Energy-Aware Edge Association for Cluster-based Personalized Federated Learning

TL;DR

This paper proposes an energy-efficient, personalized federated learning framework that uses user clustering and deep reinforcement learning for optimized edge association, improving accuracy and reducing energy consumption.

Contribution

It introduces a novel edge association method combining user clustering and deep reinforcement learning to optimize resource use in personalized federated learning.

Findings

Outperforms existing strategies in accuracy and energy efficiency.

Effectively balances model accuracy with energy consumption.

Utilizes multiple edge base stations for cost-effective learning.

Abstract

Federated Learning (FL) over wireless network enables data-conscious services by leveraging the ubiquitous intelligence at network edge for privacy-preserving model training. As the proliferation of context-aware services, the diversified personal preferences causes disagreeing conditional distributions among user data, which leads to poor inference performance. In this sense, clustered federated learning is proposed to group user devices with similar preference and provide each cluster with a personalized model. This calls for innovative design in edge association that involves user clustering and also resource management optimization. We formulate an accuracy-cost trade-off optimization problem by jointly considering model accuracy, communication resource allocation and energy consumption. To comply with parameter encryption techniques in FL, we propose an iterative solution procedure which employs deep reinforcement learning based approach at cloud server for edge association. The reward function consists of minimized energy consumption at each base station and the averaged model accuracy of all users. Under our proposed solution, multiple edge base station are fully exploited to realize cost efficient personalized federated learning without any prior knowledge on model parameters. Simulation results show that our proposed strategy outperforms existing strategies in achieving accurate learning at low energy cost.