Design of Time-Domain Learned Volterra Equalisers for WDM Systems

• Published in: 2024 International Conference on Optical Network Design and Modeling (ONDM) pp. 1 - 3
• Main Authors: Castro, Nelson, Boscolo, Sonia, Ellis, Andrew D., Sygletos, Stylianos
• Format: Conference Proceeding
• Language: English
• Published: IFIP 06-05-2024
• Subjects: machine learning; MIMO communication; nonlinearity equalisation; Optical fiber networks; Optical fibers; optical fibre systems; Optimization; Scalability; Time-domain analysis; Volterra series; Wavelength division multiplexing
• DOI: 10.23919/ONDM61578.2024.10582691

We examine various design aspects of a learned time-domain multiple-input multiple-output (MIMO) Volterra-based equaliser and reveal their impact on the convergence and performance of the model. We show that appropriate parameter initialisation is vital for the model's convergence and scalability to a higher number of channels. This design optimisation enables the first demonstration of a 7 × 7 operation of the MIMO algorithm at one step per span, achieving 1.5 dB effective signal-to-noise ratio improvement over single-channel nonlinear equalisation, hence significantly enhancing the transmission performance in a wavelength-division multiplexing scenario.