In this paper, we propose a spatial-temporal learning-based distributed routing framework for dynamic Low Earth Orbit (LEO) satellite networks, where graph attention networks (GAT) and long short-term memory (LSTM) are integrated within a deep Q-network (DQN)-based architecture to enable distributed and adaptive routing decisions based on local observations. The routing problem is formulated as a partially observable Markov decision process (POMDP) to address partial observability under dynamic topology and time-varying traffic. Simulation results show that the proposed method significantly outperforms conventional and learning-based routing schemes in terms of throughput, packet loss, queue length, and end-to-end delay, while achieving proactive congestion avoidance with up to 23.26% queue reduction. In addition, the proposed approach maintains low computational overhead with negligible carbon emissions, demonstrating its efficiency from a Green AI perspective.

翻译：本文提出了一种面向动态低轨卫星网络的时空学习分布式路由框架，该框架将图注意力网络（GAT）和长短期记忆网络（LSTM）集成于基于深度Q网络（DQN）的架构中，以实现基于局部观测的分布式自适应路由决策。将路由问题建模为部分可观测马尔可夫决策过程（POMDP），以应对动态拓扑和时变流量下的部分可观测性。仿真结果表明，所提方法在吞吐量、丢包率、队列长度和端到端延迟方面显著优于传统及基于学习的路由方案，同时实现了主动拥塞避免，队列长度减少高达23.26%。此外，所提方法保持较低的计算开销且仅产生可忽略的碳排放，从绿色人工智能角度验证了其高效性。