Application of Machine Learning Techniques for Amplitude and Phase Noise Characterization

Zibar, Darko; Carvalho, Luis H. H.; Piels, Molly; Doberstein, Andy; Diniz, Júlio C. M.; Nebendahl, B.; Franciscangelis, Carolina; Estaran, Jose; Haisch, H.; González, Neil Guerrero; Oliveira, J. C. R. F.; Monroy, Idelfonso Tafur

doi:10.1109/jlt.2015.2394808

Cited by 47 publications

(32 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For optical communication applications, we use the extended Kalman filter (EKF), which linearizes the measurement equation around the current value of the state vector [15]. It is generally more accurate to use filtering recursion equations specifically formulated for the nonlinear case, such as the particle filter (PF) [10], [16], which we also apply to the laser characterization problem, or the unscented Kalman filter (UKF) [17], [18], though these techniques have increased computational complexity.…”

Section: Semiconductor Laser Phase Tracking In a Bayesian Frameworkmentioning

confidence: 99%

“…Fig. 8 shows the experimental BER performance of polarization multiplexed 28 GBd 16 QAM for an SCL with a Lorentzian linewidth of 500 kHz, 1 GHz relaxation resonance frequency, and 0.1 ns damping factor when demodulated with the decision-directed phase-locked loop, the laser rate equation based Kalman filter, and an EKF that uses a Lorentzian laser model [10]. The DDPLL feedback parameters were optimized to yield the lowest BER: K v = 11e9, τ 1 = τ 2 = 16ns.…”

Section: B Communicationmentioning

confidence: 99%

“…Thus we would expect that taking the unique SCL line structure into account when designing a digital filter for carrier phase recovery (CPR) would yield some improvement in performance. Here, we reformulate the SCL rate equations so that they can be used in a Bayesian filtering context [9], [10]. Bayesian filtering, in this case, provides a framework for recursive estimation of the noise variance (FM noise magnitude), while the SCL rate equations specify the shape of that spectrum.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Laser Rate Equation-Based Filtering for Carrier Recovery in Characterization and Communication

Piels

Olmedo

Xue

et al. 2015

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

Abstract-We formulate a semiconductor laser rate equationbased approach to carrier recovery in a Bayesian filtering framework. Filter stability and the effect of model inaccuracies (unknown or un-useable rate equation coefficients) are discussed. Two potential application areas are explored: laser characterization and carrier recovery in coherent communication. Two rate equation based Bayesian filters, the particle filter and extended Kalman filter, are used in conjunction with a coherent receiver to measure frequency noise spectrum of a photonic crystal cavity laser with less than 20 nW of fiber-coupled output power. The extended Kalman filter is also used to recover a 28 GBd DP-16 QAM signal where a decision-directed phase-locked loop fails.

show abstract

Section: Semiconductor Laser Phase Tracking In a Bayesian Frameworkmentioning

confidence: 99%

Section: B Communicationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Laser Rate Equation-Based Filtering for Carrier Recovery in Characterization and Communication

Piels

Olmedo

Xue

et al. 2015

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Conventional time-domain approaches perform coherent detection in combination with digital signal processing (DSP) to cope with this issue [60,61], but as higher order modulation formats are implemented, the accuracy of the phase noise estimation is compromised in the presence of moderate measurement noise. Zibar et al [46] present a framework of Bayesian filtering in combination with expectation maximization (EM) to accurately characterize laser amplitude and phase noise that outperforms conventional approaches. Results demonstrate an accurate estimation of the phase noise even in the presence of large measurement noise.…”

Section: Characterization and Operation Of Transmittersmentioning

confidence: 99%

Artificial intelligence (AI) methods in optical networks: A comprehensive survey

Mata

Miguel

Durán

et al. 2018

Optical Switching and Networking

336

174

View full text Add to dashboard Cite

Artificial intelligence (AI) is an extensive scientific discipline which enables computer systems to solve problems by emulating complex biological processes such as learning, reasoning and self-correction. This paper presents a comprehensive review of the application of AI techniques for improving performance of optical communication systems and networks. The use of AI-based techniques is first studied in applications related to optical transmission, ranging from the characterization and operation of network components to performance monitoring, mitigation of nonlinearities, and quality of transmission estimation. Then, applications related to optical network control and management are also reviewed, including topics like optical network planning and operation in both transport and access networks. Finally, the paper also presents a summary of opportunities and challenges in optical networking where AI is expected to play a key role in the near future.

show abstract

“…Recently, several methods within the framework of nonlinear state-space based Bayesian filtering, (extended Kalman and particle filter), have been employed for timevarying parameter estimation such as: amplitude and phase noise, cross-polarization and cross-phase modulation induced polarization scattering and polarization mode dispersion [3]- [8]. The advantages of the statespace based Bayesian filtering for time-varying parameter estimation are that: 1) the framework is very well suited for joint parameter estimation, 2) it allows for the inclusion of the underlying physics of optical components and optical fibre channel into the estimation algorithms and 3) it allows for more complicated models of the time-varying parameters.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Techniques for Optical Performance Monitoring From Directly Detected PDM-QAM Signals

Thrane

Wass

Piels

et al. 2017

J. Lightwave Technol.

Self Cite

149

View full text Add to dashboard Cite

Linear signal processing algorithms are effective in dealing with linear transmission channel and linear signal detection, while the nonlinear signal processing algorithms, from the machine learning community, are effective in dealing with nonlinear transmission channel and nonlinear signal detection. In this paper, a brief overview of the various machine learning methods and their application in optical communication is presented and discussed. Moreover, supervised machine learning methods, such as neural networks and support vector machine, are experimentally demonstrated for in-band optical signal to noise ratio (OSNR) estimation and modulation format classification, respectively. The proposed methods accurately evaluate optical signals employing up to 64 quadrature amplitude modulation (QAM), at 32 Gbaud, using only directly-detected data.

show abstract

Application of Machine Learning Techniques for Amplitude and Phase Noise Characterization

Cited by 47 publications

References 15 publications

Laser Rate Equation-Based Filtering for Carrier Recovery in Characterization and Communication

Laser Rate Equation-Based Filtering for Carrier Recovery in Characterization and Communication

Artificial intelligence (AI) methods in optical networks: A comprehensive survey

Machine Learning Techniques for Optical Performance Monitoring From Directly Detected PDM-QAM Signals

Contact Info

Product

Resources

About