Two-Stage Federated Learning-Based Aggregated Traffic Prediction in Edge Computing-Enabled Metro Optical Networks

We propose a hierarchical model aggregation-based federated learning framework that handles heterogeneous and imbalanced data for traffic prediction in edge computing-enabled metro optical networks (MONs). It reduces the prediction errors by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\sim 5\%$</tex> for large-scale MONs.