SKYLINK: Scalable and Resilient Link Management in LEO Satellite Network

TL;DR

SkyLink tackles the challenge of scalable, resilient routing in large LEO satellite constellations by deploying a fully distributed, tile-coded contextual learning framework. Each satellite autonomously ranks and distributes traffic across local ISLs using a contextual UCB-style metric and a water-filling allocation, without centralized control. The authors introduce a global-scale simulator to benchmark performance, showing substantial reductions in delay and packet drops, higher throughput, and strong resilience to satellite outages compared with traditional path-based baselines. The work demonstrates that local, context-aware learning can achieve near-optimal performance in dynamic, massive satellite networks while maintaining low computational and communication overhead. Overall, SkyLink offers a practical pathway to scalable, resilient global broadband via mega-constellations.

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.

Figures (10)

• Figure 1: Diagram of the considered scenario
• Figure 2: Visualization of SkyLink's tile-coding mechanism.
• Figure 3: The simulated network including OneWeb satellites and ground stations. The section at the bottom is highlighted in the top map and includes and carrying traffic.
• Figure 4: Comparison of SkyLink and the reference schemes for different metrics and different numbers of users.
• Figure 5: Evolution of cost over a week for different user scales.