A Study of Nonlinear Noise Monitoring in Fiber Optic Communication System Combined with a Deep Learning Algorithm
Jun Pan, Yanhui Wang, Dongliang Bian
In fiber optic communication systems, the presence of nonlinear noise has an impact on the performance of systems and needs to be reliably monitored. This paper first briefly introduced the fiber optic communication system and then applied a deep neural network (DNN). Eleven features were extracted from the optical signal, and the optical signal-to-noise ratio (OSNR) and nonlinear noise were monitored with the DNN. Moreover, experiments were carried out on the VPI Transmission Maker 9.0 platform to simulate both QPSK and 16QAM modulation formats. It was found that the means absolute error (MAE) value of the DNN was smaller than those of SVM and BPNN. The MAE of the DNN was smaller than 0.3 dB in OSNR monitoring and smaller than 1.2 dB in nonlinear monitoring. The experimental results demonstrate the reliability of the method combined with deep learning for nonlinear noise monitoring. The proposed method can be applied in practice.
Keywords: machine learning, fiber optic communication, nonlinear noise, monitoring