Accurate Prediction of Quality of Transmission Based on a Dynamically Configurable Optical Impairment Model

Bouda, Martin; Oda, Shunri; Vassilieva, Olga; Miyabe, Masatake; Yoshida, Setsuo; Katagiri, Takahiro; Aoki, Yuriko; Hoshida, Takeshi; Ikeuchi, Tadashi

doi:10.1364/jocn.10.00a102

Cited by 35 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The design margin of future demands can then be reduced with more accurate input parameters. In [32], a re-configurable model based on physical abstraction is proposed. The extended Kalman filter is used for parameter learning.…”

Section: The Reduction Of Design Marginsmentioning

confidence: 99%

“…On the other hand, the transmission performance may be constrained by power excursions owing to specific gain-tilt of the EDFAs, EDFA gain-control mechanisms, and the number of EDFAs [45]. Power excursions can increase the discrepancy of the EDFA's output, and the excursion caused by each EDFA can be further exacerbated during the Extended Kalman filter [32] Reducing the inaccuracy of physical layer parameters Polynomial regressions [33] DNN [34] ANN, transfer learning [35] Estimating nonlinear SNR of specific links and improving tolerance to link parameter uncertainties Stochastic gradient descent polynomial regression [37] Predicting accurate BER, then adapting modulation format, or FEC and slot-size transmission. In this case, ML is a reliable tool to solve this problem and make the methods transferrable among dynamically changing heterogeneous networks.…”

Section: Power Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

An overview of ML-based applications for next generation optical networks

Gao

Liu

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Over the past few decades, the demand for the capacity and reliability of optical networks has continued to grow. In the meantime, optical networks with larger knowledge scales have become sources of numerous heterogeneous data. In order to handle these new challenges, many issues need to be resolved, among which the low-margin optical networks design, power optimization, routing and wavelength assignment (RWA), failure management are quite important. However, the use of traditional algorithms in the above four applications shows some shortcomings. Fortunately, artificial intelligence (AI), especially machine learning (ML), is regarded as one of the most promising methods to overcome these shortcomings. In this study, we review the applications of ML methods in solving these four issues. Although many ML-based researches have emerged, the applications of ML techniques in optical networks still face challenges. Therefore, we also discuss some possible future directions of investigating ML-based approaches in optical networks.

show abstract

Section: The Reduction Of Design Marginsmentioning

confidence: 99%

Section: Power Optimizationmentioning

confidence: 99%

An overview of ML-based applications for next generation optical networks

Gao

Liu

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The power, routing, modulation level and spectrum assignment (PRMSA) problem is usually determinate in the planning stage of the network and margins are included considering the QoT inaccuracies, equipment ageing, inter-channel interference, as well as the uncertainties of the optical power dynamics [7], [8]. However, there are some investigations to the development of resource allocation algorithms based on OPMs with reduced margins, which have considered ageing and inter-channel interference to configurable transponders with launch powers [5], regenerator placement [4] and the optimization of the physical topology for power minimization [9].…”

Section: Introductionmentioning

confidence: 99%

Heuristic Chaotic Hurricane-Aided Efficient Power Assignment for Elastic Optical Network

Santos

Abrão

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose a dynamical power allocation (PA) procedure for elastic optical networks (EONs) based on the evolutionary hurricane search optimization (HSO) algorithm with a chaotic logistic map diversification strategy with the purpose of improving the capability to escape from local optima, namely PA-CHSO. The aiming is the dynamical control of the transmitted optical powers according to the variations of each link state due to traffic fluctuations, channel impairments, as well as other channel-power coupling effects. Such realistic EON scenarios are affected mainly by the channel estimation inaccuracy, channel ageing and power fluctuations. The link state is based on the channel estimation and quality of transmission (QoT) parameters obtained from the optical performance monitors (OPMs). Numerical results have demonstrated the effectiveness of the PA-CHSO to dynamically mitigate the power penalty under real measurement conditions with uncertainties and noise, as well as when perturbations in the optical transmit powers are considered. INDEX TERMS Adaptive power control algorithm, optical networks, hurricane algorithm, chaotic map, elastic optical networks.

show abstract

“…In [9] a method based on a Gaussian Process regression was considered to predict the bit-error-rate using the signal power, the number of spans, the baud rate and the channel spacing as features. Experiments have been also conducted in [10]- [14] with real network testbeds. The first experimental testbed is based on a 6-node network and open ROADMs that constantly monitor performance of established demands [10]- [12].…”

Section: Introductionmentioning

confidence: 99%

“…Experiments have been also conducted in [10]- [14] with real network testbeds. The first experimental testbed is based on a 6-node network and open ROADMs that constantly monitor performance of established demands [10]- [12]. The accuracy of the signal-to-noise ratio (SNR) estimation for new light paths was improved by learning the SNR of each link composing the light path.…”

Section: Introductionmentioning

confidence: 99%

Automated Fiber Type Identification in SDN-Enabled Optical Networks

Seve

Pesic

Delezoide

et al. 2019

J. Lightwave Technol.

View full text Add to dashboard Cite

Network design margins are introduced by quality of transmission estimator inaccuracies. Some of those inaccuracies are due to uncertainty on the fiber type deployed in optical networks, and on the value of the chromatic dispersion of deployed fibers. We propose, in this paper, a method to identify all unknown fiber types (and estimate chromatic dispersion) in an optical network to reduce said uncertainties. We monitor, collect, centralize, and correlate chromatic dispersion values accumulated over each established light path, already measured by coherent receivers to autonomously identify fiber types without traffic interruption. Thanks to this method, we can identify the fiber type of all the 41-unknown links for a 28-node network built with four different fiber types and only 100 light paths. Our method is also capable of distinguishing two fiber types that only differ by their dispersion slope. We have also deployed and demonstrated this fiber type identification method at the ECOC 2018 demo session with real-time communication with our Lab from the demo floor. The SDN-enabled optical network is based on ONOS controller that periodically provides real-time chromatic dispersion values of active light paths needed for the autonomous fiber type identification.

show abstract

Accurate Prediction of Quality of Transmission Based on a Dynamically Configurable Optical Impairment Model

Cited by 35 publications

References 13 publications

An overview of ML-based applications for next generation optical networks

An overview of ML-based applications for next generation optical networks

Heuristic Chaotic Hurricane-Aided Efficient Power Assignment for Elastic Optical Network

Automated Fiber Type Identification in SDN-Enabled Optical Networks

Contact Info

Product

Resources

About