Fast neural network inverse model to maximize throughput in ultra-wideband WDM systems

Ultra-wideband systems expand the optical bandwidth in wavelength-division multiplexed (WDM) systems to provide increased capacity using the existing fiber infrastructure. In ultra-wideband transmission, power is transferred from shorter-wavelength WDM channels to longer-wavelength WDM channels due to inelastic inter-channel stimulated Raman scattering. Thus, managing launch power is necessary to improve the overall data throughput. While the launch power optimization problem can be solved by the particle swarm optimization method it is sensitive to the objective value and requires intensive objective calculations. Hence, we first propose a fast and accurate data-driven deep neural network-based physical layer in this paper which can achieve 99<i>%</i>-100<i>%</i> throughput compared to the semi-analytical approach with more than 2 orders of magnitude improvement in computational time. To further reduce the computational time, we propose an iterative greedy algorithm enabled by the inverse model to well approximate a sub-optimal solution with less than 6<i>%</i> performance degradation but almost 3 orders of magnitude reduction in computational time.