SCOPE: Spatio-Temporal Collaborative Caching and Proactive Transfer in LEO Satellite Networks

Abstract

Integrating CDNs into LEO constellations reduces latency but faces fundamental challenges due to high satellite mobility and limited onboard storage. Existing isolated caching strategies fail to cope with topology changes, leading to the cache island effect that degrades hit ratios and overloads Ground-Satellite Links (GSLs). To address this, we propose SCOPE, a Spatio-Temporal Collaborative Caching and Proactive Transfer framework. Spatially, SCOPE organizes satellites into localized collaborative groups using a latency constrained maximal-clique search to ensure intra-group reachability. Furthermore, a uniform partition strategy is applied to resolve overlaps and enforce size constraints, ensuring unique assignment and load balancing. Temporally, to ensure service continuity, SCOPE employs an orbit-aware proactive transfer mechanism. By evaluating Value Density (popularity normalized by size), high-value content is migrated from departing to entering satellites before physical links break. Extensive simulations with Starlink traces demonstrate that SCOPE significantly improves cache hit ratios and reduces latency, while offloading GSL backhaul traffic by over 50% compared to baselines.