An Informativeness-based Clustered Federated Learning Method for Reliable Traffic Prediction in Managed Wi-Fi Networks

2026-07-29

AI Summary

This work addresses the challenge of traffic prediction in managed Wi-Fi networks, where data heterogeneity across access points hinders model performance. To tackle this issue, the authors propose an information-theoretic clustering-based federated learning approach. The method employs a two-stage clustering pipeline to construct multiple local prediction models and leverages differential entropy to quantify intra-cluster information richness, prioritizing optimization of the smallest clusters to balance prediction accuracy and communication overhead. When clustering quality is insufficient, the framework automatically reverts to a global model. Experimental results demonstrate that the proposed method significantly outperforms existing distributed strategies on Wi-Fi traffic prediction tasks, achieving superior predictive performance with minimal communication and energy costs—only marginally exceeding the overhead of single-model federated learning when substantial accuracy gains are realized.

Abstract

Centrally-managed Wi-Fi solutions are increasingly leveraging Distributed Artificial Intelligence (AI) to predict key operational statistics of Access Points (APs) and proactively optimize network performance. In this context, Clustered Federated Learning (CFL) represents a fitting methodology, enabling the generation of multiple AI models that account for diverse statistical properties of the APs data distribution. However, identifying informative clusters for grouping APs models remains a significant challenge. In this paper, we address this problem by proposing a novel CFL tool integrating a two step clustering procedure. Initially, multiple clustering solutions are generated and filtered based on a minimum set of desired clustering criteria. Subsequently, if no solutions meet sufficient quality metrics, a global model is produced by aggregating all AP models. Otherwise, the final clustering solution is selected as the one that maximizes the informativeness (quantified via differential entropy) for the smallest cluster. Our results, focusing on a Wi-Fi traffic prediction problem, demonstrate that the developed CFL tool achieves the best predictive performance among all evaluated distributed strategies and the lowest communication and energy footprint among the clustered ones, exceeding the cost of single-model FL only in the regimes where it markedly improves accuracy.

Problem

• Clustered Federated Learning
• Informativeness
• Wi-Fi Traffic Prediction
• Access Point Clustering
• Distributed AI

Innovation

• Clustered Federated Learning
• Informativeness
• Differential Entropy
• Wi-Fi Traffic Prediction
• Distributed AI