Revisiting Efficient Multi-Step Nonlinearity Compensation With Machine Learning: An Experimental Demonstration

Efficient nonlinearity compensation in fiber-optic communication systems is considered a key element to go beyond the “capacity crunch”. One guiding principle for previous work on the design of practical nonlinearity compensation schemes is that fewer steps lead to better systems. In this paper, we challenge this assumption and show how to carefully design multi-step approaches that provide better performance–complexity trade-offs than their few-step counterparts. We consider the recently proposed learned digital backpropagation (LDBP) approach, where the linear steps in the split-step method are re-interpreted as general linear functions, similar to the weight matrices in a deep neural network. Our main contribution lies in an experimental demonstration of this approach for a 25 Gbaud single-channel optical transmission system. It is shown how LDBP can be integrated into a coherent receiver DSP chain and successfully trained in the presence of various hardware impairments. Our results show that LDBP with limited complexity can achieve better performance than standard DBP by using very short, but jointly optimized, finite-impulse response filters in each step. This paper also provides an overview of recently proposed extensions of LDBP and we comment on potentially interesting avenues for future work.

[1]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[2]  Yuichi Akiyama,et al.  Digital nonlinear compensation technologies in coherent optical communication systems , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[3]  F. Kschischang,et al.  Digital signal processing for fiber nonlinearities [Invited]. , 2017, Optics express.

[4]  Alex Alvarado,et al.  Revisiting Multi-Step Nonlinearity Compensation with Machine Learning , 2019, 45th European Conference on Optical Communication (ECOC 2019).

[5]  Per Larsson-Edefors,et al.  ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion Filters , 2018, 2018 European Conference on Optical Communication (ECOC).

[6]  W. Rosenkranz,et al.  Efficient numerical simulation of multichannel WDM transmission systems limited by XPM , 2003, IEEE Photonics Technology Letters.

[7]  Moshe Nazarathy,et al.  Subbanded DSP Architectures Based on Underdecimated Filter Banks for Coherent OFDM Receivers: Overview and recent advances , 2014, IEEE Signal Processing Magazine.

[8]  K. Goroshko,et al.  Overcoming performance limitations of digital back propagation due to polarization mode dispersion , 2016, 2016 18th International Conference on Transparent Optical Networks (ICTON).

[9]  Guifang Li,et al.  Efficient backward-propagation using wavelet-based filtering for fiber backward-propagation. , 2009, Optics express.

[10]  Cristian B. Czegledi,et al.  On the limits of digital back-propagation in the presence of transceiver noise. , 2017, Optics express.

[11]  Henry D. Pfister,et al.  Wideband Time-Domain Digital Backpropagation via Subband Processing and Deep Learning , 2018, 2018 European Conference on Optical Communication (ECOC).

[12]  Guifang Li,et al.  Impact of XPM and FWM on the digital implementation of impairment compensation for WDM transmission using backward propagation. , 2008, Optics express.

[13]  Michael G Taylor.  Compact Digital Dispersion Compensation Algorithms , 2008, OFC/NFOEC 2008 - 2008 Conference on Optical Fiber Communication/National Fiber Optic Engineers Conference.

[14]  Paul Voois,et al.  Architecture of a Single-Chip 50 Gb/s DP-QPSK/BPSK Transceiver With Electronic Dispersion Compensation for Coherent Optical Channels , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[15]  Polina Bayvel,et al.  Experimental Demonstration of Learned Time-Domain Digital Back-Propagation , 2019, ArXiv.

[16]  Maxim Kuschnerov,et al.  Adaptive digital back-propagation for optical communication systems , 2014, OFC 2014.

[17]  Amirhossein Ghazisaeidi,et al.  Deep Learning Based Digital Back Propagation with Polarization State Rotation & Phase Noise Invariance , 2020, 2020 Optical Fiber Communications Conference and Exhibition (OFC).

[18]  Ting Wang,et al.  Complexity versus performance tradeoff for fiber nonlinearity compensation using frequency-shaped, multi-subband backpropagation , 2011, 2011 Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference.

[19]  Takeshi Hoshida,et al.  Low complexity digital perturbation back-propagation , 2011, 2011 37th European Conference and Exhibition on Optical Communication.

[20]  B. Eggleton,et al.  Fiber nonlinearity-induced penalty reduction in CO-OFDM by ANN-based nonlinear equalization. , 2015, Optics letters.

[21]  Henry D. Pfister,et al.  Deep Learning of the Nonlinear Schrödinger Equation in Fiber-Optic Communications , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[22]  Fernando P. Guiomar,et al.  Mitigation of intra-channel nonlinearities using a frequency-domain volterra series equalizer , 2011, 2011 37th European Conference and Exhibition on Optical Communication.

[23]  Melissa E. O'Neill.  PCG : A Family of Simple Fast Space-Efficient Statistically Good Algorithms for Random Number Generation , 2014 .

[24]  Seb J Savory,et al.  Digital filters for coherent optical receivers. , 2008, Optics express.

[25]  F. Hauske,et al.  Intrachannel Nonlinearity Compensation by Inverse Volterra Series Transfer Function , 2012, Journal of Lightwave Technology.

[26]  R I Killey,et al.  Mitigation of Fiber Nonlinearity Using a Digital Coherent Receiver , 2010, IEEE Journal of Selected Topics in Quantum Electronics.

[27]  Henry D. Pfister,et al.  Nonlinear Interference Mitigation via Deep Neural Networks , 2017, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[28]  A. Carena,et al.  Efficient Time-Domain DBP using Random Step-Size and Multi-Band Quantization , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[29]  Cristian B. Czegledi,et al.  Digital backpropagation accounting for polarization-mode dispersion. , 2017, Optics express.

[30]  Mikael Mazur,et al.  Time-domain digital back propagation: Algorithm and finite-precision implementation aspects , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[31]  K. Ho.  Subband equaliser for chromatic dispersion of optical fibre , 2009 .

[32]  Frank R. Kschischang,et al.  Implications of information theory in optical fibre communications , 2016, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[33]  Zabih Ghassemlooy,et al.  Artificial Neural Network Nonlinear Equalizer for Coherent Optical OFDM , 2015, IEEE Photonics Technology Letters.

[34]  Simon Rommel,et al.  Single-step digital backpropagation for nonlinearity mitigation , 2015, Photonic Network Communications.

[35]  A. Mezghani,et al.  Delayed Single-Tap Frequency-Domain Chromatic-Dispersion Compensation , 2013, IEEE Photonics Technology Letters.

[36]  E. Mateo,et al.  Complementary FIR Filter Pair for Distributed Impairment Compensation of WDM Fiber Transmission , 2009, IEEE Photonics Technology Letters.

[37]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[38]  Maxim Kuschnerov,et al.  Reduced Complexity Digital Back-Propagation Methods for Optical Communication Systems , 2014, Journal of Lightwave Technology.

[39]  Fatih Yaman,et al.  Efficient compensation of inter-channel nonlinear effects via digital backward propagation in WDM optical transmission. , 2010, Optics express.

[40]  Alex Alvarado,et al.  Model-Based Machine Learning for Joint Digital Backpropagation and PMD Compensation , 2020, 2020 Optical Fiber Communications Conference and Exhibition (OFC).

[41]  E. Ip,et al.  Nonlinear Compensation Using Backpropagation for Polarization-Multiplexed Transmission , 2010, Journal of Lightwave Technology.

[42]  D. Marcuse,et al.  Application of the Manakov-PMD equation to studies of signal propagation in optical fibers with randomly varying birefringence , 1997 .

[43]  Danish Rafique,et al.  Compensation of intra-channel nonlinear fibre impairments using simplified digital back-propagation algorithm. , 2011, Optics express.

[44]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[45]  Polina Bayvel,et al.  On the Impact of Fixed Point Hardware for Optical Fiber Nonlinearity Compensation Algorithms , 2018, Journal of Lightwave Technology.

[46]  Fan Zhang,et al.  Intra-channel nonlinearities mitigation in pseudo-linear coherent QPSK transmission systems via nonlinear electrical equalizer , 2009 .

[47]  Arthur James Lowery,et al.  Improved single channel backpropagation for intra-channel fiber nonlinearity compensation in long-haul optical communication systems. , 2010, Optics express.

[48]  M. Brandt-Pearce,et al.  Volterra series transfer function of single-mode fibers , 1997 .

[49]  Yuichi Akiyama,et al.  Complexity reduction of perturbation-based nonlinear compensator by sub-band processing , 2015, 2015 Optical Fiber Communications Conference and Exhibition (OFC).

[50]  Zhenning Tao,et al.  Multiplier-Free Intrachannel Nonlinearity Compensating Algorithm Operating at Symbol Rate , 2011, Journal of Lightwave Technology.

[51]  Polina Bayvel,et al.  A PMD-adaptive DBP Receiver Based on SNR Optimization , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[52]  Satoshi Yoshima,et al.  Experimental study of the limits of digital nonlinearity compensation in DWDM systems , 2015, 2015 Optical Fiber Communications Conference and Exhibition (OFC).

[53]  C. Menyuk,et al.  Optimization of the split-step Fourier method in modeling optical-fiber communications systems , 2003 .

[54]  Guifang Li,et al.  Electronic post-compensation of WDM transmission impairments using coherent detection and digital signal processing. , 2008, Optics express.

[55]  Max Tegmark,et al.  Why Does Deep and Cheap Learning Work So Well? , 2016, Journal of Statistical Physics.

[56]  Per Larsson-Edefors,et al.  Dispersion Compensation FIR Filter With Improved Robustness to Coefficient Quantization Errors , 2016, Journal of Lightwave Technology.

[57]  J. Kahn,et al.  Compensation of Dispersion and Nonlinear Impairments Using Digital Backpropagation , 2008, Journal of Lightwave Technology.

[58]  Henry D. Pfister,et al.  What Can Machine Learning Teach Us about Communications? , 2018, 2018 IEEE Information Theory Workshop (ITW).

[59]  R. Gilmore,et al.  Baker‐Campbell‐Hausdorff formulas , 1974 .

[60]  Xiaojun Liang,et al.  Multi-stage perturbation theory for compensating intra-channel nonlinear impairments in fiber-optic links. , 2014, Optics express.

[61]  Mikael Mazur,et al.  ASIC Implementation of Time-Domain Digital Back Propagation for Coherent Receivers , 2018, IEEE Photonics Technology Letters.