SKYLINK: Scalable and Resilient Link Management in LEO Satellite Network

2025-09-10

AI Summary

To address routing inefficiency and fragility in low-Earth-orbit (LEO) satellite networks—caused by high satellite mobility, dynamic traffic patterns, and frequent link failures—this paper proposes SKYLINK, a fully distributed, learning-based link management framework. Methodologically, it introduces a time-varying graph model to capture topology dynamics, designs a lightweight distributed reinforcement learning algorithm for decentralized link decision-making, incorporates real-time traffic-aware scheduling, and develops a high-fidelity LEO network simulator scalable to millions of nodes. Theoretically, the algorithm’s computational complexity is proven independent of constellation size. Experimental evaluation under a 25.4-million-user scenario demonstrates that SKYLINK reduces the weighted delay-packet-loss metric by 29% over bent-pipe architectures and by 92% over Dijkstra-based routing; achieves up to 99% packet loss reduction; and improves throughput by 46%.

Technology Category

• Planning, Routing, and Scheduling: Routing
• Search and Optimization: Distributed Search
• Machine Learning: Distributed Machine Learning & Federated Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The rapid growth of space-based services has established LEO satellite networks as a promising option for global broadband connectivity. Next-generation LEO networks leverage inter-satellite links (ISLs) to provide faster and more reliable communications compared to traditional bent-pipe architectures, even in remote regions. However, the high mobility of satellites, dynamic traffic patterns, and potential link failures pose significant challenges for efficient and resilient routing. To address these challenges, we model the LEO satellite network as a time-varying graph comprising a constellation of satellites and ground stations. Our objective is to minimize a weighted sum of average delay and packet drop rate. Each satellite independently decides how to distribute its incoming traffic to neighboring nodes in real time. Given the infeasibility of finding optimal solutions at scale, due to the exponential growth of routing options and uncertainties in link capacities, we propose SKYLINK, a novel fully distributed learning strategy for link management in LEO satellite networks. SKYLINK enables each satellite to adapt to the time-varying network conditions, ensuring real-time responsiveness, scalability to millions of users, and resilience to network failures, while maintaining low communication overhead and computational complexity. To support the evaluation of SKYLINK at global scale, we develop a new simulator for large-scale LEO satellite networks. For 25.4 million users, SKYLINK reduces the weighted sum of average delay and drop rate by 29% compared to the bent-pipe approach, and by 92% compared to Dijkstra. It lowers drop rates by 95% relative to k-shortest paths, 99% relative to Dijkstra, and 74% compared to the bent-pipe baseline, while achieving up to 46% higher throughput. At the same time, SKYLINK maintains constant computational complexity with respect to constellation size.

Problem

• Managing inter-satellite links in highly mobile LEO networks
• Addressing dynamic traffic patterns and potential link failures
• Achieving scalable routing with minimal delay and packet loss

Innovation

• Distributed learning strategy for link management
• Adapts to time-varying network conditions in real-time
• Ensures scalability, resilience with low overhead