Loss weight adaptive multi-task learning based optical performance monitor for multiple parameters estimation.
Loss weight adaptive multi-task learning based optical performance monitor for multiple parameters estimation.
复制标题
DOI：
10.1364/oe.27.037041
复制
发表时间：
2019-12
期刊：
影响因子：
3.8
通讯作者：
Zhenming Yu;Zhiquan Wan;Liang Shu;Shaohua Hu;Yilun Zhao;Jing Zhang-;Kun Xu
中科院分区：
文献类型：
--
作者：
Zhenming Yu;Zhiquan Wan;Liang Shu;Shaohua Hu;Yilun Zhao;Jing Zhang-;Kun Xu
将一种基于减重自适应多任务学习的人工神经网络(MTL-ANN)应用于联合光信噪比监测和调制格式识别(MFI)。利用5 km标准单模光纤(SSMF)传输的偏振分复用(PDM)相干光学系统实验验证了该监测系统的有效性。选择包括九种调制自适应M-QAM格式的一组调制方案作为发送信号。选择基于恒模算法(CMA)的极化解复用后的信号幅度直方图作为输入特征，而不是圆形星座。实验结果表明，在估计的光信噪比范围内，MFI的准确率达到100%。此外，当处理为回归问题和分类问题时，OSNR估计的均方根误差(RMSE)为0.68dB，精度为98.7%。与固定失重的MTL-ANN不同，失重自适应MTL-ANN可以针对不同的链路配置自动搜索最优的失重率。此外，估计参数的个数可以很容易地扩展，这对于未来异构光网络中的多参数估计具有很大的吸引力。
A loss weight adaptive multi-task learning based artificial neural network (MTL-ANN) is applied for joint optical signal-to-noise ratio (OSNR) monitoring and modulation format identification (MFI). We conduct an experiment of polarization division multiplexing (PDM) coherent optical system with 5 km standard single mode fiber (SSMF) transmission to verify this monitor. A group of modulation schemes including nine modulation adaptive M-QAM formats are selected as the transmission signals. Instead of circular constellation, signals' amplitude histograms after constant module algorithm (CMA) based polarization de-multiplexing are selected as input features for our proposed monitor. The experimental results show that the MFI accuracy reaches 100% in the estimated OSNR range. Furthermore, when treated as regression problem and classification problem, OSNR estimation with a root mean-square error (RMSE) of 0.68 dB and an accuracy of 98.7% are achieved, respectively. Unlike loss weight fixed MTL-ANN, loss weight adaptive MTL-ANN could search the optimal loss weight ratio automatically for different link configurations. Besides that, the number of estimated parameters can be easily expanded, which is attractive for multiple parameters estimation in future heterogeneous optical networks.