Combining QoT Regression and Modulation Format Classification for Reliable Lightpath Provisioning in Elastic Optical Networks

Paper i proceeding, 2024

The dynamic provisioning of lightpaths in elastic op- tical networks (EONs) requires the decision of which modulation format (MF) to be used by the lightpath. This requires the quality of transmission (QoT) estimation of the unestablished lightpath. machine learning (ML) has been used as an effective QoT estimator in the presence of uncertain physical layer parameters. However, minor inaccuracies in the estimation may lead to the incorrect modulation format selection. In this paper, we analyze this issue, and propose the use of two ML models that, combined, reduce the incorrect modulation format selection compared to the cases of using a single model.