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.
By Peng Hu, Mustafa Alhassan, Amjad Iqbal
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.
By Kees van Berkel
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.
By Xin Ming Li, Peng Hu
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...
By Zheng Lin, Zhanwei Wang, Yuxin Zhang, Yafei Wang, Ons Aouedi, Zihan Fang, Jinfeng Xu, Jing Yang, Vu Nguyen Ha, Yuanwei Liu, Mohamed-Slim Alouini, Symeon Chatzinotas
The paper introduces a heterogeneous federated learning approach using the FractalNet architecture tailored for satellite mega‑constellations. It formalizes contact‑window‑constrained, depth‑heterogeneous optimization and proposes a distributed path scheduler that assigns model depth based on satellite SWAP‑C constraints, predicted contacts, and training statistics. The framework includes periodic update pooling and a three‑tier agentic control plane, and is validated through a wildfire detection case study across LEO, MEO, and GEO/HEO shells, demonstrating improvements in convergence, communication efficiency, energy adaptation, and robustness.
By Sai Puppala, Koushik Sinha
Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited from terrestrial federated learning...
The paper proposes an online learning framework for configuring dynamic constellation topologies in satellite networks, addressing the challenges posed by continuous orbital movement and node maneuvering. It does not rely on predefined orbital plane structures, making it robust to changes caused by satellite maneuvers. Experiments show that the method performs comparably to state‑of‑the‑art offline techniques and can be adapted to constrained online learning, balancing per‑iteration computational cost against convergence speed.
By Jo\~ao Norberto, Ricardo Ferreira, Cl\'audia Soares
arXiv:2608. 14789v1 Announce Type: new Abstract: Large low-Earth-orbit (LEO) Earth-observation (EO) constellations offer frequent access to geographically dispersed ground targets, but emergency requests may arrive after committed routine-plan execution has begun.
By Qian Yin, Xinwei Wang, Guohua Wu
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.
By Blaise Ag\"uera y Arcas, Travis Beals, Maria Biggs, Jessica V. Bloom, Thomas Fischbacher, Konstantin Gromov, Urs K\"oster, Rishiraj Pravahan, James Manyika
The paper introduces a reinforcement‑learning framework for managing bundles and flow control in deep‑space networks, where relay nodes must schedule and drop data under intermittent connectivity and limited storage. It defines a goal‑oriented loss based on excess age to prioritize mission‑relevant information and formulates relay control as a constrained semi‑Markov decision process solved with masked Lagrangian PPO. Simulations show that the approach improves age‑based utility and inter‑flow fairness compared to traditional schedulers.
By Sajjad Baghaeea, Aimin Lib, Shanmugarajan Balasubramanian, Elif Uysal
arXiv:2609.01062v1 Announce Type: new
Abstract: Satellites are emerging as promising platforms to extend generative \emph{artificial intelligence} (AI) services to remote areas lacking terrestrial in...
By Jierui Zhang, Jianhao Huang, Zhanwei Wang, Kaibin Huang
The paper introduces TELGEN, a traffic engineering algorithm that uses graph neural networks to predict an optimal TE algorithm rather than a direct solution. TELGEN generalizes across diverse network topologies and traffic patterns, achieving less than a 3% optimality gap on networks up to 5,000 nodes and 3.6 million links, while reducing solving time by up to 84% and training time by up to 79.6% compared to existing methods.
By Fangtong Zhou, Xiaorui Liu, Ruozhou Yu, Guoliang Xue