Local Graph-Aware Hop-by-Hop Routing for Dynamic LEO Satellite Networks

Efficient Information Routing for Constellations with Satellite Clusters via Static Digraph

Abstract. Inter-satellite routing is key to enabling low-latency global connectivity in satellite constellations. Traditional models based on fixed topologies or discrete-time snapshots often overlook the geometric and temporal complexity of orbital motion, especially in sparse or heterogeneous systems. We introduce an event-based graph framework that captures all possible data exchanges within a constellation over a given time horizon. Each node represents a communication event—a finite interval during which one or more satellites can exchange data—while directed edges connect events that can be sequentially linked through shared satellites and overlapping time. The resulting structure is a static directed graph encoding all feasible routing paths based solely on mutual visibility. This compact formulation avoids redundancy typical of time-expanded graphs and naturally accommodates both permanent and temporary clusters, representing continuous or intermittent multi-satellite connectivity. Routing is performed on the event digraph using standard algorithms with latency- and hop-based metrics. Tests on LEO constellations demonstrate that the method efficiently identifies optimal paths and reveals key trade-offs between delay, hop count, and connectivity density, offering a scalable tool for constellation-level routing analysis.

A Per-Action Structured D3QN-Based Hierarchical Routing Algorithm for LEO Mega-Constellation Networks

Low Earth orbit (LEO) mega-constellations demand scalable routing that survives time-varying topologies, constrained onboard resources, and dynamic traffic. Deterministic shortest-path routing guarantees optimal paths but adapts poorly to real-time loads; distributed deep reinforcement learning (DRL) can introduce loops and inconsistent end-to-end decisions. This paper fuses deterministic inter-domain planning with DRL-based intra-domain forwarding in a single hierarchical framework. An evolutionary greedy algorithm partitions the constellation into compact domains. Dijkstra’s algorithm then computes backbone paths on the domain-level graph. Inside each domain, a context-enhanced Per-Action Dueling Double Deep Q-Network encodes individual neighbors through a weight-shared encoder and summarizes the valid-neighbor set via masked mean pooling. This design lets the policy compare a candidate against the current alternative set without injecting input-order bias. Local one- and two-hop topological features drive decentralized inference. A greedy–beam–Dijkstra fallback ladder guarantees reachability whenever the subgraph stays connected. On a 1584-satellite Starlink Gen1-1 topology, all 21 domain sizes and six inter-domain strategies reach 100% of test pairs; the best average hop count sits at 1.16× the global Dijkstra benchmark. Under an identical 52-dimensional state and training pipeline on 1000 held-out source–destination pairs, Context Per-Action uses 75.8% fewer parameters than a flat multilayer perceptron (MLP), lifts greedy success from 74.6% to 83.5%, and lifts greedy-plus-beam success from 88.3% to 94.5% (means over three independent training seeds). Centralized load-aware routing under dynamic traffic cuts high-load packet loss from 34–73% to 0–9.5% in the adopted flow-level model and preserves 99.2% reachability despite 30% link failures. Zero-shot transfer from ideal Walker topologies to real two-line element (TLE) snapshots and purely local load adaptation remain open; multi-snapshot training or online adaptation is the necessary next step.

A Novel RL-Driven Zone-Based Leader-Aware Energy-Efficient Routing Protocol for Dynamic MANET Environments

The paper introduces RML-ZEREM to solve existing limitations, which functions as a Reinforcement Learning (RL) based Zone-Based Leader-Aware Energy-Efficient Routing Protocol for MANETs, which serves next-generation MANET applications.

GT-PAR: Graph Transformer-Aided Traffic Prediction and Adaptive Routing for Dynamic LEO Satellite Networks

Low Earth Orbit (LEO) satellites are essential for 6G non-terrestrial networks due to their global coverage and low-latency communication. However, the highly dynamic topology and uneven traffic distribution cause routing inefficiencies. This letter proposes a Graph Transformer–aided Traffic Prediction and Adaptive Routing (GT-PAR) scheme to capture topology-dependent spatial coupling and long-range link-utilization dynamics. The ground segment periodically broadcasts lightweight link-utilization predictions, and the satellites select the next routing hops using the congestion-aware cost analyzed in Lemmas 1 and 2. The simulation results show that GT-PAR can significantly reduce the packet loss and end-to-end delay when compared with representative routing schemes.

Topology-Aware Learning for Routing In Satellite–Terrestrial Integrated Networks: A Review of Graph Neural Network and Reinforcement Learning Approaches

This review analyses topology-aware learning-based routing for STINs, concentrating on Graph Neural Networks (GNNs) and hybrid GNN–Reinforcement Learning (GNN–RL) frameworks.

Reliable Session-Oriented Multi-Path Routing for LEO Satellite Networks: A Multi-Agent Learning Approach