光通信技术2025，Vol.49Issue(3)：108-113,6.DOI:10.13921/j.cnki.issn1002-5561.2025.03.018
基于Stokes空间和Stacking模型的调制格式识别
Modulation format identification based on Stokes space and Stacking model
摘要
Abstract
To improve the accuracy and robustness of modulation format identification(MFI)in elastic optical network(EON),this paper proposes an MFI method based on Stokes space and a Stacking model.The method extracts one-dimensional probabili-ty distribution features of the three axes in Stokes space using kernel density estimation to construct a 240-dimensional feature vector.A genetic algorithm is employed to optimize the combination of base models and meta-models in the Stacking model,while Bayesian optimization is used for hyperparameter tuning,enhancing classification performance under low signal-to-noise ratios.Simulation results show that,within an optical signal-to-noise ratio(OSNR)range of 5～30 dB,the model achieves a macro-average area under the receiver operating characteristic curve(AUC)of 1.The identification accuracy exceeds 98.5％for modulation formats such as polarization-division multiplexing binary phase-shift keying(PDM-BPSK)and polarization-division multiplexing quadrature phase-shift keying(PDM-QPSK),with an average accuracy improvement of 2.05％～5.63％ compared to benchmark models like XGBoost and TabNet.Additionally,100％identification precision is achieved at an OSNR of 18 dB.关键词
弹性光网络/调制格式识别/集成学习/光信噪比Key words
elastic optical network/modulation format identification/ensemble learning/optical signal-to-noise ratio分类
电子信息工程引用本文复制引用
刘昱,刘战胜..基于Stokes空间和Stacking模型的调制格式识别[J].光通信技术,2025,49(3):108-113,6.基金项目
江苏大学高级人才科研启动基金(16JDG023)资助. （16JDG023）
