Nonlinear compensation in multi-channel 400ZR-based optical interconnects employing deep learning techniques

• Grant number: 25/18015-1
• Support Opportunities: Scholarships in Brazil - Master
• Start date: February 01, 2026
• End date: January 31, 2028
• Field of knowledge: Engineering - Electrical Engineering - Telecommunications
• Principal Investigator: Ivan Aritz Aldaya Garde
• Grantee: João Pedro Innocente Gosmin
• Host Institution: Faculdade de Engenharia. Universidade Estadual Paulista (UNESP). Campus São João da Boa Vista. São João da Boa Vista , SP, Brazil
• Associated research grant: 24/01712-9 - Compensation for transmission impairments in advanced optical communication systems employing artificial intelligence, AP.R

Abstract

The growing demand for high-capacity, energy-efficient optical interconnects has led to the widespread adoption of the 400 ZR and 400 ZR+ standards in short-reach, high-speed communication links. While these systems benefit from advanced digital signal processing, their performance is still constrained by nonlinear distortion in optical fibers. In particular, nonlinear intersymbol interference (ISI) significantly degrades performance in multichannel 400 ZR+-like wavelength-division multiplexing (WDM) systems. This project investigates deep learning-based nonlinear equalization techniques for 4-channel WDM 400 ZR-like systems, comparing single-channel and joint multi-channel processing. The proposed approach employs a sequentialized multi-layer perceptron (S-MLP) architecture, optimized via multi-objective hyperparameter tuning to balance bit error ratio (BER) reduction and computational complexity. The methodology involves simulating realistic transmission scenarios using VPI Photonics, implementing the S-MLP in TensorFlow/Keras, and assessing performance through Pareto front analysis. The results will provide guidelines on the conditions under which multi-channel compensation offers unconditional or conditional superiority over single-channel schemes, enabling more efficient design of next-generation optical interconnects. (AU)