Nonlinear Equalization Based on Artificial Neural Network in DML-Based OFDM Transmission Systems

This article reports the application of an equalizer based on an artificial neural network (ANN), in the form of nonlinear waveform regression, to mitigate nonlinear impairments in directly modulated laser (DML)-based orthogonal frequency-division multiplexing (OFDM) optical transmission. Experiments involving transmission over 0–200 km demonstrate that using an ANN with one hidden layer can greatly reduce nonlinear distortion. The proposed scheme outperformed a Volterra nonlinear equalizer at transmission distances exceeding 25 km. Using a 10G-class DML, the proposed scheme achieved the following data rates: 39.2 Gbps at 100 km (an improvement of 59%) and 33.5 Gbps at 150 km (an improvement of 57%). We also modified the cost function of the ANN during the training procedure to overcome the poor signal-to-noise ratio of the original ANN at low frequencies. This resulted in $>$30-Gbps transmission over 0–200 km.

[1]  K. Lever,et al.  Computational complexity of Volterra based nonlinear compensators , 1996 .

[2]  Jiri Matas,et al.  All you need is a good init , 2015, ICLR.

[3]  Jorge Campello De Souza,et al.  Optimal discrete bit loading for multicarrier modulation systems , 1998 .

[4]  Chia-Chien Wei,et al.  Employing Deep Neural Network for High Speed 4-PAM Optical Interconnect , 2017, 2017 European Conference on Optical Communication (ECOC).

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

[6]  Takehiro Tsuritani,et al.  Improving DML-Based OFDM Transmission by a Filter-Aided Neural Network Equalizer , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).

[7]  Vincent Houtsma,et al.  92 and 50 Gbps TDM-PON using Neural Network Enabled Receiver Equalization Specialized for PON , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  C. Wei,et al.  On Adiabatic Chirp and Compensation for Nonlinear Distortion in DML-Based OFDM Transmission , 2018, Journal of Lightwave Technology.

[10]  F. Fidler,et al.  160-Gb/s CWDM capacity upgrade using 2.5-Gb/s rated uncooled directly Modulated lasers , 2004, IEEE Photonics Technology Letters.

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

[12]  Beatriz Ortega,et al.  Comprehensive Impairment and Performance Description of Directly Modulated/Detected OOFDM Systems , 2013, Journal of Lightwave Technology.

[13]  Takehiro Tsuritani,et al.  Reducing the Impact of Nonlinear Distortion in DML-Based OFDM Transmission by Frequency Gap , 2018, Journal of Lightwave Technology.

[14]  Chia-Chien Wei,et al.  Study of Training Patterns for Employing Deep Neural Networks in Optical Communication Systems , 2018, 2018 European Conference on Optical Communication (ECOC).

[15]  Chia-Chien Wei,et al.  EAM-based high-speed 100-km OFDM transmission featuring tolerant modulator operation enabled using SSII cancellation. , 2014, Optics express.

[16]  Chia-Chien Wei,et al.  Frequency- and time-domain nonlinear distortion compensation in high-speed OFDM-IMDD LR-PON with high loss budget. , 2017, Optics express.

[17]  J. Helms,et al.  Intermodulation distortions of broad-band modulated laser diodes , 1992 .

[18]  Syed Tajammul Ahmad,et al.  Radial Basis Function Neural Network Nonlinear Equalizer for 16-QAM Coherent Optical OFDM , 2016, IEEE Photonics Technology Letters.

[19]  J.E. Mitchell,et al.  A 10-Gb/s 1024-Way-Split 100-km Long-Reach Optical-Access Network , 2007, Journal of Lightwave Technology.

[20]  Hoon Kim,et al.  Transmission of 28-Gb/s Duobinary and PAM-4 Signals Using DML for Optical Access Network , 2017, IEEE Photonics Technology Letters.

[21]  D. Marcuse,et al.  Nonlinear distortion generated by dispersive transmission of chirped intensity-modulated signals , 1991, IEEE Photonics Technology Letters.

[22]  E. Giacoumidis,et al.  Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM , 2016, 2016 Optical Fiber Communications Conference and Exhibition (OFC).

[23]  B. Charbonnier,et al.  Adaptive Loading Algorithm Implemented in AMOOFDM for NG-PON System Integrating Cost-Effective and Low-Bandwidth Optical Devices , 2009, IEEE Photonics Technology Letters.

[24]  Chia-Chien Wei,et al.  Analysis and iterative equalization of transient and adiabatic chirp effects in DML-based OFDM transmission systems. , 2012, Optics express.

[25]  C. Wei.  Small-signal analysis of OOFDM signal transmission with directly modulated laser and direct detection. , 2011, Optics letters.