Generalized optical signal-to-noise ratio monitoring using a convolutional neural network for digital coherent receivers

Abstract

In this Letter, we propose a generalized optical signal-to-noise ratio (GOSNR) monitoring scheme using a convo-lutional neural network trained on constellation density features acquired from a back-to-back setup and demon-strate accurate GOSNR estimations for links having dif-ferent nonlinearities. The experiments were carried over dense wavelength division multiplexing links configured on 32-Gbaud polarization division multiplexed 16-quadrature amplitude modulation (QAM) and demonstrated that the GOSNRs are estimated within 0.1 dB mean absolute error with maximum estimation errors below 0.5 dB on metro class links. The proposed technique does not require any informa-tion about the noise floor in the conventional spectrum-based means and therefore is readily deployable for real-time mon-itoring. (c) 2023 Optica Publishing Group