Identifying Probabilistically Shaped Modulation Formats Through 2D Stokes Planes With Two-Stage Deep Neural Networks

Abstract

A lightweight two-stage convolutional (deep) neural network (CNN) based modulation format identification (MFI) scheme is proposed and demonstrated for the polarization domain multiplexing (PDM) fiber communication system with probabilistically shaped (PS) modulation formats. The scheme is tested on a PDM system at a symbol rate of 28 GBaud. Six probabilistically shaped (PS) modulation formats (of 3 bit/symbol PS-16QAM, PS-32QAM, and PS-64QAM, of 4 bit/symbol PS-32QAM and PS-64QAM, and of 5 bit/symbol PS-64QAM) along with six standard modulation formats (BPSK, QPSK, 8PSK and three uniformly shaped (US) QAM: US-16QAM, US-32QAM and US-64QAM) are identified by the trained CNN. By taking advantage of computer vision, the results show that the proposed scheme can provide very high accuracy and significantly improve the identification performance over the existing techniques. The influences of the learning rate of the CNN are also discussed. INDEX TERMS Optical fiber communication, modulation format identification, convolutional neural networks.

Machine Learning Techniques for Optical Performance Monitoring and Modulation Format Identification: A Survey

“…Similarly, it would be the case with the probabilistic shaping 64-QAM format and the standard 16-QAM format. Therefore, current MFI techniques used for standard M-QAM modulation formats may produce low classification accuracy when employed for the classification of probabilistic shaping modulation formats, and hence new MFI techniques are required for such new formats [218].…”

Multi-Task Learning Convolutional Neural Network and Optical Spectrums Enabled Optical Performance Monitoring

“…Currently, a plethora of frequency domain, time domain, and polarization domain OSR and OSNR monitoring technologies have been proposed [7]. In the time domain and polarization domain, constellation diagrams [8], eye diagrams [9], and stokes planes [10] have been utilized for OSR. Similarly, OSNR monitoring methods based on asynchronous delay-tap sampling (ADTS) [11], asynchronous single channel sampling (ASCS) [12], waveforms [13], amplitude histograms (AHs) [6] have also been proposed.…”