Transformer-Based Nonlinear Equalization for DP-16QAM Coherent Optical Communication Systems

被引：3

作者：

Gautam, Naveenta ^{[1
,2
]}

Pendem, Sai Vikranth ^{[1
,3
]}

Lall, Brejesh ^{[4
]}

Choudhary, Amol ^{[1
,3
]}

机构：

[1] Indian Inst Technol Delhi, Bharti Sch Telecommun Technol & Management, New Delhi 110016, India

[2] Indian Inst Technol Delhi, Ultrafast Opt Commun & High Performance Integrated, New Delhi 110016, India

[3] Indian Inst Technol Delhi, Dept Elect Engn, New Delhi 110016, India

[4] Indian Inst Technol Delhi, Dept Elect Engn, New Delhi 110016, India

来源：

IEEE COMMUNICATIONS LETTERS | 2024年 / 28卷 / 03期

关键词：

Transformers; Transformer; optical communications; nonlinear equalisation; machine learning; neural networks; OFDM;

D O I：

10.1109/LCOMM.2023.3344996

中图分类号：

TN [电子技术、通信技术];

学科分类号：

0809 ;

摘要：

Compensating for nonlinear effects using digital signal processing (DSP) is complex and computationally expensive in long-haul optical communication systems due to intractable interactions between Kerr nonlinearity, chromatic dispersion (CD), and amplified spontaneous emission (ASE) noise from inline amplifiers. The application of machine learning architectures has demonstrated promising advancements in enhancing transmission performance through the mitigation of fiber nonlinear effects. In this letter, we apply a Transformer-based model to dual-polarisation (DP)-16QAM coherent optical communication systems. We test the performance of the proposed model for different values of fiber lengths and launched optical powers and show improved performance compared to the state-of-the-art digital backpropagation (DBP) algorithm, fully connected neural network (FCNN) and bidirectional long short term memory (BiLSTM) architecture.

引用

页码：577 / 581

页数：5

共 17 条

[1] Performance Versus Complexity Study of Neural Network Equalizers in Coherent Optical Systems [J].

Freire, Pedro J. ;

Osadchuk, Yevhenii ;

Spinnler, Bernhard ;

Napoli, Antonio ;

Schairer, Wolfgang ;

Costa, Nelson ;

Prilepsky, Jaroslaw E. ;

Turitsyn, Sergei K. .

JOURNAL OF LIGHTWAVE TECHNOLOGY, 2021, 39 (19) :6085-6096

[2] OptiDistillNet: Learning nonlinear pulse propagation using the student-teacher model [J].

Gautam, Naveenta ;

Kaushik, Vinay ;

Choudhary, Amol ;

Lall, Brejesh .

OPTICS EXPRESS, 2022, 30 (23) :42430-42439

[3] Comparative study of neural network architectures for modelling nonlinear optical pulse propagation [J].

Gautam, Naveenta ;

Choudhary, Amol ;

Lall, Brejesh .

OPTICAL FIBER TECHNOLOGY, 2021, 64 (64)

[4] Unsupervised Support Vector Machines for Nonlinear Blind Equalization in CO-OFDM [J].

Giacoumidis, E. ;

Tsokanos, A. ;

Ghanbarisabagh, M. ;

Mhatli, S. ;

Barry, L. P. .

IEEE PHOTONICS TECHNOLOGY LETTERS, 2018, 30 (12) :1091-1094

[5] Harnessing machine learning for fiber-induced nonlinearity mitigation in long-haul coherent optical OFDM [J].

Giacoumidis, Elias ;

Lin, Yi ;

Wei, Jinlong ;

Aldaya, Ivan ;

Tsokanos, Athanasios ;

Barry, Liam P. .

FUTURE INTERNET, 2019, 11 (01)

[6] Fiber nonlinearity-induced penalty reduction in CO-OFDM by ANN-based nonlinear equalization [J].

Giacoumidis, Elias ;

Le, Son T. ;

Ghanbarisabagh, Mohammad ;

McCarthy, Mary ;

Aldaya, Ivan ;

Mhatli, Sofien ;

Jarajreh, Mutsam A. ;

Haigh, Paul A. ;

Doran, Nick J. ;

Ellis, Andrew D. ;

Eggleton, Benjamin J. .

OPTICS LETTERS, 2015, 40 (21) :5113-5116

[7]

Häger C, 2018, 2018 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXPOSITION (OFC)

[8]

Hamgini BB, 2024, Arxiv, DOI arXiv:2304.13119

[9] Fundamentals of Coherent Optical Fiber Communications [J].

Kikuchi, Kazuro .

JOURNAL OF LIGHTWAVE TECHNOLOGY, 2016, 34 (01) :157-179

[10] Bi-directional gated recurrent unit neural network based nonlinear equalizer for coherent optical communication system [J].

Liu, Xinyu ;

Wang, Yongjun ;

Wang, Xishuo ;

Xu, Hui ;

Li, Chao ;

Xin, Xiangjun .

OPTICS EXPRESS, 2021, 29 (04) :5923-5933

← 1 2 →