Traffic-Aware Domain Partitioning and Load-Balanced Inter-Domain Routing for LEO Satellite Networks

TL;DR

This paper introduces DTAR, a novel deep reinforcement learning-based inter-domain routing method for LEO satellite networks that improves load balancing and reliability amid high mobility and link failures.

Contribution

It combines offline domain partitioning with online dynamic routing decisions using graph attention networks and reinforcement learning.

Findings

DTAR reduces link load imbalance and end-to-end delay.

DTAR improves routing success rate and reduces packet loss.

DTAR performs well under normal, surge, and fault scenarios.

Abstract

Low Earth Orbit (LEO) satellite networks provide global coverage and low latency, yet high node mobility, uneven traffic distribution, and stochastic link failures pose severe challenges for inter-domain routing. Existing approaches either neglect graph-structured topology or lack dynamic awareness of real-time link states, struggling to balance load distribution and routing reliability. This paper proposes DTAR, a traffic-aware deep reinforcement learning approach for inter-domain routing in LEO satellite networks. A multi-objective NSGA-II algorithm first generates an offline domain partition maximizing intra-domain traffic ratio and minimizing load imbalance. A Graph Attention Network dynamically encodes inter-domain link traffic intensity, load distribution, and fault status, upon which an action-masked PPO agent learns routing decisions online. Simulations on a 288-satellite Walker constellation against multiple baselines demonstrate that DTAR significantly reduces link load imbalance and end-to-end delay, while improving routing success rate and reducing packet loss rate across normal, traffic surge, and fault scenarios.