Fair Resource Allocation For Hierarchical Federated Edge Learning in Space-Air-Ground Integrated Networks via Deep Reinforcement Learning with Hybrid Control

TL;DR

This paper introduces a novel hierarchical federated learning framework in space-air-ground networks, leveraging deep reinforcement learning to optimize resource allocation and ensure fairness across multiple tasks.

Contribution

It proposes a new HFL framework in SAGINs with multi-layer aggregation, and employs DSAC to optimize resource allocation and fairness, addressing complex multi-task optimization challenges.

Findings

The proposed DSAC-based algorithm outperforms baseline methods.

Effective resource allocation improves federated learning convergence.

The framework ensures fairness among multiple tasks in SAGINs.

Abstract

The space-air-ground integrated network (SAGIN) has become a crucial research direction in future wireless communications due to its ubiquitous coverage, rapid and flexible deployment, and multi-layer cooperation capabilities. However, integrating hierarchical federated learning (HFL) with edge computing and SAGINs remains a complex open issue to be resolved. This paper proposes a novel framework for applying HFL in SAGINs, utilizing aerial platforms and low Earth orbit (LEO) satellites as edge servers and cloud servers, respectively, to provide multi-layer aggregation capabilities for HFL. The proposed system also considers the presence of inter-satellite links (ISLs), enabling satellites to exchange federated learning models with each other. Furthermore, we consider multiple different computational tasks that need to be completed within a limited satellite service time. To maximize the convergence performance of all tasks while ensuring fairness, we propose the use of the distributional soft-actor-critic (DSAC) algorithm to optimize resource allocation in the SAGIN and aggregation weights in HFL. Moreover, we address the efficiency issue of hybrid action spaces in deep reinforcement learning (DRL) through a decoupling and recoupling approach, and design a new dynamic adjusting reward function to ensure fairness among multiple tasks in federated learning. Simulation results demonstrate the superiority of our proposed algorithm, consistently outperforming baseline approaches and offering a promising solution for addressing highly complex optimization problems in SAGINs.