Joint Modulation Format Identification and OSNR Monitoring using MT-LIN model

The monitoring of parameters such as optical signal-to-noise ratio (OSNR), modulation format or dispersion in optical performance monitoring (OPM) technology is of great research significance to ensure the normal operation of dynamic and flexible optical communication networks. In this paper, a Multi-task joint monitoring model for modulation format identification (MFI) and OSNR estimation of Lightweight Convective Neural Network with Improved Inception Model (MT-LIN) is proposed. The recognition accuracy of MT-LIN model for BPSK, QPSK, 8PSK, 16QAM, 32QAM and 64QAM is 99.32%, and the average root mean square error (RMSE) of OSNR monitoring for six modulation formats is 0.52dB. In conclusion, we designed a multi-task learning model to realize the joint monitoring of modulation format and OSNR, which meets the practical application requirements of dynamic multi-service optical communication scenarios.