AI 中文总结
研究棕地光链路中光信噪比等预测问题,采用基于DLM的混合物理/机器学习框架,校准跨距/光线路放大器边界,单通道和OSaaS配置中光信噪比/广义光信噪比误差小。
AI 中文摘要
我们提出了一种用于棕地光链路的基于DLM的混合物理/机器学习框架,可精确预测每通道功率、光信噪比和广义光信噪比。通过DLM校准跨距/光线路放大器边界,在单通道和光服务即服务(OSaaS)配置中,光信噪比/广义光信噪比误差不超过0.39/0.43分贝。
英文摘要
We present a DLM-anchored hybrid physics/ML framework for brownfield optical links that accurately predicts per-channel power, OSNR, and GSNR. Calibrating span/ILA boundaries via DLM yields OSNR/GSNR errors of no more than 0.39/0.43 dB across single-channel and OSaaS provisioning.
Comments3 pages, 4 figures. Published in Optical Fiber Communication Conference (OFC) 2026
Journal refOptical Fiber Communication Conference (OFC) 2026, paper M4A.5