FedNET: Federated Learning for Proactive Traffic Management and Network Capacity Planning

TL;DR

FedNET introduces a federated learning framework for proactive, privacy-preserving traffic prediction and high-risk link identification in large-scale networks, enabling early capacity planning and stress detection without exposing sensitive data.

Contribution

The paper presents FedNET, a novel federated learning approach for multi-step traffic forecasting and risk assessment in networks, improving privacy and prediction accuracy over centralized methods.

Findings

FL achieves near-centralized accuracy with $R^2 >0.92$ for short-term forecasts.

Longer prediction horizons still provide meaningful $R^2$ scores around 0.45-0.55.

FedNET effectively predicts high-risk links three days in advance, aiding proactive network management.

Abstract

We propose FedNET, a proactive and privacy-preserving framework for early identification of high-risk links in large-scale communication networks, that leverages a distributed multi-step traffic forecasting method. FedNET employs Federated Learning (FL) to model the temporal evolution of node-level traffic in a distributed manner, enabling accurate multi-step-ahead predictions (e.g., several hours to days) without exposing sensitive network data. Using these node-level forecasts and known routing information, FedNET estimates the future link-level utilization by aggregating traffic contributions across all source-destination pairs. The links are then ranked according to the predicted load intensity and temporal variability, providing an early warning signal for potential high-risk links. We compare the federated traffic prediction of FedNET against a centralized multi-step learning baseline and then systematically analyze the impact of history and prediction window sizes on forecast accuracy using the $R^2$ score. Results indicate that FL achieves accuracy close to centralized training, with shorter prediction horizons consistently yielding the highest accuracy ($R^2 >0.92$), while longer horizons providing meaningful forecasts ($R^2 \approx 0.45\text{--}0.55$). We further validate the efficacy of the FedNET framework in predicting network utilization on a realistic network topology and demonstrate that it consistently identifies high-risk links well in advance (i.e., three days ahead) of the critical stress states emerging, making it a practical tool for anticipatory traffic engineering and capacity planning.