Abstract

The problem of Raman amplifier optimization is studied. A differentiable interpolation function is obtained for the Raman gain coefficient using machine learning (ML), which allows for the gradient descent optimization of forward-propagating Raman pumps. Both the frequency and power of an arbitrary number of pumps in a forward pumping configuration are then optimized for an arbitrary data channel load and span length. The forward propagation model is combined with an experimentally-trained ML model of a backward-pumping Raman amplifier to jointly optimize the frequency and power of the forward amplifier's pumps and the powers of the backward amplifier's pumps. The joint forward and backward amplifier optimization is demonstrated for an unrepeatered transmission of 250 km. A gain flatness of $< $ 1 dB over 4 THz is achieved. The optimized amplifiers are validated using a numerical simulator.

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

Mehran Soltani, Francesco Da Ros, Andrea Carena, and Darko Zibar
Opt. Express 30(25) 45958-45969 (2022)

Intelligent gain flattening in wavelength and space domain for FMF Raman amplification by machine learning based inverse design

Yufeng Chen, Jiangbing Du, Yuting Huang, Ke Xu, and Zuyuan He
Opt. Express 28(8) 11911-11920 (2020)

Simultaneous gain profile design and noise figure prediction for Raman amplifiers using machine learning

Uiara Celine de Moura, Ann Margareth Rosa Brusin, Andrea Carena, Darko Zibar, and Francesco Da Ros
Opt. Lett. 46(5) 1157-1160 (2021)

Machine learning aided optimization for balanced resource allocations in SDM-EONs

Shrinivas Petale and Suresh Subramaniam
J. Opt. Commun. Netw. 15(5) B11-B22 (2023)

Machine learning model with physical constraints for diffuse optical tomography

Yun Zou, Yifeng Zeng, Shuying Li, and Quing Zhu
Biomed. Opt. Express 12(9) 5720-5735 (2021)