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
arXiv:2608. 03436v1 Announce Type: cross Abstract: Federated learning over low Earth orbit (LEO) satellite networks is limited by frequent link changes, short contact times, and a highly dynamic topology, making centralized or synchronized training inefficient and hard to scale.
By Ziwu Liu, In\^es Pinto Gouveia, Rehana Yasmin, Paulo Esteves-Verissimo, Ali Shoker
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
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
The paper presents a reinforcement learning-based approximate dynamic programming method for deploying Walker-type satellite constellations amid uncertainties such as launch failures and satellite malfunctions. It models the deployment as a Markov Decision Process that includes low‑injection orbit launches, continuous low‑thrust orbit raising, and variable satellite loads. Using offline approximate value iteration with linear function approximation and action pruning, the approach reduces computational and memory demands, and preliminary results show convergence to policies with lower expected costs and deployment times compared to a rolling‑horizon baseline.