Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks

TL;DR

This work addresses traffic offloading in the highly dynamic and heterogeneous SAGIN by formulating it as a DEC-POMDP and proposing Differentiated Federated Reinforcement Learning (DFRL). The core method, Differentiated Federated Soft Actor-Critic (DFSAC), separates local policy learning from a global trend model that aggregates regional knowledge, enabling privacy-preserving, region-specific optimization guided by global context. Empirical results show that DFSAC outperforms traditional FRL, distributed DDQN, and centralized RL baselines in terms of throughput, packet loss, and delay, and remains robust under higher mobility and larger network loads. The approach offers scalable, privacy-aware optimization for traffic offloading in SAGIN, with potential impact on real-world multi-layer networks and beyond.

Abstract

The Space-Air-Ground Integrated Network (SAGIN) plays a pivotal role as a comprehensive foundational network communication infrastructure, presenting opportunities for highly efficient global data transmission. Nonetheless, given SAGIN's unique characteristics as a dynamically heterogeneous network, conventional network optimization methodologies encounter challenges in satisfying the stringent requirements for network latency and stability inherent to data transmission within this network environment. Therefore, this paper proposes the use of differentiated federated reinforcement learning (DFRL) to solve the traffic offloading problem in SAGIN, i.e., using multiple agents to generate differentiated traffic offloading policies. Considering the differentiated characteristics of each region of SAGIN, DFRL models the traffic offloading policy optimization process as the process of solving the Decentralized Partially Observable Markov Decision Process (DEC-POMDP) problem. The paper proposes a novel Differentiated Federated Soft Actor-Critic (DFSAC) algorithm to solve the problem. The DFSAC algorithm takes the network packet delay as the joint reward value and introduces the global trend model as the joint target action-value function of each agent to guide the update of each agent's policy. The simulation results demonstrate that the traffic offloading policy based on the DFSAC algorithm achieves better performance in terms of network throughput, packet loss rate, and packet delay compared to the traditional federated reinforcement learning approach and other baseline approaches.

Figures (15)

• Figure 1: The global learning model does not work well because of environmental differentiations.
• Figure 2: The four-layer SAGIN architecture.
• Figure 3: The agents communicate through the trend model.
• Figure 4: The learning process of DFSAC algorithm.
• Figure 5: The frame structure of DFSAC-based traffic offloading method in SAGIN.