Multi-Functional Optical Spectrum Analysis Using Multi-Task Cascaded Neural Networks

Abstract

In the optical communication systems, the optical spectrum (OS) provides useful informations for optical performance monitoring and optical link diagnosis. In this paper, we investigate the neural-network based OS analysis (OSA) techniques able to simultaneously recognize the OS and estimate the optical signal to noise ratio (OSNR), cascaded filtering distortion (CFD) and carrier wavelength drift (CWD). We demonstrate that, compared with the multi-task artificial neural network (MT-ANN) and convolutional neural network (MT-CNN), the proposed multi-task cascaded ANNs (CANN) and cascaded CNNs (CCNN) can greatly improve the OSA performance and accelerate the training process by exploiting specific features and loss functions for different tasks. The CCNN able to deal with the high-resolution OS (HOS) can further improve the OSA performance compared with the CANN. The averaged OS recognition accuracy and OSNR, CFD and CWD estimation errors obtained with the CCNN (CANN) for the 15 kinds of optical signals are 99.32% (97.07%), 0.36 (0.55) dB, 0.24 (0.32) and 0.04 (0.06) GHz, respectively, even when the various OS distortions are present. The proposed CANN and CCNN with a better versatility, higher OSA accuracy and faster convergence speed are promising enabling techniques for the future intelligent OSA systems.

Joint OSNR and Nonlinear Noise Power Estimation Based on Deep Learning for Coherent Optical Communication Systems

“…For nonlinear noise power estimation, the estimation error is also less than 1.0 dB and is tolerant for different launch power and transmission distance. The results indicate that this joint estimation scheme is transparent for modulation format information and is insensitive to CD and PMD [22,23]. The proposed joint OSNR and nonlinear noise power estimation scheme may provide an ideal candidate for future dynamic and flexible optical networks due to the advantages of low complexity and easy implementation.…”

“…The OSNR degradation caused by the accumulated ASE noise makes the lower part of the optical spectrum submerge below the noise pedestal, and meanwhile raising both of the optical spectrum edges is shown in Fig. 3(a) [22,24]. From Fig.…”

“…The effects of ASE noise and nonlinearity on OSNR estimation, and the effects of different launch power and transmission distance on nonlinear noise power estimation are discussed separately. Since the optical spectrum is insensitive to CD and polarization mode dispersion (PMD) [22,23], this scheme achieves accurate estimation of OSNR and nonlinear noise power even in fiber optic transmission systems with large cumulative dispersion and modulation format transparency.…”