DNN-assisted optical geometric constellation shaped PSK modulation for PAM4-to-QPSK format conversion gateway node

TL;DR

This paper introduces a DNN-assisted optical gateway that converts PAM4 signals to QPSK format with improved efficiency and performance, utilizing geometric constellation shaping and non-uniform phase noise management.

Contribution

It presents a novel optical modulation conversion method using neural networks for decision-making, achieving better BER and mutual information in a proof-of-principle experiment.

Findings

1 dB BER improvement with neural network-based signal recovery

Successful demonstration of PAM4 to QPSK conversion with geometric constellation shaping

Enhanced mutual information in the generated QPSK signals

Abstract

An optical gateway to convert four-level pulse amplitude modulation to quadrature phase shift keying modulation format having shaping gain was proposed for flexible intensity to phase mapping which exploits non-uniform phase noise. The power consumption of the optical modulation format conversion can save by making a DNN-based decision on the receiver side for the generated QPSK signal with non-uniform phase noise. A proof-of-principle experiment has shown that an optically geometric constellation shaped QPSK modulated signals generated from regular PAM4 signals with Gaussian-distributed noise. The shaped QPSK signal shows BER and generalized mutual information improvement by 1dB gain through the use of digital neural network signal recovery.