Experimental validation of machine-learning based spectral-spatial power evolution shaping using Raman amplifiers

TL;DR

This paper demonstrates a real-time machine learning framework that controls Raman amplifier pump powers to shape 2D power profiles with high accuracy, validated through experiments and simulations.

Contribution

It introduces a combined CNN and differential evolution approach for online optimization of Raman amplifier pump powers to achieve precise 2D power shaping.

Findings

Achieves less than 0.5 dB MAE in 2D power profile control.

Attains less than 1 dB gain deviation in flat gain scenarios.

Simulation shows potential for less than 0.6 dB deviation with sufficient pump power.

Abstract

We experimentally validate a real-time machine learning framework, capable of controlling the pump power values of Raman amplifiers to shape the signal power evolution in two-dimensions (2D): frequency and fiber distance. In our setup, power values of four first-order counter-propagating pumps are optimized to achieve the desired 2D power profile. The pump power optimization framework includes a convolutional neural network (CNN) followed by differential evolution (DE) technique, applied online to the amplifier setup to automatically achieve the target 2D power profiles. The results on achievable 2D profiles show that the framework is able to guarantee very low maximum absolute error (MAE) (<0.5 dB) between the obtained and the target 2D profiles. Moreover, the framework is tested in a multi-objective design scenario where the goal is to achieve the 2D profiles with flat gain levels at the end of the span, jointly with minimum spectral excursion over the entire fiber length. In this case, the experimental results assert that for 2D profiles with the target flat gain levels, the DE obtains less than 1 dB maximum gain deviation, when the setup is not physically limited in the pump power values. The simulation results also prove that with enough pump power available, better gain deviation (less than 0.6 dB) for higher target gain levels is achievable.