Federated Learning in Mobile Networks: A Comprehensive Case Study on Traffic Forecasting

TL;DR

This work demonstrates a comprehensive federated learning framework for multi-site mobile traffic forecasting at the network edge, using real Barcelona LTE data. It formalizes the FL objective, employs an LSTM-based predictor, and evaluates both predictive accuracy and a sustainability metric that accounts for energy and data-transfer costs. Through extensive ablations, it shows that federated learning achieves strong predictive performance with favorable energy trade-offs, benefits from client selection and personalization, and can be enhanced by incorporating exogenous data sources. The study provides actionable insights for deploying privacy-preserving, environmentally conscious FL-driven traffic management in next-generation mobile networks.

Abstract

The increasing demand for efficient resource allocation in mobile networks has catalyzed the exploration of innovative solutions that could enhance the task of real-time cellular traffic prediction. Under these circumstances, federated learning (FL) stands out as a distributed and privacy-preserving solution to foster collaboration among different sites, thus enabling responsive near-the-edge solutions. In this paper, we comprehensively study the potential benefits of FL in telecommunications through a case study on federated traffic forecasting using real-world data from base stations (BSs) in Barcelona (Spain). Our study encompasses relevant aspects within the federated experience, including model aggregation techniques, outlier management, the impact of individual clients, personalized learning, and the integration of exogenous sources of data. The performed evaluation is based on both prediction accuracy and sustainability, thus showcasing the environmental impact of employed FL algorithms in various settings. The findings from our study highlight FL as a promising and robust solution for mobile traffic prediction, emphasizing its twin merits as a privacy-conscious and environmentally sustainable approach, while also demonstrating its capability to overcome data heterogeneity and ensure high-quality predictions, marking a significant stride towards its integration in mobile traffic management systems.

Figures (8)

• Figure 1: Overview of federated learning traffic prediction involving multiple BS sites. The steps corresponding to FL model training are marked with green circles.
• Figure 2: Average KL-divergence between datasets from different BSs.
• Figure 3: Special events that affect the RNTI count in LCCN, EB, and S1.
• Figure 4: Mean and standard deviation of the MAE obtained by each learning approach, for different prediction step values $T\in[1-10]$.
• Figure 5: MAE achieved by applying each considered outlier detection and correction method.