基于半监督深度学习的光学性能监测

Optical Performance Monitoring Based on Semi-Supervised Deep Learning

针对在动态光网络中使用传统深度学习进行多节点光信号监测时存在需要大量标记样本、无标记样本没能得到充分利用和样本标记困难等问题,提出一种基于半监督深度学习的光学性能监测方法,将大量未标记的异步延迟抽头图作为FixMatch模型的输入进行光信噪比监测。研究结果表明,与半监督学习Mean Teacher和卷积神经网络等传统方法相比,FixMatch方法在数据标记率仅为10%、传输速度为40 Gbit/s且调制格式分别为16阶正交振幅调制(QAM)、32QAM和64QAM的情况下,分别实现了100.00%、98.67%和98.44%的分类精度;将数据标记率降到5%,FixMatch方法也能保持99.33%、96.00%和97.67%的优秀分类结果。同时通过色散实验得到,相较于其他方法,FixMatch方法具有明显优势。此外,将其视为分类和回归任务得到的分类精度和平均绝对误差分别为99.33%和0.095 dB。这证明了利用未标记数据能有效提高光学性能监测模型的性能和泛化能力。此外,还讨论了较低数据标记率对该方法的影响。

For multinode optical signal monitoring based on traditional deep learning techniques in dynamic optical networks,many labeled samples and unlabeled samples are not fully used,and sample labeling is difficult.This paper introduces an optical performance monitoring method based on semisupervised deep learning.The proposed method uses a substantial amount of unlabeled asynchronous delaytap photographs as input features for the FixMatch model to monitor optical signaltonoise ratio.The results show that compared to traditional methods,such as semisupervised learning Mean Teacher and convolutional neural networks,FixMatch achieves classification accuracies of 100.00%,98.67%,and 98.44%for different modulation formats,such as 16-quadrature amplitude modulation(16QAM),32QAM,and 64QAM,respectively,at a transmission speed of 40 Gbit/s using only 10%labeled data.When the labeling rate is reduced to 5%,FixMatch still maintains good results with accuracies of 99.33%,96.00%,and 97.67%.Dispersion experiments demonstrate the clear advantage of FixMatch compared to other methods.Furthermore,considering it as both a classification and regression task yields a classification accuracy and mean absolute error of 99.33%and 0.095 dB,respectively.This study demonstrates the effectiveness of using unlabeled data to improve the performance and generalization capability of optical performance monitoring models.In addition,the effect of a lower labeled data rate on the method is discussed.