Experimental demonstration of arbitrary Raman gain–profile designs using machine learning

Moura, Uiara Celine de; Ros, Francesco Da; Brusin, Ann Margareth Rosa; Carena, Andrea; Zibar, Darko

doi:10.1364/ofc.2020.t4b.2

Cited by 7 publications

(4 citation statements)

References 9 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we extend our recent work [19], where the machine learning (ML) framework proposed by [16], [17] is experimentally evaluated in many practical scenarios. In [19], the ML framework was extensively investigated over distributed and discrete counter-propagating Raman amplifiers with different fiber types and lengths. Results show maximum errors between target and designed gain-profiles below 0.5 dB for 80% of the evaluated cases.…”

Section: Introductionmentioning

confidence: 96%

“…Results show maximum errors between target and designed gain-profiles below 0.5 dB for 80% of the evaluated cases. As a complementary result for [19], in this work we test the ML framework ability in achieving flat and tilted gain-profiles. Results show a maximum of 0.5 dB of deviation from target gain-profiles for all investigated Raman amplifiers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Experimental Characterization of Raman Amplifier Optimization Through Inverse System Design

Moura

Ros

Brusin

et al. 2021

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

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 paper, 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.

show abstract

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Experimental Characterization of Raman Amplifier Optimization Through Inverse System Design

Moura

Ros

Brusin

et al. 2021

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several solutions to this optimization problem have been reported in the literature but have mainly focused on realizing flat gain profiles [24]- [32]. Recently, a machine learning framework for the ultra-fast configuration of the pump powers and wavelengths has been theoretically proposed and as a proof-of-principle experimentally demonstrated in Cband only [33], [34]. The proposed approach can be used for the design of Raman amplifiers, where an arbitrary gain profile is achievable in a controlled way.…”

mentioning

confidence: 99%

“…The previous experimental results that we have published in [33], [34] were limited to the C-band only. Increasing the bandwidth from C to S+C+L-band (a factor of 4.4 for the considered case) is highly-challenging.…”

mentioning

confidence: 99%

Multi–Band Programmable Gain Raman Amplifier

Moura

Iqbal

Kamalian

et al. 2021

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

Optical communication systems, operating in C-band, are reaching their theoretically achievable capacity limits. An attractive and economically viable solution to satisfy the future data rate demands is to employ the transmission across the full low-loss spectrum encompassing O, E, S, C and L band of the single mode fibers (SMF). Utilizing all five bands offers a bandwidth of up to ∼53.5 THz (365 nm) with loss below 0.4 dB/km. A key component in realizing multi-band optical communication systems is the optical amplifier. Apart from having an ultra-wide gain profile, the ability of providing arbitrary gain profiles, in a controlled way, will become an essential feature. The latter will allow for signal power spectrum shaping which has a broad range of applications such as the maximization of the achievable information rate × distance product, the elimination of static and lossy gain flattening filters (GFF) enabling a power efficient system design, and the gain equalization of optical frequency combs. In this paper, we experimentally demonstrate a multiband (S+C+L) programmable gain optical amplifier using only Raman effects and machine learning. The amplifier achieves >1000 programmable gain profiles within the range from 3.5 to 30 dB, in an ultra-fast way and a very low maximum error of 1.6 • 10 −2 dB/THz over an ultrawide bandwidth of 17.6-THz (140.7-nm). Index Terms-optical communications, multi-band systems, optical amplifiers, machine learning, neural networks. I. INTRODUCTION O VER the past two decades, a great evolution of optical communication systems, in terms of spectral efficiency×distance product, has been enabled by the advances in digital coherent detection. So far, most of the efforts, on reaching the capacity of the nonlinear fiber-optic channel, have been focusing on the C-band

show abstract

Machine Learning Assisted Hybrid EDFA-Raman Amplifier Design for C+L Bands

Ionescu

Ghazisaeidi

Renaudier

2020

2020 European Conference on Optical Communications (ECOC)

View full text Add to dashboard Cite

Experimental demonstration of arbitrary Raman gain–profile designs using machine learning

Abstract: A machine learning framework for Raman amplifier design is experimentally tested. Performance in terms of maximum error over the gain profile is investigated for various fiber types and lengths, demonstrating highly-accurate designs.

Cited by 7 publications

References 9 publications

Experimental Characterization of Raman Amplifier Optimization Through Inverse System Design

Experimental Characterization of Raman Amplifier Optimization Through Inverse System Design

Multi–Band Programmable Gain Raman Amplifier

Machine Learning Assisted Hybrid EDFA-Raman Amplifier Design for C+L Bands

Contact Info

Product

Resources

About