ANN-Based Asymmetric QoT Estimation for Network Capacity Improvement of Low-Margin Optical Networks

Accurate quality-of-transmission (QoT) estimation prior to lightpath deployment is essential for minimizing design margins in optical networks. Owing to their high precision and strong generalization capabilities, artificial neural networks (ANNs) have emerged as a promising approach for lightpath QoT estimation. However, focusing exclusively on prediction accuracy is inadequate for maximizing global network capacity. Conventional models employing symmetric loss functions apply identical penalties to both overestimation and underestimation errors, thereby precluding controlled bias in predictions and their impact on overall network capacity. This paper investigates the margin configuration for the whole network capacity and proposes a novel QoT estimation method with asymmetric loss functions, which jointly considers the assessment of global network capacity and gives different penalties for overestimation and underestimation. We further present an iterative search algorithm grounded in network capacity considerations to optimize the parameters of these asymmetric loss functions. Simulation results confirm that our ANN-based models facilitate efficient modulation format assignment, leading to corresponding increases in network capacity.