Aug 2026· Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication· 0 citations· 20 references
Computer Science
TL;DR
TETHER combines persistent virtual IPs, anticipatory state migration, and transport continuity mechanisms to transparently relocate application state between satellites before performance degradation occurs, showing that anticipatory migration preserves long-lived TCP sessions across satellite transitions and enables applications to trade latency tolerance against migration overhead.
Abstract
While compute and application state for networked services are typically hosted on terrestrial servers, a specific subset of workloads such as multi-party interactive applications can benefit from in-orbit compute, particularly in regions with sparse terrestrial network infrastructure. Hosting stateful services on LEO satellites, however, introduces a fundamental challenge: the satellite serving a user changes every few minutes due to orbital motion, threatening to disrupt users' active connection sessions. This paper presents TETHER, a network abstraction that preserves application-visible connectivity despite continual satellite movement. TETHER combines persistent virtual IPs, anticipatory state migration, and transport continuity mechanisms to transparently relocate application state between satellites before performance degradation occurs. The system leverages Linux Checkpoint/Restore In Userspace (CRIU) for process migration and exploits predictable orbital trajectories to proactively schedule migrations. We explore two migration policies with different trade-offs between latency and overhead. directly-above migrates application state to the satellite closest to the user, minimizing latency at the cost of more frequent migrations. In contrast, edge-of-reachability migrates state to a satellite that can stay under an acceptable latency budget the longest, reducing migration frequency while tolerating higher latency. We evaluate both policies using the xeoverse LEO network emulator. Our results show that anticipatory migration preserves long-lived TCP sessions across satellite transitions and enables applications to trade latency tolerance against migration overhead.
Overall, ICN-style receiver-driven forwarding can serve as a deployable overlay transport substrate for coordinated WAN multipath without requiring changes to IP routing.
Evaluation on a 5-node GPU cluster under synthetic and production-derived churn shows that Connex reduces P99 tail spikes by up to 85% compared to NCCL-based baselines, achieves sub-second cutover, and maintains 100% goodput at moderate loads where baselines collapse to 0–28%, while incurring less than 5% steady-state overhead.
Yanying Lin, Vincent Liu, Tao Luo et al.· Conference on Applications,...· 0 citations
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.
Yuyu Liu, Qian Wu, Zeqi Lai et al.· Asia-Pacific Workshop on Net...· 0 citations
The incorporation of optical Inter-Satellite Links (ISLs) has allowed Low Earth Orbit (LEO) constellations to evolve into a fully developed mesh network, capable of propagating traffic between any two points of the globe with minor reliance on ground infrastructure. However, the dynamics of their orbital topology, coupled with the uneven distribution of load demand across distinct geographical regions, poses a unique set of challenges for routing traffic entirely through space. In this paper, we present ATLAS (Adaptive Twin-mode Load-balanced Orbital routing Strategy), a hybrid routing approach for LEO networks that effectively distribute traffic load across the constellation, while being robust against failures. The framework primarily utilizes a centralized routing algorithm to proactively compute paths based on the combined factor of existing traffic loads and latencies of individual ISLs. If the data flow encounters failed links during propagation, ATLAS switches to a distributed algorithm that utilizes the orbital geometry of the constellation to reroute around affected regions. Simulation results show that our heuristics significantly outperform other state-of-the-art approaches from the literature in terms of throughput, load balancing, and robustness against link failures, while offering adequate latency performance.
Anindo Mahmood, Murat Yuksel· International Conference on...· 0 citations
Ground station handovers across Earth based Deep Space Network (DSN) terminals incur carrier lock reacquisition delays of 4 to 8 minutes per event, introducing periodic telemetry blackouts during cislunar flights. We address this limitation by formulating temporal handover sequences as perfect interval conflict graphs. For single spacecraft trajectories, we establish that adding a single reserve channel ($k=4$) enables static offline channel preallocation, eliminating spacecraft transponder retuning during station switches. To sustain link availability under unexpected atmospheric fades or station outages, we construct a Robust Space Communication Graph (R-SCG) model, demonstrating that four channels suffice to maintain uninterrupted coverage under single node failure conditions. For unmodeled link disruptions, we implement a distributed local recoloring scheme with $O(1)$ amortized complexity, augmented by Random Forest state classification for predictive channel reassignment. Furthermore, for colocated spacecraft clusters, we show that the joint ground space conflict graph retains chordality, bounding the required spectrum to $3+c$ channels for $c$ concurrent assets. A 10 day orbital simulation demonstrates that static channel preassignment recovers up to 2.7~hours of telemetry throughput relative to conventional reactive handover schemes.
The demand for Low-earth-orbit (LEO) satellite networking and routing is continuously growing. Container-based satellite network emulation becomes an important networking evaluation choice for LEO satellite network. While many container-based satellite network emulators optimize virtual network efficiency, they often overlook route installation latency—the duration of installing computed routes into kernel routing table. This latency represents a significant bottleneck for emulating large-scale LEO constellations, which are characterized by dynamic topologies and frequent, massive routing re-convergences. High routing installation latency not only reduces emulation efficiency but also compromises evaluation reliability and renders subsequent data transmission experiments infeasible. In this paper, we present a Lock-Free and Filtered Route Installation (LFRI) mechanism. LFRI filters out non-effective route installations, thereby shortening the installation procedure without changing the routing results. LFRI employs a lock-free installation mechanism that enables parallelized and efficient route installation. Experimental results demonstrate that, compared to the legacy Netlink installation, LFRI reduces the route installation latency by up to 99.9% in emulations of typical LEO satellite constellations, bringing it down to under ten milliseconds, within a performance level comparable to routing installation on physical machines. Meanwhile, in the case study evaluating path availability ratio and restoration time, LFRI yields more consistent and credible experimental data.
Wenhao Lu, Zhiyuan Wang, Shan Zhang et al.· Asia-Pacific Workshop on Net...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
