基于多源域迁移学习的光纤非线性损伤补偿  

Fiber Nonlinear Impairment Compensation based on Multi-source Domain Transfer Learning

作　　者：陈志轩 蔡炬[1] 张洪波 张敏[1] 万峰 杜杰 刘娇 张倩武[2] CHEN Zhixuan;CAI Ju;ZHANG Hongbo;ZHANG Min;WAN Feng;DU Jie;LIU Jiao;ZHANG Qianwu(College of Communication Engineering,Chengdu University of Information Technology,Chengdu 610225,China;Key Laboratory of Specialty Fiber Optics and Optical Access Networks,Shanghai University,Shanghai 200072,China)

机构地区：[1]成都信息工程大学通信工程学院,成都610225 [2]上海大学特种光纤与光接入网省部共建重点实验室,上海200072

出　　处：《光通信研究》2025年第1期23-28,共6页Study on Optical Communications

基　　金：四川省科技计划资助项目(2021YFG0149);上海市科委重点实验室资助项目(SKLSFO2019-06);高等学校学科创新引智计划资助项目(111;D20031)。

摘　　要：【目的】近年来基于神经网络(NN)的均衡器在光纤非线性损伤补偿中被广泛使用,但在实际应用中,需要消耗大量资源对NN进行再训练以适应新环境下的光通信系统。迁移学习通过将初始系统(源域)训练的NN模型中的一部分参数应用于新环境(目标域)下的NN模型,仅需使用少量的训练数据即可实现目标域模型的快速重构,但是该方法需要在所有源域中找到最佳源域进行迁移以获得良好的性能,且当目标域变化后需重新寻找最佳源域,这会消耗大量的训练资源。【方法】为解决此问题,文章提出了一种基于多源域迁移学习的方法,该方法将卷积神经网络(CNN)和双向长短期记忆(BiLSTM)作为均衡器,通过特定源域训练和多源域训练两个过程交替更新网络参数,然后针对新环境下的光通信系统进行微调,只需使用少量的初始训练数据即可适应传输系统的变化,且无需寻找最佳源域即可实现良好的性能。【结果】文章在5通道50-GBaud波分复用(WDM)双偏振16阶正交幅度调制(DP-16QAM)的光传输系统中进行了仿真验证,综合数值仿真结果表明,仅需使用35%的目标域数据进行多源域迁移学习,即可具有比再训练方法更好的性能。同时,与再训练和单源域迁移学习相比,多源域迁移学习的Q因子分别提高了0.82和0.18 dB。【结论】因此,多源域迁移学习方案更适合于实际的光通信系统。【Objective】In recent years,equalizer based on Neural Network(NN)has been widely used in optical fiber nonlinear impairment compensation.However,in practical application,it needs to consume a lot of resources to retrain NN to adapt to optical communication system in new environment.Transfer learning applies some parameters of the NN model trained by the initial system(source domain)to the NN model in the new environment(target domain).Only a small amount of training data is needed to achieve rapid reconstruction of the target domain model.However,this method needs to find the best source domain in all source domains for migration to obtain good performance.When the target domain changes,it is necessary to find the best source domain again,which will consume a lot of training resources.This work suggests a solution based on multi-source domain transfer learning to solve this issue.【Methods】This method employs Convolutional Neural Networks(CNN)and Bidirectional Long Short-Term Memory(BiLSTM)as equalizers.It alternately updates network parameters through two processes:specific source domain training and multi-source domain training.Subsequently,the optical communication system in the new environment is fine-tuned,allowing it to adapt to changes in the transmission system using only a small amount of initial training data.Moreover,good performance can be achieved without the need to search for the optimal source domain.【Results】A 5-channel 50-GBaud Wavelength Division Multiplexing(WDM)Dual-Polarization 16-order Quadrature Amplitude Modulation(DP-16QAM)optical transmission system is simulated to verify the effectiveness of the proposed method.The numerical simulation results show that the multi-source domain transfer learning outperforms the retraining method when using just 35%of the target domain data.Meanwhile,the Q-factor of multi-source domain transfer learning are improved by 0.82 and 0.18 dB,respectively,in compared with retraining and single source domain transfer learning.【Conclusion】Therefore,

关 键 词：光通信系统 非线性损伤补偿 卷积神经网络 双向长短期记忆 迁移学习 

分 类 号：TN929[电子电信—通信与信息系统]