论文部分内容阅读
提出了一种基于异步降频光采样眼图重构和人工神经网络(ANN)的光性能监测(OPM)新方法。首先对被监测光信号进行异步降频光采样,通过软件同步算法进行眼图重构;然后提取重构眼图的特征参数对ANN进行训练;最后以ANN的预测输出对光信号的损伤进行监测。构建10 Gb/s NRZ-OOK4、0 Gb/s RZ-OOK和40 Gb/s RZ-DPSK仿真实验系统,进行光信噪比(OSNR)和色散(CD)参数监测。结果表明,本文方法进行OPM具有较高的精度,ANN预测输出与测试数据的相关系数大于0.98,损伤监测的平均误差小于5%。
A new optical performance monitoring (OPM) method based on asynchronous down-sampled optical eye reconstruction and artificial neural network (ANN) is proposed. Firstly, asynchronous down-light sampling of the monitored optical signal is carried out and reconstructed by the software synchronization algorithm. Then the characteristic parameters of the reconstructed eye are extracted to train the ANN. Finally, the damage of the optical signal is monitored by the predictive output of ANN . The 10 Gb / s NRZ-OOK4, 0 Gb / s RZ-OOK and 40 Gb / s RZ-DPSK simulation system were constructed to monitor the optical signal noise ratio (OSNR) and dispersion (CD) parameters. The results show that the method proposed in this paper has higher precision. The correlation coefficient between ANN prediction output and test data is greater than 0.98, and the average error of damage monitoring is less than 5%.