STG-SR: Spatio-Temporal Graph based Load Balancing Routing for Satellite Networks

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.

Load-Balanced and Congestion-Aware Routing for LEO Laser Satellite Networks Based on Deep Reinforcement Learning

To address load imbalance in low earth orbit (LEO) laser satellite networks (LSN), this paper proposes a deep reinforcement learning (DRL) based routing algorithm, which combines proximal policy optimization (PPO) and K-shortest path (KSP) strategies to transform the large-scale routing problem into a decision-making process over a small set of paths. Simulation results demonstrate that, compared with traditional Dijkstra and random routing algorithms, the proposed algorithm fully exploits network resources, effectively prevents network bottlenecks, and significantly enhances the network’s service-carrying capacity.

HAT-Route: A Physics-Aware Hierarchical Transformer Framework for Scalable Cloud-Edge Collaborative Routing

Routing optimization in cloud-edge collaborative networks faces a fundamental conflict between global strategic planning and local real-time responsiveness, further complicated by structural heterogeneity and stochastic traffic patterns. Traditional protocols lack adaptivity, while existing Deep Reinforcement Learning (DRL) approaches based on Graph Neural Networks (GNN) struggle with limited receptive fields and over-smoothing issues in large-scale topologies. In this paper, we propose HAT-Route, a Transformer-driven hierarchical routing framework supported by the Network Digital Twin (NDT). Our contributions are threefold: 1) We establish a cloud-edge collaborative architecture operating under the Centralized Training and Decentralized Execution paradigm. This architecture balances the trade-off between global optimization and real-time inference. 2) We introduce FlowFormer, a Spatiotemporal Transformer for the NDT. FlowFormer integrates a novel Edge-Conditioned Spatial Attention (EC-SAT) mechanism to capture physical link constraints and distinguish between congestion and Head-of-Line (HOL) blocking. 3) We design HAT-Route, a hierarchical DRL agent that utilizes Graph Transformers for global policy learning in the cloud, coupled with knowledge distillation to deploy lightweight policies at the network edge. Extensive experiments demonstrate that our framework outperforms traditional protocols and GNN-based baselines in terms of QoS optimization, training stability, scalability, and generalization capability on large-scale network topologies.

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

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

Low Earth orbit (LEO) satellite networks exhibit rapidly changing topology and time-varying traffic hotspots, which makes hop-by-hop routing highly sensitive to local congestion and state staleness. Existing routing methods either rely on global path computation or use plain local observations, while graph-enhanced approaches often focus on generic neighborhood representation rather than direct comparison among candidate next hops. To address this issue, this paper proposes a Local Graph-Aware Routing method (LGAR) for dynamic LEO satellite networks. LGAR organizes the current node, reachable candidate neighbors, and candidate links into a local graph, and then constructs structured action representations through node encoding, relation message extraction, and attention-based context aggregation. The resulting representations are integrated into an off-policy actor-critic framework to support adaptive hop-by-hop routing decisions. Experiments under the hub-inversion setting show that LGAR achieves an average total delay of 47.64 ms and an average queueing delay of 5.81 ms while maintaining a delivery rate of 99.93%. Compared with MATMR, LGAR-NoGraph, and GRLR, LGAR reduces the average total delay by 12.38%, 12.85%, and 30.75%, respectively. Additional scenario, ablation, and scalability results further show that LGAR generalizes beyond the main setting and that its gain mainly comes from local graph modeling and relation-aware action encoding.

Link-Aware Routing in Multi-Tier LEO Mega-Constellations

In multi-tier low-Earth orbit (LEO) mega-constellations, the mobility of satellites across different orbital altitudes leads to dynamic changes in network topology and inter-satellite link (ISL) states, including ISL duration and capacity. These changes often result in unstable connectivity and disrupted end-to-end data transmission. To address this issue, we formulate a routing optimization problem to determine the optimal ISL path between two end users by maximizing the average ISL utility, considering both ISL duration and capacity. To solve this problem, we propose a routing method that first prunes unstable ISLs using a graph neural network (GNN) and then selects optimal end-to-end paths on the pruned graph using a heuristic routing algorithm. Simulation results demonstrate that the proposed algorithm achieves higher throughput and a lower packet loss rate compared to benchmark methods.