Iterative Transfer Learning Approach for QoT Prediction of Lightpath in Optical Networks

Machine learning (ML) has been widely used in optical networks for accurate Quality-of-transmission (QoT) estimation of Lightpaths (LPs). However, this domain has two main issues: ML-based models require a sufficiently large amount of data for training, and once the model is trained on one type of configuration, it cannot be used for another configuration. This paper focuses on these two issues and proposes an Active Transfer Learning (ATL) based solution. In ATL, Active learning (AL) helps in reducing the dataset’s size while not compromising the model’s performance, while the Transfer learning (TL) concept enables the transfer of knowledge from a source domain to the target domain with improved accuracy. This combined approach of ATL delivers promising results with minimum data samples and enhanced performance.