Simultaneous Monitoring of Chromatic Dispersion and Optical Signal to Noise Ratio in Optical Network Using Asynchronous Delay Tap Sampling and Convolutional Neural Network (Deep Learning)

The article presents the possibilities of using Asynchronous Delay Tap Sampling (ADTS) and Convolutional Neural Network (CNN) methods to simultaneously monitor the parameters of Chromatic Dispersion (CD) and Optical Signal to Noise Ratio (OSNR), which have a significant impact on the quality of transmission in the optical network. Using the ADTS method, which allows the presentation of impairments in the form of characteristics, a set of 10000 images was generated simultaneously disturbed by the combination of CD and OSNR phenomena. Next, using the CNN algorithms, the network learning process was carried out in order to obtain the best possible model for recognizing impairments and predicting their values. After the appropriate number of tests, very good results were obtained ensuring a high adjustment of the models at the level of the matching factor R
²
(Coefficient of determination) above 0.995. Models with such a fit fulfil the requirements set for monitoring systems to recognize the value of occurring impairments within appropriate accuracy limits.