版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
作者机构:Beijing Univ Posts & Telecommun Sch Elect Engn State Key Lab Informat Photon & Opt Commun Beijing 100876 Peoples R China Beijing Inst Technol Beijing 100081 Peoples R China Beijing Univ Posts & Telecommun Beijing Key Lab Space Round Interconnect & Converg Beijing 100876 Peoples R China Changzhou Jingxin New Generat Informat Technol Res Changzhou 213161 Peoples R China
出 版 物:《JOURNAL OF LIGHTWAVE TECHNOLOGY》 (J Lightwave Technol)
年 卷 期:2025年第43卷第7期
页 面:3078-3089页
核心收录:
学科分类:0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0702[理学-物理学]
基 金:National Natural Science Foundation of China [61835002, 61935005] Funds for National Key Scientific Instrument Development Program Beijing Municipal Natural Science Foundation [JQ24018] Program for Youth Innovative Research Team of BUPT [2024YQTD02]
主 题:Blind equalizers Fitting Probabilistic logic Optical fibers Optical fiber networks Adaptive equalizers Accuracy Optical transmitters Estimation Clustering algorithms Blind equalization probabilistic shaping discrete Gaussian fitting coherent optical fiber communication
摘 要:A flexible multi-rate adaptive blind equalization scheme based on probabilistic shaping (PS) in coherent optical fiber communication systems is proposed, addressing the performance degradation of clustering algorithms when performing nonlinear blind equalization for high-order modulation signals in PS systems. The scheme analyzes received signals distribution using the discrete Gaussian fitting theory and combines it with a weighted clustering algorithm to implement the Gaussian-weighted decision equalization (GWDE) method, enabling adaptive blind equalization for PS signals. Moreover, the scheme utilizes the probability distribution characteristics of the equalization process to implement the shaping degree estimation (SDE), enabling accurate quantification of the signal shaping degree. The proposed scheme has been experimentally and numerically validated in a 64QAM coherent optical fiber communication system. The results show that for $\nu = 0.05$ PS-64QAM signals, the proposed scheme improves tolerance to nonlinear effects caused by launched optical power (LOP). Compared to the unequalized signal, tolerance to these effects increases by over 1 dBm;relative to the K-means equalized signal, tolerance to LOP nonlinear effects improves by approximately 0.7 dBm. Additionally, the scheme reduces computational complexity by 12% compared to K-means. The proposed scheme also achieves 100% accuracy in estimating the degree of signal shaping, given the prerequisite of ensuring reliable communication. This approach holds significant potential for the dynamic rate transmission of diverse fine-grained services in future optical fiber communication systems.