• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于多层感知器的数字预失真实现24.576 Gbit/s光PAM4信号传输的FPGA实现

FPGA Implementation for 24.576-Gbit/s Optical PAM4 Signal Transmission with MLP-Based Digital Pre-Distortion.

作者信息

Hu Sheng, Zheng Tianqi, Bian Chengzhen, Yang Xiongwei, Sun Xinda, Zhu Zonghui, Gou Yumeng, Meng Yuanxiao, Zhang Jie, Ge Jingtao, Li Yichen, Wang Kaihui

机构信息

State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 200433, China.

出版信息

Sensors (Basel). 2024 Dec 9;24(23):7872. doi: 10.3390/s24237872.

DOI:10.3390/s24237872
PMID:39686408
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11644889/
Abstract

In this work, we implemented a short-reach real-time optical communication system using MLP for pre-distortion. Lookup table (LUT) algorithms are commonly employed for pre-distortion in intensity modulation and direct detection (IM/DD) systems. However, storage limitations typically restrict the LUT pattern length to 9, limiting its effectiveness in compensating for nonlinear effects. A multilayer perceptron (MLP) can overcome this limitation by predicting errors and generating pre-distorted signals, thus replacing the extensive storage requirements of LUTs with minimal computational resources. The MLP-based digital pre-distortion (MLP-DPD) technique enables the creation of long-pattern LUTs for improved nonlinear compensation. In this work, an MLP-DPD scheme was implemented on a field-programmable gate array (FPGA). The FPGA was used to generate a 14.7456 GBaud pre-distorted pulse amplitude modulation 4-level (PAM4) signal. This signal was then transmitted over 20 km of standard single-mode fiber (SSMF). At the receiver, the parallel constant modulus algorithm (PCMA) was applied for signal processing. The bit error rate (BER) achieved met the 2.4 × 10 threshold for soft-decision forward error correction (SD-FEC), enabling a net transmission bit rate of 24.576 Gbit/s. This approach demonstrates the feasibility of using MLP-DPD for effective nonlinear compensation in high-speed optical communication systems with limited resources.

摘要

在这项工作中,我们实现了一种使用多层感知器(MLP)进行预失真的短距离实时光通信系统。查找表(LUT)算法通常用于强度调制和直接检测(IM/DD)系统中的预失真。然而,存储限制通常将LUT模式长度限制为9,这限制了其在补偿非线性效应方面的有效性。多层感知器(MLP)可以通过预测误差和生成预失真信号来克服这一限制,从而用最少的计算资源取代LUT大量的存储需求。基于MLP的数字预失真(MLP-DPD)技术能够创建长模式LUT以改善非线性补偿。在这项工作中,一种MLP-DPD方案在现场可编程门阵列(FPGA)上得以实现。该FPGA用于生成一个14.7456 GBaud的预失真4电平脉冲幅度调制(PAM4)信号。然后该信号通过20 km的标准单模光纤(SSMF)进行传输。在接收器端,并行恒模算法(PCMA)被应用于信号处理。实现的误码率(BER)满足软判决前向纠错(SD-FEC)的2.4×10阈值,实现了24.576 Gbit/s的净传输比特率。这种方法证明了在资源有限的高速光通信系统中使用MLP-DPD进行有效非线性补偿的可行性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/a96e5eea48cd/sensors-24-07872-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/201ebec98a0f/sensors-24-07872-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/931a7f4018dc/sensors-24-07872-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/7f04342df3a0/sensors-24-07872-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/88bc7b4e95b6/sensors-24-07872-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/533c4f4c3b46/sensors-24-07872-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/dd62ecebe7b7/sensors-24-07872-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/f88a89b74bce/sensors-24-07872-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/a96e5eea48cd/sensors-24-07872-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/201ebec98a0f/sensors-24-07872-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/931a7f4018dc/sensors-24-07872-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/7f04342df3a0/sensors-24-07872-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/88bc7b4e95b6/sensors-24-07872-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/533c4f4c3b46/sensors-24-07872-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/dd62ecebe7b7/sensors-24-07872-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/f88a89b74bce/sensors-24-07872-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/68de/11644889/a96e5eea48cd/sensors-24-07872-g008.jpg

相似文献

1
FPGA Implementation for 24.576-Gbit/s Optical PAM4 Signal Transmission with MLP-Based Digital Pre-Distortion.基于多层感知器的数字预失真实现24.576 Gbit/s光PAM4信号传输的FPGA实现
Sensors (Basel). 2024 Dec 9;24(23):7872. doi: 10.3390/s24237872.
2
FPGA-based 4 × 29.4912 Gbit/s PS-PAM4 signal transmission with a low-complexity probabilistic shaping scheme.基于现场可编程门阵列(FPGA)的4×29.4912吉比特每秒的伪静态脉冲幅度调制四电平(PS-PAM4)信号传输,采用低复杂度概率整形方案。
Opt Lett. 2023 Mar 15;48(6):1514-1517. doi: 10.1364/OL.484599.
3
FPGA implementation for 44.2368-Gbit/s PAM8 signal transmission with pruned pre-equalization.采用剪枝预均衡的44.2368 Gbit/s PAM8信号传输的现场可编程门阵列实现
Opt Lett. 2023 Sep 1;48(17):4562-4565. doi: 10.1364/OL.498579.
4
C-band 200 Gbit/s/λ PAM-4 transmission over 2-km SSMF using look-up-table pre-distortion combined with nonlinear Tomlinson-Harashima pre-coding.采用查找表预失真与非线性汤姆林森-哈拉萨玛预编码相结合的方式,在2公里单模光纤上实现C波段200吉比特/秒/波长的四电平脉冲幅度调制传输。
Opt Express. 2022 Apr 25;30(9):15416-15427. doi: 10.1364/OE.457629.
5
Adaptive-memory-length look-up table (LUT)-based digital pre-distortion for IM/DD underwater wireless optical communications.基于自适应记忆长度查找表(LUT)的强度调制/直接检测水下无线光通信数字预失真
Opt Express. 2024 Feb 26;32(5):8081-8091. doi: 10.1364/OE.516562.
6
100 Gbit/s PAM4 signal transmission and reception for 2-km interconnect with adaptive notch filter for narrowband interference.采用自适应陷波滤波器抑制窄带干扰的2公里互连的100 Gbit/s PAM4信号发送与接收。
Opt Express. 2018 Sep 3;26(18):24066-24074. doi: 10.1364/OE.26.024066.
7
FPGA implementation of power-lite Volterra-inspired neural network equalizer in 180-Gb/s net bitrate IMDD short-reach optical system.180Gb/s净比特率强度调制直接检测短距离光通信系统中受Volterra启发的低功耗神经网络均衡器的现场可编程门阵列实现
Opt Lett. 2024 Aug 15;49(16):4573-4576. doi: 10.1364/OL.533564.
8
400 Gbit/s single-carrier and 1 Tbit/s three-carrier superchannel signals using dual polarization 16-QAM with look-up table correction and optical pulse shaping.采用带有查找表校正和光脉冲整形的双偏振16-QAM的400 Gbit/s单载波和1 Tbit/s三载波超信道信号。
Opt Express. 2014 Jan 13;22(1):71-83. doi: 10.1364/OE.22.000071.
9
Transmission of a 56  Gbit/s PAM4 signal with low-resolution DAC and pre-equalization only over 80  km fiber in C-band IM/DD systems for optical interconnects.在用于光互连的C波段强度调制/直接检测(IM/DD)系统中,仅通过低分辨率数模转换器(DAC)和预均衡在80公里光纤上传输56 Gbit/s的四电平脉冲幅度调制(PAM4)信号。
Opt Lett. 2021 Nov 15;46(22):5615-5618. doi: 10.1364/OL.441598.
10
Two-stage look-up-table-based 16QAM vector millimeter-wave signal generation and reception.基于两级查找表的16QAM矢量毫米波信号生成与接收。
Opt Lett. 2024 Feb 15;49(4):879-882. doi: 10.1364/OL.513987.

引用本文的文献

1
Study on Height Measurement for Polyethylene Terephthalate (PET) Materials Based on Residual Networks.基于残差网络的聚对苯二甲酸乙二酯(PET)材料高度测量研究
Sensors (Basel). 2025 Jun 28;25(13):4030. doi: 10.3390/s25134030.
2
Digital Frequency-Domain MIMO Equalizer Enabling Six-LP-Mode Strong-Coupling IM/DD MDM Optical Transmission System.支持六电平模式强耦合强度调制/直接检测多模复用光传输系统的数字频域多输入多输出均衡器
Sensors (Basel). 2025 Apr 18;25(8):2562. doi: 10.3390/s25082562.

本文引用的文献

1
FPGA implementation of power-lite Volterra-inspired neural network equalizer in 180-Gb/s net bitrate IMDD short-reach optical system.180Gb/s净比特率强度调制直接检测短距离光通信系统中受Volterra启发的低功耗神经网络均衡器的现场可编程门阵列实现
Opt Lett. 2024 Aug 15;49(16):4573-4576. doi: 10.1364/OL.533564.
2
Low-complexity frequency domain frame synchronization for short-reach IM/DD optical fiber transmission systems.用于短距离强度调制/直接检测(IM/DD)光纤传输系统的低复杂度频域帧同步
Opt Express. 2024 Jun 3;32(12):21077-21091. doi: 10.1364/OE.521946.
3
Gradient-descent noise whitening techniques for short-reach IM-DD optical interconnects with severe bandwidth limitation.
用于具有严重带宽限制的短距离强度调制-直接检测(IM-DD)光互连的梯度下降噪声白化技术。
Opt Express. 2024 Jan 15;32(2):1715-1727. doi: 10.1364/OE.509262.
4
Experimental demonstration of low-complexity trigonometric-memory-polynomial decision-feedback equalizer for nonlinear compensation in IM/DD optical systems.用于强度调制/直接检测(IM/DD)光通信系统中非线性补偿的低复杂度三角记忆多项式判决反馈均衡器的实验演示。
Opt Express. 2024 Jan 29;32(3):3329-3341. doi: 10.1364/OE.510106.
5
Deep Learning Equalizer Connected with Viterbi-Viterbi Algorithm for PAM D-Band Radio over Fiber Link.用于光纤链路中PAM D波段无线通信的深度学习均衡器与维特比-维特比算法相结合
Sensors (Basel). 2023 Dec 12;23(24):9773. doi: 10.3390/s23249773.
6
FPGA implementation for 44.2368-Gbit/s PAM8 signal transmission with pruned pre-equalization.采用剪枝预均衡的44.2368 Gbit/s PAM8信号传输的现场可编程门阵列实现
Opt Lett. 2023 Sep 1;48(17):4562-4565. doi: 10.1364/OL.498579.
7
Enhanced Performance of Artificial-Neural-Network-Based Equalization for Short-Haul Fiber-Optic Communications.基于人工神经网络的均衡增强在短距离光纤通信中的应用。
Sensors (Basel). 2023 Jun 27;23(13):5952. doi: 10.3390/s23135952.
8
Two-Lane DNN Equalizer Using Balanced Random-Oversampling for W-Band PS-16QAM RoF Delivery over 4.6 km.基于平衡随机过采样的双路 DNN 均衡器在 W 波段 PS-16QAM RoF 传输中的应用,传输距离为 4.6km。
Sensors (Basel). 2023 May 10;23(10):4618. doi: 10.3390/s23104618.
9
Degenerated look-up table-based perturbative fiber nonlinearity compensation algorithm for probabilistically shaped signals.用于概率整形信号的基于退化查找表的微扰光纤非线性补偿算法。
Opt Express. 2020 Apr 27;28(9):13401-13413. doi: 10.1364/OE.391169.
10
Experimental study of PAM-4, CAP-16, and DMT for 100 Gb/s short reach optical transmission systems.用于100 Gb/s短距离光传输系统的PAM-4、CAP-16和DMT的实验研究。
Opt Express. 2015 Jan 26;23(2):1176-89. doi: 10.1364/OE.23.001176.