Advanced formulation of QoT-Estimation for un-established lightpaths using cross-train machine learning methods

Planning tools with excellent accuracy along with precise and advance estimation of the quality of transmission (QoT) of lightpaths (LPs) have techno-economic importance for a network operator. The QoT metric of LPs is defined by the generalized signal-to-noise ratio (GSNR) which includes the effect of both amplified spontaneous emission (ASE) noise and non-linear interference (NLI) accumulation. Typically, a considerable number of analytical models are available for the estimation of QoT but all of them require the exact description of system parameters. Thus, the analytical models are impractical in case of un-used network scenarios. In this study, we exploit an alternative approach based on three machine learning (ML) techniques for QoT estimation (QoT-E). The proposed ML based techniques are cross-trained on the characteristic features extracted from the telemetry data of the already in-service network. This new approach provides a reliable QoT-E and consequently assists the network operator in network planning and also enables the reliable low-margin LP deployment.