MZM nonlinear equalization by sinusoidal subcarrier modulation combined with LM-BP neural network

Abstract

In order to mitigate the nonlinear effects of Mach-Zehnder modulator (MZM) on optical transmission signals in intensity modulation and direct detection (IM-DD) systems, a combined approach utilizing sinusoidal subcarrier modulation (SSM) and the Levenberg-Marquardt back propagation (LM-BP) neural network is proposed in this paper. The method employs a sine wave as the subcarrier to carry the 4 pulse amplitude modulation (PAM4) signals, aiming to equalize the distorted signals after MZM modulation. Subsequently, the LM-BP algorithm eliminates any remaining inter-symbol interference (ISI). This scheme uses sine wave modulation to solve the problem of additional ISI caused by triangular wave modulation. Furthermore, this combined approach simplifies the algorithm complexity compared to solely relying on a neural network equalizer. In this paper, the performance of SSM-LM-BP scheme is simulated and analyzed in IM-DD system. The results show that the joint scheme outperforms the triangular wave modulation scheme as well as the neural network algorithm after transmitting 50 Gbit/s PAM4 signals for 80 km without relays under the conditions of dispersion compensation, and the symbol error rate (SER) can be as low as 10⁻⁵.

References

[[1]] Zhou J, Wang H D, Wei J L, et al.. Adaptive moment estimation for polynomial nonlinear equalizer in PAM8-based optical interconnects. Optics express, 2019, 27(22): 32210-32216, J]

[[2]] Nebojsa S, Fotini K, Zhang Q, et al.. Volterra and wiener equalizers for short-reach 100G PAM-4 applications. Journal of lightwave technology, 2017, 35(21): 4583-4594, J]

[[3]] Giacoumidis E, Wei J L, Mhatli S, et al.. Nonlinear inter-subcarrier intermixing reduction in coherent optical OFDM using fast machine learning equalization. 2017 Optical Fiber Communications Conference and Exhibition: OFC 2017, March 19–23, 2017, Los Angeles, California, USA, 2017 New York IEEE W3J.2 [C]

[[4]] Fu J J, Ahi Z, Zhang Z F. 128 Gbit/s high speed optical interconnection networks in data centers by a 30 GHz Mach-Zehnder modulator. Optoelectronics letters, 2023, 19(1): 36-40, J]

[[5]] Navid H, Aditya J, Roger H, et al.. A distributed low-noise amplifier for broadband linearization of a silicon photonic Mach-Zehnder modulator. IEEE journal of solid-state circuits, 2021, 56(6): 1897-1909, J]

[[6]] Zhou Z Y, Zhang Q. A scheme for suppressing non-linear influence of Mach-Zehnder modulatorin RoF system. Journal of optoelectronics·laser, 2021, 32(3): 223-230 [J]

[[7]] Luo Y L, Rady R, Entesari K, et al.. A power-efficient 20–35-GHz MZM driver with programmable linearizer for analog photonic links in 28-nm CMOS. IEEE transactions on microwave theory and techniques, 2023, 71(3): 1262-1273, J]

[[8]] Li L, Liu R, Sun Y D. A nonlinear equalization for a PAM4 IM-DD system using MZM. Optoelectronics letters, 2022, 18(4): 238-242, J]

[[9]] Lyubomirsky I, Ling W. Advanced modulation for datacenter interconnect. 2016 Optical Fiber Communications Conference and Exhibition, March 20–24, 2016, Anaheim, California, USA, 2016 New York IEEE w4j3 [C]

[[10]] Nebojsa S, Zhang Q, Cristian P, et al.. Performance and DSP complexity evaluation of a 112-Gbit/s PAM-4 transceiver employing a 25-GHz TOSA and ROSA. 2015 European Conference on Optical Communication (ECOC), September 27–October 1, 2015, Valencia, Spain, 2015 New York IEEE 7341947 [C]

[[11]] Ye C, Zhang D G, Huang X A, et al.. Demonstration of 50Gbps IM-DD PAM4 PON over 10GHz class optics using neural network based nonlinear equalization. 2017 European Conference on Optical Communication (ECOC), September 17–21, 2017, Gothenburg, Sweden, 2017 New York IEEE 8346196 [C]

[[12]] Zhang J, Jiang L, Luo B, et al.. 56-Gbit/s PAM-4 optical signal transmission over 100-km SMF enabled by TCNN regression model. IEEE photonics journal, 2021, 13(4): 1-6 [J]

[[13]] Reza A G, Rhee J K K. Nonlinear equalizer based on neural networks for PAM-4 signal transmission using DML. IEEE photonics technology letters, 2018, 30(15): 1416-1419, J]

[[14]] Wang S B, Yuan W H, Zhou J W. Analysis of runoff coefficient prediction based on LM-BP neural network. Journal of physics: conference series, 2022, 2333: 012020 [J]