DRL-Enabled Hierarchical Federated Learning Optimization for Data Heterogeneity Management in Multi-Access Edge Computing

This paper designs a novel Hierarchical Federated Learning (HFL) management scheme, enabled by deep reinforcement learning (DRL), for multi-access edge computing (MEC) environments to accelerate convergence. To do this, the proposed scheme controls the number of local updates performed by mobile dev...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE access 2024, Vol.12, p.147209-147219
Hauptverfasser:	Cho, Suhyun, Lim, Sunhwan, Lee, Joohyung
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Adaptation models Computational modeling Convergence Deep reinforcement learning Degradation Edge computing Federated learning Hierarchical federated learning multi-access edge computing Optimization Performance evaluation Servers Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!