可学习的数字信号处理:光纤通信线性补偿的新基准。

IF 19.4 1区 物理与天体物理 Q1 Physics and Astronomy
Zekun Niu, Hang Yang, Lyu Li, Minghui Shi, Guozhi Xu, Weisheng Hu, Lilin Yi
{"title":"可学习的数字信号处理:光纤通信线性补偿的新基准。","authors":"Zekun Niu, Hang Yang, Lyu Li, Minghui Shi, Guozhi Xu, Weisheng Hu, Lilin Yi","doi":"10.1038/s41377-024-01556-5","DOIUrl":null,"url":null,"abstract":"<p><p>The surge in interest regarding the next generation of optical fiber transmission has stimulated the development of digital signal processing (DSP) schemes that are highly cost-effective with both high performance and low complexity. As benchmarks for nonlinear compensation methods, however, traditional DSP designed with block-by-block modules for linear compensations, could exhibit residual linear effects after compensation, limiting the nonlinear compensation performance. Here we propose a high-efficient design thought for DSP based on the learnable perspectivity, called learnable DSP (LDSP). LDSP reuses the traditional DSP modules, regarding the whole DSP as a deep learning framework and optimizing the DSP parameters adaptively based on backpropagation algorithm from a global scale. This method not only establishes new standards in linear DSP performance but also serves as a critical benchmark for nonlinear DSP designs. In comparison to traditional DSP with hyperparameter optimization, a notable enhancement of approximately 1.21 dB in the Q factor for 400 Gb/s signal after 1600 km fiber transmission is experimentally demonstrated by combining LDSP and perturbation-based nonlinear compensation algorithm. Benefiting from the learnable model, LDSP can learn the best configuration adaptively with low complexity, reducing dependence on initial parameters. The proposed approach implements a symbol-rate DSP with a small bit error rate (BER) cost in exchange for a 48% complexity reduction compared to the conventional 2 samples/symbol processing. We believe that LDSP represents a new and highly efficient paradigm for DSP design, which is poised to attract considerable attention across various domains of optical communications.</p>","PeriodicalId":18093,"journal":{"name":"Light, science & applications","volume":"13 1","pages":"188"},"PeriodicalIF":19.4000,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11319808/pdf/","citationCount":"0","resultStr":"{\"title\":\"Learnable digital signal processing: a new benchmark of linearity compensation for optical fiber communications.\",\"authors\":\"Zekun Niu, Hang Yang, Lyu Li, Minghui Shi, Guozhi Xu, Weisheng Hu, Lilin Yi\",\"doi\":\"10.1038/s41377-024-01556-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The surge in interest regarding the next generation of optical fiber transmission has stimulated the development of digital signal processing (DSP) schemes that are highly cost-effective with both high performance and low complexity. As benchmarks for nonlinear compensation methods, however, traditional DSP designed with block-by-block modules for linear compensations, could exhibit residual linear effects after compensation, limiting the nonlinear compensation performance. Here we propose a high-efficient design thought for DSP based on the learnable perspectivity, called learnable DSP (LDSP). LDSP reuses the traditional DSP modules, regarding the whole DSP as a deep learning framework and optimizing the DSP parameters adaptively based on backpropagation algorithm from a global scale. This method not only establishes new standards in linear DSP performance but also serves as a critical benchmark for nonlinear DSP designs. In comparison to traditional DSP with hyperparameter optimization, a notable enhancement of approximately 1.21 dB in the Q factor for 400 Gb/s signal after 1600 km fiber transmission is experimentally demonstrated by combining LDSP and perturbation-based nonlinear compensation algorithm. Benefiting from the learnable model, LDSP can learn the best configuration adaptively with low complexity, reducing dependence on initial parameters. The proposed approach implements a symbol-rate DSP with a small bit error rate (BER) cost in exchange for a 48% complexity reduction compared to the conventional 2 samples/symbol processing. We believe that LDSP represents a new and highly efficient paradigm for DSP design, which is poised to attract considerable attention across various domains of optical communications.</p>\",\"PeriodicalId\":18093,\"journal\":{\"name\":\"Light, science & applications\",\"volume\":\"13 1\",\"pages\":\"188\"},\"PeriodicalIF\":19.4000,\"publicationDate\":\"2024-08-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11319808/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Light, science & applications\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1038/s41377-024-01556-5\",\"RegionNum\":1,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Physics and Astronomy\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Light, science & applications","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1038/s41377-024-01556-5","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Physics and Astronomy","Score":null,"Total":0}
引用次数: 0

摘要

人们对下一代光纤传输的兴趣日益高涨,推动了数字信号处理(DSP)方案的发展,这些方案不仅性能高、复杂度低,而且具有很高的成本效益。然而,作为非线性补偿方法的基准,传统的数字信号处理器在设计时采用逐块模块进行线性补偿,补偿后会出现残余线性效应,从而限制了非线性补偿的性能。在此,我们提出了一种基于可学习视角的 DSP 高效设计思想,称为可学习 DSP(LDSP)。LDSP 重用了传统的 DSP 模块,将整个 DSP 视为一个深度学习框架,并基于反向传播算法从全局范围自适应地优化 DSP 参数。这种方法不仅确立了线性 DSP 性能的新标准,也是非线性 DSP 设计的重要基准。与采用超参数优化的传统 DSP 相比,通过结合 LDSP 和基于扰动的非线性补偿算法,实验证明 400 Gb/s 信号在经过 1600 公里光纤传输后,Q 因数显著提高了约 1.21 dB。得益于可学习模型,LDSP 能以较低的复杂度自适应学习最佳配置,减少对初始参数的依赖。与传统的 2 样本/符号处理相比,所提出的方法以较小的误码率 (BER) 成本实现了符号率 DSP,并将复杂度降低了 48%。我们相信,LDSP 代表了一种新的、高效的 DSP 设计范例,有望在光通信的各个领域引起广泛关注。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Learnable digital signal processing: a new benchmark of linearity compensation for optical fiber communications.

Learnable digital signal processing: a new benchmark of linearity compensation for optical fiber communications.

The surge in interest regarding the next generation of optical fiber transmission has stimulated the development of digital signal processing (DSP) schemes that are highly cost-effective with both high performance and low complexity. As benchmarks for nonlinear compensation methods, however, traditional DSP designed with block-by-block modules for linear compensations, could exhibit residual linear effects after compensation, limiting the nonlinear compensation performance. Here we propose a high-efficient design thought for DSP based on the learnable perspectivity, called learnable DSP (LDSP). LDSP reuses the traditional DSP modules, regarding the whole DSP as a deep learning framework and optimizing the DSP parameters adaptively based on backpropagation algorithm from a global scale. This method not only establishes new standards in linear DSP performance but also serves as a critical benchmark for nonlinear DSP designs. In comparison to traditional DSP with hyperparameter optimization, a notable enhancement of approximately 1.21 dB in the Q factor for 400 Gb/s signal after 1600 km fiber transmission is experimentally demonstrated by combining LDSP and perturbation-based nonlinear compensation algorithm. Benefiting from the learnable model, LDSP can learn the best configuration adaptively with low complexity, reducing dependence on initial parameters. The proposed approach implements a symbol-rate DSP with a small bit error rate (BER) cost in exchange for a 48% complexity reduction compared to the conventional 2 samples/symbol processing. We believe that LDSP represents a new and highly efficient paradigm for DSP design, which is poised to attract considerable attention across various domains of optical communications.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
27.00
自引率
2.60%
发文量
331
审稿时长
20 weeks
期刊介绍: Light: Science & Applications is an open-access, fully peer-reviewed publication.It publishes high-quality optics and photonics research globally, covering fundamental research and important issues in engineering and applied sciences related to optics and photonics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信