Distance and spectral power profile shaping using machine learning enabled Raman amplifiers

Soltani, Mehran; Ros, Francesco Da; Carena, Andrea; Zibar, Darko

doi:10.1109/sum48717.2021.9505741

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raman amplifiers have lately attracted fresh interest as a result of their ability to amplify broadband signals by the assistance of ML when used in a multi-pump laser arrangement [ 218 ]. In addition, they have reduced noise when using distributed amplifiers and ML [ 219 ]. The Raman amplifiers’ capacity to arbitrarily set the gain by varying the pump power and wavelength is another distinctive quality improved by ML [ 220 ].…”

Section: Nlo Processes Analyzed With MLmentioning

confidence: 99%

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning

et al. 2022

View full text Add to dashboard Cite

The ability to interpret information through automatic sensors is one of the most important pillars of modern technology. In particular, the potential of biosensors has been used to evaluate biological information of living organisms, and to detect danger or predict urgent situations in a battlefield, as in the invasion of SARS-CoV-2 in this era. This work is devoted to describing a panoramic overview of optical biosensors that can be improved by the assistance of nonlinear optics and machine learning methods. Optical biosensors have demonstrated their effectiveness in detecting a diverse range of viruses. Specifically, the SARS-CoV-2 virus has generated disturbance all over the world, and biosensors have emerged as a key for providing an analysis based on physical and chemical phenomena. In this perspective, we highlight how multiphoton interactions can be responsible for an enhancement in sensibility exhibited by biosensors. The nonlinear optical effects open up a series of options to expand the applications of optical biosensors. Nonlinearities together with computer tools are suitable for the identification of complex low-dimensional agents. Machine learning methods can approximate functions to reveal patterns in the detection of dynamic objects in the human body and determine viruses, harmful entities, or strange kinetics in cells.

show abstract

Section: Nlo Processes Analyzed With MLmentioning

confidence: 99%

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, recent development of fast and accurate models and algorithms have enabled its computation, including global optimisation algorithms such as evolutionary algorithms (EA) [17,18], particle swarm optimisation (PSO) [19], artificial neural network (ANN) [20] and faster but sub-optimal strategies [21]. Most importantly, the speed of these algorithms has been improved through analytical [22,23], numerical [24,25], or even ANN [26,27] models that estimate the NLI in the presence of ISRS. These works have all assumed an ideal transceiver subsystem (TRX), and do not allow for the assessment of the impact of TRX noise on the per-channel QoT in the presence of ISRS.…”

Section: Introductionmentioning

confidence: 99%

On the impact of launch power optimization and transceiver noise on the performance of ultra-wideband transmission systems [Invited]

Galdino

Blugia

Sillekens

et al. 2022

J. Opt. Commun. Netw.

View full text Add to dashboard Cite

Ultra-wideband transmission is a promising, cost-effective solution to meet the increasing demand for data traffic in optical fiber systems. However, system performance and quality of transmission (QoT) are limited by fiber nonlinearity, in particular, interchannel stimulated Raman scattering (ISRS), leading to a power transfer from short to long wavelengths. As the result, per-channel launch power optimization is required to maximize the system throughput. In this paper, we investigate how the transceiver noise and launch power optimization impact the total throughput and the per-channel QoT for transmission bandwidths of up to 20 THz, using the S-, C-, and L-bands. To measure the gains through the optimum launch power profile, a spectrally uniform launch power is used as a baseline. Through experimental analysis and theoretical modeling, the main limitations constraining the achieved data throughput of 178 Tb/s over a continuous bandwidth of 16.83 THz and 40 km were investigated. The impact of the launch power optimization and the transceiver constrained signal-to-noise ratio (SNR) are analyzed and compared, and the approaches to overcome data throughput limitations are considered. An extensive theoretical investigation for different system configurations is described, demonstrating the trade-off between ISRS impact and transceiver noise. The former degrades the QoT and increases the gains in performance obtained by optimizing the launch power, while the latter reduces these gains and the SNR variation across the bandwidth, with a major impact over short distances.

show abstract

Distance and spectral power profile shaping using machine learning enabled Raman amplifiers

Cited by 2 publications

References 9 publications

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning

A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning

On the impact of launch power optimization and transceiver noise on the performance of ultra-wideband transmission systems [Invited]

Contact Info

Product

Resources

About