Binarized Coherent Optical Receiver Based on Opto-Electronic Neural Network

The resolution of analog to digital converter (ADC) and the power consumption of digital signal processing (DSP) are becoming the bottleneck of optical communication system. To acquire and recover signals with low resolution ADCs, we propose a binarized coherent optical receiver based on opto-electronic neural network, which consists of three layers, the broadcast layer, the optical neural layer, and the electronic neural layer. The broadcast layer that composed of Mach–Zehnder interferometers (MZIs) is to duplicate and select the input optical signal into the opto-electronic neural network. The optical neural layer is constituted by specially designed structures to map the binarized weights into optical domain, which can be integrated on silicon together with the broadcast layer. The one-bit vertical resolution ADCs act as the binarized activation after the optical neural layer. This binarized coherent optical receiver is demonstrated in simulation of 50-Gb/s single polarization (SP) QPSK system and 100-Gb/s polarization multiplexing (PDM) QPSK system. The one-bit vertical resolution ADCs can be utilized to recover the complex modulation format signal successfully. The broadcast layer and the optical neural layer can be integrated based on silicon, which could increase the calculation speed and reduce the energy consumption of the total system.

[1]  C Koos,et al.  Nonlinear silicon-on-insulator waveguides for all-optical signal processing. , 2007, Optics express.

[2]  Paul R. Prucnal,et al.  Neuromorphic Silicon Photonics , 2016, ArXiv.

[3]  J. Bowers,et al.  Hybrid Silicon Photonic Integrated Circuit Technology , 2013, IEEE Journal of Selected Topics in Quantum Electronics.

[4]  Mingyi Gao,et al.  K-means-clustering-based fiber nonlinearity equalization techniques for 64-QAM coherent optical communication system. , 2017, Optics express.

[5]  A. VanderLugt,et al.  Optical Signal Processing , 1990 .

[6]  C. L. Schow,et al.  A WDM 4×28Gbps integrated silicon photonic transmitter driven by 32nm CMOS driver ICs , 2015, 2015 Optical Fiber Communications Conference and Exhibition (OFC).

[7]  Leif K. Oxenløwe,et al.  Constellation Shaping for WDM Systems Using 256QAM/1024QAM With Probabilistic Optimization , 2016, Journal of Lightwave Technology.

[8]  David A. B. Miller,et al.  Self-configuring universal linear optical component [Invited] , 2013, 1303.4602.

[9]  T Wuth,et al.  Multi-rate (100G/40G/10G) Transport Over Deployed Optical Networks , 2008, OFC/NFOEC 2008 - 2008 Conference on Optical Fiber Communication/National Fiber Optic Engineers Conference.

[10]  Yi Luo,et al.  All-optical machine learning using diffractive deep neural networks , 2018, Science.

[11]  Ingo Fischer,et al.  Photonic machine learning implementation for signal recovery in optical communications , 2018, Scientific Reports.

[12]  Yoshua Bengio,et al.  BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 , 2016, ArXiv.

[13]  Alan E. Willner,et al.  All-Optical Signal Processing , 2014, Journal of Lightwave Technology.

[14]  Minghao Qi,et al.  Ultrabroad-bandwidth arbitrary radiofrequency waveform generation with a silicon photonic chip-based spectral shaper , 2010 .

[15]  Michal Lipson,et al.  WDM-compatible mode-division multiplexing on a silicon chip , 2014, Nature Communications.

[16]  Dan M. Marom,et al.  Switching solutions for WDM-SDM optical networks , 2015, IEEE Communications Magazine.

[17]  Qunbi Zhuge,et al.  Digital subcarrier multiplexing for fiber nonlinearity mitigation in coherent optical communication systems. , 2014, Optics express.

[18]  J. Teng,et al.  Optically reconfigurable metasurfaces and photonic devices based on phase change materials , 2015, Nature Photonics.

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

[20]  A.J.M. Timmermans,et al.  Computer vision system for on-line sorting of pot plants using an artificial neural network classifier , 1996 .

[21]  Shanhui Fan,et al.  Training of Photonic Neural Networks through In Situ Backpropagation , 2018, 2019 Conference on Lasers and Electro-Optics (CLEO).

[22]  J. Leuthold,et al.  Nonlinear silicon photonics , 2010 .

[23]  Di Liang,et al.  Recent progress in lasers on silicon , 2010 .

[24]  Xiang Zhou,et al.  Ultra-High-Capacity DWDM transmission system for 100G and beyond , 2010, IEEE Communications Magazine.

[25]  Alan Pak Tao Lau,et al.  Coherent detection in optical fiber systems. , 2008, Optics express.

[26]  Miles H. Anderson,et al.  Microresonator-based solitons for massively parallel coherent optical communications , 2016, Nature.

[27]  P. Winzer,et al.  Capacity Limits of Optical Fiber Networks , 2010, Journal of Lightwave Technology.

[28]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[29]  Ming-Fang Huang,et al.  698.5-Gb/s PDM-2048QAM transmission over 3km multicore fiber , 2013 .

[30]  Alan Y. Liu,et al.  Heterogeneous Silicon Photonic Integrated Circuits , 2016, Journal of Lightwave Technology.

[31]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[32]  David A. B. Miller,et al.  Perfect optics with imperfect components , 2015 .

[33]  Robert H. Walden,et al.  Analog-to-digital converter survey and analysis , 1999, IEEE J. Sel. Areas Commun..

[34]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

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

[36]  D. Miller,et al.  Are optical transistors the logical next step , 2010 .

[37]  M. Nakazawa,et al.  2048 QAM (66 Gbit/s) single-carrier coherent optical transmission over 150 km with a potential SE of 15.3 bit/s/Hz , 2014, OFC.

[38]  Wim Bogaerts,et al.  Demonstration of a 4 × 4-port universal linear circuit , 2016 .

[39]  Steve Madden,et al.  Photonic chip based ultrafast optical processing based on high nonlinearity dispersion engineered chalcogenide waveguides , 2012 .

[40]  Jau Tang.  A comparison study of the Shannon channel capacity of various nonlinear optical fibers , 2006, Journal of Lightwave Technology.

[41]  A. Mecozzi,et al.  Kramers–Kronig coherent receiver , 2016 .

[42]  K. Kikuchi,et al.  Evaluation of Sensitivity of the Digital Coherent Receiver , 2008, Journal of Lightwave Technology.

[43]  Tingye Li.  Upgrading lightwave transmission capacity with wavelength-multiplexing and high-speed technologies , 1995, IEEE/LEOS 1995 Digest of the LEOS Summer Topical Meetings. Flat Panel Display Technology.

[44]  Luke Theogarajan,et al.  Electronic and photonic integrated circuits for fast data center optical circuit switches , 2013, IEEE Communications Magazine.

[45]  Jianjun Yu,et al.  400Gb/s (4 x 100Gb/s) orthogonal PDM-RZ-QPSK DWDM signal transmission over 1040km SMF-28. , 2009, Optics express.

[46]  Yongdong Zhang,et al.  Supervised Hash Coding With Deep Neural Network for Environment Perception of Intelligent Vehicles , 2018, IEEE Transactions on Intelligent Transportation Systems.

[47]  T. Duthel,et al.  Coherent Equalization and POLMUX-RZ-DQPSK for Robust 100-GE Transmission , 2008, Journal of Lightwave Technology.

[48]  M. O'Sullivan,et al.  Modulation formats for 100Gb/s coherent optical systems , 2009, 2009 Conference on Optical Fiber Communication - incudes post deadline papers.

[49]  Ian A. D. Williamson,et al.  Training of Photonic Neural Networks through In Situ Backpropagation , 2019 .

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

[51]  William Shieh,et al.  Coherent optical orthogonal frequency division multiplexing , 2006 .

[52]  F. Kschischang,et al.  Roadmap of optical communications , 2015, 1507.05157.

[53]  Peter J Winzer,et al.  Fiber-optic transmission and networking: the previous 20 and the next 20 years [Invited]. , 2018, Optics express.