arXiv AI
Deep Tech to Space: Space Data Centers and AI Revolution at the Edge
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 26
Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services
The paper introduces heterogeneous space data centers (SDCs) that combine large and small nodes to deliver AI‑centric computing and communication services for ground, aerial, and in‑orbit users. It outlines use cases, node sizing, placement strategies, and interconnection topologies, and focuses on dawn‑dusk low‑Earth orbit configurations to analyze solar power, visibility windows, and latency‑aware coverage. The authors evaluate latency, service reliability, and energy requirements for various SDC roles and deployment scales, highlighting trade‑offs among node size, orbit selection, and service portfolio, and offer design guidance and future research directions for AI infrastructure in space.
arXiv AI
Jul 17
The Cost and Network Limits of Space-Based AI Compute
arXiv:2607. 14172v1 Announce Type: cross Abstract: This paper evaluates whether large-scale AI data centers deployed in low-Earth orbit (LEO) could become a cost-effective alternative to terrestrial facilities.
arXiv AI
Oct 27
Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation
arXiv:2610.35282v1 Announce Type: cross Abstract: The proliferation of orbital sensing data and the real-time demands of emerging global services are pushing low Earth orbit (LEO) satellite networks...
arXiv Machine Learning
Sep 18
LEO Satellite Internet of Things: Architecture, Technology, and On-Orbit Verification
The article proposes a comprehensive two‑dimensional system architecture for 6G LEO satellite Internet of Things, integrating LEO satellites with terrestrial networks. It evaluates three key enabling technologies: massive grant‑free random access for uplink, deep learning‑based multibeam precoding for downlink, and distributed cooperative routing for inter‑satellite links. An on‑orbit verification platform is introduced to validate the real‑world feasibility and performance of these solutions, and the paper concludes with open challenges and future research directions.
arXiv Machine Learning
Jun 18
Towards a future space-based, highly scalable AI infrastructure system design
arXiv:2511. 19468v2 Announce Type: replace-cross Abstract: If AI is a foundational general-purpose technology, we should anticipate that demand for AI compute -- and energy -- will continue to grow.
arXiv Machine Learning
5d ago
RAMA: Retrieval-Augmented Multi-Agent Routing with Episodic Memory for LEO Satellite Networks
RAMA is a retrieval‑augmented multi‑agent deep reinforcement learning framework for routing in Low‑Earth Orbit satellite networks. It combines each satellite’s local observation, recent routing history, neighboring state information, and retrieved entries from a per‑satellite episodic memory, integrating them via a Transformer‑based decision network trained with Approximate Information State objectives. In a 140‑satellite Kepler constellation, RAMA cuts mean end‑to‑end latency by 13.4% and 99th‑percentile latency by 66.7% compared to a state‑of‑the‑art DDQN, and on a 1,584‑satellite Starlink shell 1 it achieves a 93.2% mean latency reduction, with further gains from online updates.