1.国网湖北直流公司,湖北 宜昌 443005
2.华中科技大学 光学与电子信息学院,武汉 430074
段施奇(1988-),男,湖北武汉人。高级工程师,本科,主要研究方向为光通信与电力通信系统。
程孟凡,教授。E-mail:chengmf@hust.edu.cn
收稿:2025-10-30,
修回:2025-11-13,
纸质出版:2026-10-10
移动端阅览
段施奇,范金泽,陈海健,等. 基于VCSEL的偏振自稳定储备池结构[J]. 光通信研究,2026(5): 145-149.
Duan S Q, Fan J Z, Chen H J, et al. Self-stabilizing Polarization Reservoir Computing based on VCSEL[J]. Study on Optical Communications, 2026(5): 145-149.
段施奇,范金泽,陈海健,等. 基于VCSEL的偏振自稳定储备池结构[J]. 光通信研究,2026(5): 145-149. DOI: 10.13756/j.gtxyj.2026.250340.
Duan S Q, Fan J Z, Chen H J, et al. Self-stabilizing Polarization Reservoir Computing based on VCSEL[J]. Study on Optical Communications, 2026(5): 145-149. DOI: 10.13756/j.gtxyj.2026.250340.
目的
2
近年来,随着人工智能(AI)技术的飞速发展,模型训练所需的算力也快速增长。储备池神经网络作为一种可物理实现的光子学神经网络,以其训练成本低,易于硬件实现等特点,逐渐被广为关注,在时序信息处理中有着广泛的应用。储备池的非线性节点有丰富的光学非线性器件选择,垂直腔表面发射激光器(VCSEL)因有体积小、光束质量好、非线性丰富等特征,近年来开始被广泛用于储备池神经网络中。基于VCSEL的偏振复用储备池能够实现高速的任务并行处理,是一种高效的储备池计算方式。然而在偏振复用模型中,温度、应力等外界环境变化会显著改变光纤双折射,从而导致偏振态旋转,对储备池的计算稳定性带来了不可忽视的干扰。
方法
2
为解决此问题,文章提出了一种含有偏振自稳定结构的VCSEL偏振复用储备池,利用磁光效应原理以及光纤的互异性传输实现在时间延迟线上的偏振自稳定,减小光纤中双折射对偏振态引入的噪声。
结果
2
通过Santa-Fe时间序列预测、信道均衡、光电振荡器(OEO)混沌同步三个任务,验证了所提偏振自稳定结构的有效性。还通过信道均衡与OEO同步两任务并行处理的测试,验证了该结构在多任务并行处理中的适用性。
结论
2
该结构为将来进一步提升储备池容量和长期计算稳定性提供了可行的思路。
Objective
2
In recent years
the rapid advancement of Artificial Intelligence (AI) technology has significantly increased the computational power required for model training. Reservoir computing (RC)
as physically realizable photonic neural networks
have garnered widespread attention due to their low training costs and ease of hardware implementation
demonstrating broad applications in temporal information processing. The nonlinear nodes in reservoirs offer diverse optical nonlinear device options. Vertical Cavity Surface Emitting Lasers (VCSELs)
characterized by compact size
high beam quality
and rich nonlinear dynamics
have recently been widely adopted in RC. Polarization-multiplexed VCSEL-based reservoirs enable high-speed parallel task processing
representing an efficient reservoir computing approach. However
in polarization-multiplexed systems
environmental variations such as temperature and stress can alter fiber birefringence
which leads to the polarization state rotation and brings non-negligible interference to the computational stability of the reservoir.
Methods
2
To address this issue
this paper proposes a polarization-multiplexed VCSEL reservoir with a self-stabilizing polarization structure. By leveraging the magneto-optic effect and reciprocal fiber transmission
the design achieves polarization stabilization on time-delay lines
effectively reducing birefringence-induced polarization noise in optical fibers.
Results
2
The effectiveness of the proposed structure is validated through three tasks: Santa Fe time series prediction
channel equalization
and opto-electronic oscillator (OEO) chaotic synchronization. The article also demonstrates the impact of the structure in multi-task parallel processing by testing the parallel processing of two tasks
channel equalization and OEO synchronization.
Conclusion
2
This structure provides a feasible approach to further enhance reservoir capacity and long-term computational stability in future applications.
贾科军 , 牛振 , 于凯 , 等 . 基于SSA-ELM神经网络的室内可见光定位系统 [J ] . 光通信研究 , 2025 ( 1 ): 230154 .
Jia K J , Niu Z , Yu K , et al . Indoor Positioning System based on SSA-ELM Neural Network for Visible Light [J ] . Study on Optical Communications , 2025 ( 1 ): 230154 .
马愈昭 , 张岩峰 , 冯帅 . 基于神经网络的侧向激光雷达信号去噪算法 [J ] . 光电工程 , 2023 , 50 ( 6 ): 220341 .
Ma Y Z , Zhang Y F , Feng S . A Denoising Algorithm based on Neural Network for Side-scatter Lidar Signal [J ] . Opto-Electron Eng , 2023 , 50 ( 6 ): 220341 .
项水英 , 宋紫薇 , 张雅慧 , 等 . 光子神经网络研究进展 [J ] . 光电工程 , 2024 , 51 ( 7 ): 240101 - 240124 .
Xiang S Y , Song Z W , Zhang Y H , et al . Progress in the Research of Optical Neural Networks [J ] . Opto-Electron Engineering , 2024 , 51 ( 7 ): 240101 .
Vandoorne K , Dambre J , Verstraeten D , et al . Parallel reservoir Computing using Optical Amplifiers [J ] . IEEE Transactions on Neural Networks , 2011 , 22 ( 9 ): 1469 - 1481 .
Mesaritakis C , Papataxiarhis V , Syvridis D . Micro Ring Resonators as Building Blocks for an All-optical High-speed Reservoir-computing Bit-pattern-recognition System [J ] . JOSA B , 2013 , 30 ( 11 ): 3048 - 3055 .
Vandoorne K , Mechet P , Van Vaerenbergh T , et al . Experimental Demonstration of Reservoir Computing on a Silicon Photonics Chip [J ] . Nature Communications , 2014 , 5 ( 1 ): 3541 .
Appeltant L , Soriano M C , Van Der Sande G , et al . Information Processing Using a Single Dynamical Node as Complex System [J ] . Nature Communications , 2011 , 2 ( 1 ): 468 .
Larger L , Soriano M C , Brunner D , et al . Photonic information Processing beyond Turing: an Optoelectronic Implementation of Reservoir Computing [J ] . Optics Express , 2012 , 20 ( 3 ): 3241 .
Duport F , Schneider B , Smerieri A , et al . All-optical Reservoir Computing [J ] . Optics Express , 2012 , 20 ( 20 ): 22783 .
Nakayama J , Kanno K , Uchida A . Laser Dynamical Reservoir Computing with Consistency: anApproach of a Chaos Mask Signal [J ] . Optics Express , 2016 , 24 ( 8 ): 8679 .
Vatin J , Rontani D , Sciamanna M . Enhanced Performance of a Reservoir Computer using Polarization Dynamics in VCSELs [J ] . Optics Letters , 2018 , 43 ( 18 ): 4497 .
Dong Y , Shi Y , Feng J , et al . Equalization of Short-reach IMDD Transmission with Enhanced Reservoir Computing [J ] . Journal of Lightwave Technology , 2025 , 43 ( 3 ): 1212 - 1221 .
Hasegawa H , Kanno K , Uchida A . Parallel and Deep Reservoir Computing using Semiconductor Lasers with Optical Feedback [J ] . Nanophotonics , 2023 , 12 ( 5 ): 869 - 881 .
Guo X X , Xiang S Y , Zhang Y H , et al . Polarization Multiplexing Reservoir Computing based on a VCSEL With Polarized Optical Feedback [J ] . IEEE Journal of Selected Topics in Quantum Electronics , 2020 , 26 ( 1 ): 1 - 9 .
Takushima Y , Yamashita S , Kikuchi K , et al . Polarization-stable and Single-frequency Fiber Lasers . Journal of Lightwave Technology , 1998 , 16 ( 4 ): 661 - 669 .
Lavrov R , Jacquot M , Larger L . Nonlocal Nonlinear Electro-Optic Phase Dynamics Demonstrating 10 Gb/s Chaos Communications [J ] . IEEE Journal of Quantum Electronics , 2010 , 46 ( 10 ): 1430 - 1435 .
0
浏览量
0
下载量
0
CSCD
0
CNKI被引量
关联资源
相关文章
相关作者
相关机构
鄂公网安备 42011202002092号