Joint Cache Placement and Routing in Satellite-Terrestrial Edge Computing Network: A GNN-Enabled DRL Approach

2025-08-22

AI Summary

To address the low cache service efficiency in satellite–terrestrial edge computing networks (STECNs) caused by dynamic low-Earth-orbit (LEO) satellite topologies and heterogeneous user content demands, this paper proposes a graph neural network (GNN)-enhanced deep reinforcement learning framework for joint optimization. Specifically, we integrate a GNN into a soft actor–critic (SAC) agent to model the spatiotemporal topology of the satellite network as a dynamic graph, enabling end-to-end, routing-aware joint decision-making for caching and routing. Compared with conventional heuristic and decoupled optimization approaches, the proposed framework significantly improves service delivery success rate and reduces communication traffic overhead. Moreover, it demonstrates superior robustness and generalization capability under highly dynamic network conditions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Satisfiability

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In this letter, we investigate the problem of joint content caching and routing in satellite-terrestrial edge computing networks (STECNs) to improve caching service for geographically distributed users. To handle the challenges arising from dynamic low Earth orbit (LEO) satellite topologies and heterogeneous content demands, we propose a learning-based framework that integrates graph neural networks (GNNs) with deep reinforcement learning (DRL). The satellite network is represented as a dynamic graph, where GNNs are embedded within the DRL agent to capture spatial and topological dependencies and support routing-aware decision-making. The caching strategy is optimized by formulating the problem as a Markov decision process (MDP) and applying soft actor-critic (SAC) algorithm. Simulation results demonstrate that our approach significantly improves the delivery success rate and reduces communication traffic cost.

Problem

• Optimizing joint caching and routing in satellite-terrestrial networks
• Handling dynamic satellite topologies and heterogeneous content demands
• Improving delivery success rate while reducing traffic cost

Innovation

• GNN-embedded DRL for dynamic satellite networks
• MDP formulation with SAC algorithm optimization
• Joint caching and routing decision-making framework