Journal
JOURNAL OF LIGHTWAVE TECHNOLOGY
Volume 39, Issue 4, Pages 1162-1170Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JLT.2020.3036603
Keywords
Stimulated emission; Gain; Optical pumping; Optimization; Pump lasers; Nonlinear optics; Adaptive optics; Machine learning; neural networks; optical amplifiers; optical communications
Funding
- European Research Council through the ERC-CoG FRECOM Project [771878]
- European Union [754462]
- Villum Foundations [29344]
Ask authors/readers for more resources
Optical communication systems are evolving to meet the increasing demand for transmission rates, with a versatile machine learning framework demonstrated for designing and modeling Raman amplifiers. Thorough experimental characterization on practical fiber types showed the framework's applicability and accuracy.
Optical communication systems are always evolving to support the need for ever-increasing transmission rates. This demand is supported by the growth in complexity of communication systems which are moving towards ultra-wideband transmission and space-division multiplexing. Both directions will challenge the design, modeling, and optimization of devices, subsystems, and full systems. Amplification is a key functionality to support this growth and in this context, we recently demonstrated a versatile machine learning framework for designing and modeling Raman amplifiers with arbitrary gains. In this article, we perform a thorough experimental characterization of such machine learning framework. The applicability of the proposed approach, as well as its ability to accurately provide flat and tilted gain-profiles, are tested on several practical fiber types, showing errors below 0.5 dB. Moreover, as channel power optimization is heavily employed to further enhance the transmission rate, the tolerance of the framework to variations in the input signal spectral profile is investigated. Results show that the inverse design can provide highly accurate gain-profile adjustments for different input signal power profiles even not considering this information during the training phase.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available