光路传输质量智能预测技术  

Intelligent prediction technology for optical path quality of transmission

作　　者：谷志群 周宇航 张佳玮[1] 纪越峰[1] GU Zhiqun;ZHOU Yuhang;ZHANG Jiawei;JI Yuefeng(State Key Laboratory of Information Photonics and Optical Communications,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]北京邮电大学信息光子学与光通信全国重点实验室,北京100876

出　　处：《光通信技术》2024年第3期1-6,共6页Optical Communication Technology

基　　金：国家自然科学基金项目(62101058、U21B2005)资助;河北省省级科技计划项目(22567624H)资助。

摘　　要：针对传统基于数理模型的光路传输质量(QoT)预测方法难以同时满足高精度和低计算复杂度需求的问题,介绍了单光路、多光路、跨拓扑光路3种光路QoT智能预测技术。这些技术依托于机器学习模型,力求实现端到端光路QoT的精确预测,并可有效应对以下挑战:其一,面对物理层参数的多样性,如何选择适合的机器学习模型和输入特征;其二,如何有效捕捉光路间错综复杂的关系;其三,如何在少样本情况下实现网络模型的训练和持续优化。最后,对未来的光路QoT预测技术发展方向进行了展望。Addressing the challenge of traditional mathematical model-based quality of transmission(QoT)prediction methods struggling to simultaneously meet the demands of high precision and low computational complexity,this paper introduces three intelligent QoT prediction techniques for single optical paths,multiple optical paths,and cross-topology optical paths.These tech-niques rely on machine learning models to achieve accurate end-to-end optical path QoT predictions and effectively tackle the following challenges:firstly,how to select appropriate machine learning models and input features amidst the diversity of physi-cal layer parameters.Secondly,how to effectively capture the intricate relationships among optical paths.Thirdly,how to train and continuously optimize network models with limited samples.Finally,the article offers a glimpse into the future development directions of optical path QoT prediction technologies.

关 键 词：光网络 光路传输质量 机器学习 

分 类 号：TN256[电子电信—物理电子学]