be obtained without the need of re-training the whole model. This model, once adopted, can have prominent advantages in both computation efficiency and physical background. Besides, this model can still be effectively trained without the needs of transmitted signals collected in advance. Tasks of on-off keying signals with bit rates ranging from 2Gbps to 50Gbps are adopted to demonstrate the fidelity of the model.