Optical performance monitoring using lifelong learning with confrontational knowledge distillation in 7-core fiber...

We propose a novel optical performance monitoring (OPM) scheme, including modulation format recognition (MFR) and optical signal-to-noise ratio (OSNR) estimation, for 7-core fiber in elastic optical networks (EONs) by using the specific Stokes sectional images of the received signals. Meanwhile, MFR and OSNR estimation in all channels can be utilized by using a lightweight neural network via lifelong learning. In addition, the proposed scheme saves the computational resources for real implementation through confrontational knowledge distillation, making it easy to deploy the proposed neural network in the receiving end and intermediate node. Five modulation formats, including BPSK, QPSK, 8PSK, 8QAM, and 16QAM, were recognized by the proposed scheme within the OSNR of 10-30 dB over 2 km weakly coupled 7-core fiber. Experimental results show that 100% recognition accuracy of all these five modulation formats can be achieved while the RMSE of the estimation is below 0.1 dB. Compared with conventional neural network architectures, the proposed neural network achieves better performance, whose runtime is merely 20.2 ms, saving the computational resource of the optical network.