Abstract
The optical signal-to-noise ratio (OSNR) and received optical channel power are critical parameters in determining the quality of transmission. The OSNR and received optical channel power are influenced by network impairments such as fiber loss, amplified stimulated emission noise, and nonlinear impairments. Furthermore, environmental effects and routing, modulation, and spectrum assignment schemes influence the OSNR and thus the reach of the optical channels. These impairments and effects vary with the spectral loads that are hard to predict in brownfield networks. Several deep neural network (DNN)-based methods have been explored to estimate the OSNR and nonlinear noise. However, these methods ignore the network topology. This paper bridges this gap by leveraging supervised graph convolution neural networks (GCNs), which operate directly on graphs for OSNR and received power estimation in an optical mesh network. We also develop and implement a novel graph windowed neural network (GWinN) to reduce the over-smoothing effects of a GCN and thus learn localized behaviors like fiber cuts. We apply a DNN, GCN, and GWinN in practice to a testbed of 8 reconfigurable optical add-drop multiplexers and 22 amplifiers. Our procedure accurately estimates the OSNR with a prediction error mean and a standard deviation of (${-}{0.02}\;{\rm dB}$, 0.35 dB) for a reference OSNR ranging from (16 dB) to (24 dB).
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Rana Kumar Jana, Bijoy Chand Chatterjee, Abhishek Pratap Singh, Anand Srivastava, Biswanath Mukherjee, Andrew Lord, and Abhijit Mitra
J. Opt. Commun. Netw. 14(11) 882-893 (2022)
Jasper Müller, Sai Kireet Patri, Tobias Fehenberger, Helmut Griesser, Jörg-Peter Elbers, and Carmen Mas-Machuca
J. Opt. Commun. Netw. 14(12) 1010-1019 (2022)
Ihtesham Khan, Muhammad Bilal, M. Umar Masood, Andrea D’Amico, and Vittorio Curri
J. Opt. Commun. Netw. 13(4) B72-B82 (2021)