A Silicon Photonic Neural Network for Chromatic Dispersion Compensation in 20 Gbps PAM4 Signal at 125 km and Its Scalability up to 100 Gbps

TL;DR

This paper demonstrates a silicon photonic neural network that effectively compensates for chromatic dispersion in optical links, achieving high data rates up to 20 Gbps over 125 km and showing potential scalability to 100 Gbps.

Contribution

It introduces a silicon photonic neural network architecture for dispersion compensation, combining linear and nonlinear stages, with experimental validation and scalability analysis.

Findings

Effective dispersion compensation at 20 Gbps over 125 km

Comparison of training algorithms for neural network optimization

Scalability study indicating potential for 100 Gbps transmission

Abstract

A feed-forward photonic neural network (PNN) is tested for chromatic dispersion compensation in Intensity Modulation/Direct Detection optical links. The PNN is based on a sequence of linear and nonlinear transformations. The linear stage is constituted by an 8-tap time-delayed complex perceptron implemented on a Silicon-On-insulator platform and acting as a tunable optical filter. The nonlinear stage is provided by the square modulus of the electrical field applied at the end-of-line photodetector. The training maximizes the separation between the optical levels (i.e. the eye diagram aperture), with consequent reduction of the Bit Error Rate. Effective equalization is experimentally demonstrated for 20 Gbps 4-level Pulse Amplitude Modulated signal up to 125 km. An evolutionary algorithm and a gradient-based approach are tested for the training and then compared in terms of repeatability and convergence time. The optimal weights resulting from the training are interpreted in light of the theoretical transfer function of the optical fiber. Finally, a simulative study proves the scalability of the layout to larger bandwidths, up to 100 Gbps.