Wiener-Hammerstein model and its learning for nonlinear digital pre-distortion of optical transmitters

TL;DR

This paper introduces a Wiener-Hammerstein model-based digital pre-distortion method for optical transmitters, leveraging neural network-like structures for efficient nonlinear compensation, validated through experiments showing significant SNR and power gains.

Contribution

It proposes a novel Wiener-Hammerstein model for optical transmitter pre-distortion, combining machine learning optimization techniques for improved nonlinear compensation.

Findings

Achieves 0.52-dB SNR gain in experiments.

Provides 6.0-dB increase in optical power at fixed SNR.

Demonstrates effectiveness of the model in optical communication systems.

Abstract

We present a simple nonlinear digital pre-distortion (DPD) of optical transmitter components, which consists of concatenated blocks of a finite impulse response (FIR) filter, a memoryless nonlinear function and another FIR filter. The model is a Wiener-Hammerstein (WH) model and has essentially the same structure as neural networks or multilayer perceptions. This awareness enables one to achieve complexity-efficient DPD owing to the model-aware structure and exploit the well-developed optimization scheme in the machine learning field. The effectiveness of the method is assessed by electrical and optical back-to-back (B2B) experiments, and the results show that the WH DPD offers a 0.52-dB gain in signal-to-noise ratio (SNR) and 6.0-dB gain in optical modulator output power at a fixed SNR over linear-only DPD.