Hidden Feature Extraction Learning and End-to-End Joint Equalization With LDPC Decoding Method for Optical Interconnect

被引:0
作者
Yang, Chuanchuan [1 ,2 ]
Qin, Hao [1 ]
Lan, Tianxiang [1 ]
Gao, Yunfeng [3 ]
Wang, Jiaxing [4 ]
Zhao, Yuping [1 ,2 ]
Chang-Hasnain, Constance J. [4 ]
机构
[1] Peking Univ, Dept Elect, State Key Lab Adv Opt Commun Syst & Networks, Beijing 100871, Peoples R China
[2] Peking Univ, Shenzhen Grad Sch, Shenzhen 518055, Peoples R China
[3] CITIC Grp Corp, Beijing 100020, Peoples R China
[4] Berxel Photon Co Ltd, Shenzhen 518055, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Decoding; Training; Vertical cavity surface emitting lasers; Optical fiber communication; Parity check codes; Optical interconnections; Feature extraction; Artificial neural networks; Modulation; Forward error correction; End-to-end learning; joint equalization and decoding; LDPC codes; neural network; optical interconnect; VCSEL; PARITY-CHECK CODES; NEURAL-NETWORK; DENSITY EVOLUTION; PRE-DISTORTION; DESIGN; 5G;
D O I
10.1109/JLT.2024.3505415
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The vertical-cavity surface-emitting lasers and multimode fiber (VCSEL-MMF) solution has successfully emerged in optical interconnects (OIs), which meets the challenges of signal impairments in ultra-high-speed scenarios. Deep learning (DL) techniques, which can approximate any nonlinear function, enable the design of communication systems by carrying out the optimization in a single end-to-end (E2E) process including the transceivers as well as communication channels. In this paper, we propose a hidden feature extraction learning method for neural network equalization to improve training efficiency without increasing computational burden. Superior bit error rate (BER) is demonstrated in achieving 288 Gb/s 100 m VCSEL-MMF interconnect compared with black-box training strategy. Furthermore, an E2E joint equalization and low-density parity-check (LDPC) decoding method is proposed to improve the overall performance. Based on the autoencoder (AE) architecture, the E2E network involves a digital pre-distorter (DPD), a digital optical link model, a feed forward equalizer (FFE) and a deep learning based Normalized Offset Min-Sum (DL-NOMS) LDPC decoder. Experimental results demonstrate that the BER performance of the proposed E2E scheme is two-magnitude lower than the E2E equalization and FFE+DL-NOMS decoding method in back-to-back (BTB) and 100 m VCSEL-MMF links.
引用
收藏
页码:1746 / 1758
页数:13
相关论文
共 52 条
[21]   Least Angle Regression-Based Modified Volterra Nonlinear Equalizer for Optical Interconnection System [J].
Gao, Yunfeng ;
Yang, Chuanchuan ;
Wang, Jiaxing ;
Zhang, Cheng ;
Zhang, Xiaoyu ;
Guo, Haipeng ;
Qin, Xin ;
Shen, Chih-Chiang ;
Li, Hongbin ;
Chen, Zhangyuan ;
Chang-Hasnain, Constance J. .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (12) :3622-3632
[22]   Neural Network DPD for Aggrandizing SM-VCSEL-SSMF-Based Radio over Fiber Link Performance [J].
Hadi, Muhammad Usman ;
Awais, Muhammad ;
Raza, Mohsin ;
Khurshid, Kiran ;
Jung, Hyun .
PHOTONICS, 2021, 8 (01) :1-15
[23]  
Karanov B, 2020, 2020 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXPOSITION (OFC)
[24]   End-to-End Deep Learning of Optical Fiber Communications [J].
Karanov, Boris ;
Chagnon, Mathieu ;
Thouin, Felix ;
Eriksson, Tobias A. ;
Buelow, Henning ;
Lavery, Domanic ;
Bayvel, Polina ;
Schmalen, Laurent .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2018, 36 (20) :4843-4855
[25]  
Karinou F., 2016, P 42 EUR C OPT COMM, P1
[26]   Density Evolution for Nonbinary LDPC Codes Under Gaussian Approximation [J].
Li, Ge ;
Fair, Ivan J. ;
Krzymien, Witold A. .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2009, 55 (03) :997-1015
[27]   Techno-Economic Comparison of Silicon Photonics and Multimode VCSELs [J].
Mahgerefteh, Daniel ;
Thompson, Craig ;
Cole, Chris ;
Denoyer, Gilles ;
Nguyen, Thelinh ;
Lyubomirsky, Ilya ;
Kocot, Chris ;
Tatum, Jim .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2016, 34 (02) :233-242
[28]   TDECQ-Based Optimization of Nonlinear Digital Pre-Distorters for VCSEL-MMF Optical Links Using End-to-End Learning [J].
Minelli, Leonardo ;
Forghieri, Fabrizio ;
Shao, Tong ;
Shahpari, Ali ;
Gaudino, Roberto .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2024, 42 (02) :621-635
[29]   Development and Characterization of 100 Gb/s Data Communication VCSELs [J].
Murty, M. V. Ramana ;
Wang, Jingyi ;
Harren, Ann Lehman ;
Cheng, An-Nien ;
Dolfi, David W. ;
Feng, Zheng-Wen ;
Sridhara, Aaditya ;
Joyo, Sumitro Taslim ;
Chu, Jason ;
Giovane, Laura M. .
IEEE PHOTONICS TECHNOLOGY LETTERS, 2021, 33 (16) :812-815
[30]  
Niu K, 2021, IEEE INT CONF COMMUN, P144, DOI 10.1109/ICCC52777.2021.9580304