Corpus ID: 235265938

End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth

  title={End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth},
  author={Ognjen Jovanovic and Metodi Plamenov Yankov and Francesco Da Ros and Darko Zibar},
We propose an autoencoder-based geometric shaping that learns a constellation robust to SNR and laser linewidth estimation errors. This constellation maintains shaping gain in mutual information (up to 0.3 bits/symbol) with respect to QAM over various SNR and laser linewidth values. 

Figures from this paper


Deep Learning of Geometric Constellation Shaping Including Fiber Nonlinearities
A new geometric shaping method is proposed, leveraging unsupervised machine learning to optimize the constellation design, which mitigates nonlinear effects with gains up to 0.13 bit/4D when trained with a simplified fiber channel model. Expand
Optimization of 16-ary Quadrature Amplitude Modulation constellations for phase noise impaired channels
An iterative constellation optimization algorithm is used to find new 16-ary Quadrature Amplitude Modulation (QAM) constellations. The constellations double phase noise tolerance and improve receiverExpand
Hardware-Efficient Coherent Digital Receiver Concept With Feedforward Carrier Recovery for $M$ -QAM Constellations
This paper presents a novel digital feedforward carrier recovery algorithm for arbitrary M-ary quadrature amplitude modulation (M-QAM) constellations in an intradyne coherent optical receiver. TheExpand
Design of Signal Constellations in the Presence of Phase Noise
  • Yang Li, Shuzheng Xu, H. Yang
  • Mathematics, Computer Science
  • 2008 IEEE 68th Vehicular Technology Conference
  • 2008
Simulation indicates the symbol error performance of the new constellation is not only 6dB better than QAM at error rate of 10-3 in phase noise of 0.1rad, but also comparative with QAM when only white Gaussian noise is considered. Expand
Constellation Design for Memoryless Phase Noise Channels
It is shown that the optimized constellations are much more robust with respect to the changes in the phase noise characteristics than the phase shift keying (PSK) modulation and quadrature amplitude modulation (QAM). Expand
Constellation Optimization in the Presence of Strong Phase Noise
This paper addresses the problem of optimizing signal constellations for strong phase noise by considering three optimization formulations, which provide an analytical framework for constellation design and shows that the optimalconstellations significantly outperform conventional constellation designs and those proposed in the literature in terms of SEP, error floors, and MI. Expand
Toward transport ecosystem interoperability enabled by vendor-diverse coherent optical sources over an open line system
This paper takes a partial step toward demonstrating end-to-end interop by interoperating vendor-diverse packet switching platforms from Arista, Cisco, and Juniper, which utilize the same coherent DSP chip set, over an open line system (OLS). Expand
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand
Geometric Shaping of 2-D Constellations in the Presence of Laser Phase Noise
This article proposes a geometric shaping (GS) strategy to design 8, 16, 32, and 64-ary modulation formats for the optical fibre channel impaired by both additive white Gaussian (AWGN) and phase noise and demonstrates an enhanced signal-to-noise ratio (SNR) tolerance in high phase noise regimes. Expand
, T . Eriksson , and G . Colavolpe , “ Constellation Optimization in the Presence of Strong Phase Noise ” , IEEE Transactions on Communications , vol . 61 , no . 12
  • IEEE Transactions on Wireless Communications
  • 2014