56-Gbit/s PAM-4 Optical Signal Transmission Over 100-km SMF Enabled by TCNN Regression Model

Abstract

Due to the interaction between chromatic dispersion (CD) and direct detection, the CD induced power-fading effect has been considered as the key point to limit transmission rate and distance in intensity modulation direct-detection (IM/DD) systems. Besides, the performance of the IM/DD systems will be further affected by the bandwidth limitation and nonlinearity effect. In this paper, we propose a low complexity nonlinear equalizer (NLE) based on temporal convolutional neural network (TCNN) regression model which combines dilated convolutions with residual connections. Then, the performance of our proposed equalizer is experimentally demonstrated in 56-Gbit/s 4-level pulse amplitude modulation (PAM4) intensity modulation direct-detection system. The results show that the receiver sensitivity with the help of our TCNN equalizer can be improved about 1.5 dB and 3.5 dB compared to 2D-CNN and 1D-CNN equalizer under 70-km single mode fiber (SMF) transmission. Furthermore, the proposed equalizer can extend maximum transmission distance to 100 km at bit error rate threshold of 3.8×10 -3 .

The Algorithm Accuracy of Mathematical Model to Improve the Transmission Speed of E-commerce Platform

“…We determine the basic structure under the dynamic transmission control of the network according to the synchronous control full-slave scheme [9]. Assuming that there is no packet loss problem in the signal transmission of the arrayed e-commerce platform in the asymmetric coupling network, there is the following formula:  represents the initial condition at the time parameter 0 t  .…”

Next-Generation Passive Optical Network Based on Sparse Code Multiple Access and Graph Neural Networks

“…In optical communications, machine learning has been considered as a powerful nonlinear decision classifier to decode the distorted signals by inverting the effects of linear and nonlinear distortions. Various machine learning methods are proposed to extract the features of Euclidean data and achieve great success [17]- [22]. Graph Neural Network (GNN), as a deep learning method that operates on graph domain, has been widely concerned and adopted in non-Euclidean data structures [23]- [26].…”