Space Network of Experts: Architecture and Expert Placement

• URL: http://arxiv.org/abs/2605.00515v1
• Date: Fri, 01 May 2026 08:40:31 GMT
• Title: Space Network of Experts: Architecture and Expert Placement
• Abstract summary: Space data centers are envisioned as a promising platform for executing energy-intensive large language models (LLMs)<n>One key challenge, however, is the efficient distributed deployment of a large-scale LLM in a satellite network.<n>We present the Space Network of Experts (Space-XNet) framework targeting the distributed execution of a popular mixture-of-experts (MoE) model in space.
• Score: 53.89437186709926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Leveraging continuous solar energy harvesting at high efficiency, space data centers are envisioned as a promising platform for executing energy-intensive large language models (LLMs). Recognizing this advantage, space and AI conglomerates (e.g., SpaceX, Google) are actively investing in this vision. One key challenge, however, is the efficient distributed deployment of a large-scale LLM in a satellite network due to the limited onboard computing and communication resources. This gives rise to a placement problem that involves partitioning and mapping model components to satellites such that the fundamentally different model architecture and network topology can be reconciled to ensure low-latency token generation. To address this problem, we present the Space Network of Experts (Space-XNet) framework targeting the distributed execution of a popular mixture-of-experts (MoE) model in space. The proposed placement strategies are two-level: (1) layer placement, which assigns MoE layers to satellite subnets; and (2) intra-layer expert placement, which assigns individual experts to satellites associated with the same layer/subnet. For layer placement, we exploit the ring-like communication pattern of autoregressive inference to partition the satellite constellation along the orbiting direction into subnets arranged on a ring, each hosting one MoE layer. Based on this architecture, we formulate and solve an optimization problem for intra-layer expert placement to map experts with heterogeneous activation probabilities onto satellites. The derived strategy reveals an intuitive principle: a frequently activated expert should be mapped to a satellite on a routing path with low expected latency. Experiments over a thousand-satellite constellation show that Space-XNet achieves at least a threefold latency reduction compared with conventional random and ablation-based placement strategies.

Related papers

• ASTREA: Introducing Agentic Intelligence for Orbital Thermal Autonomy [51.56484100374058]
  ASTREA is the first agentic system executed on flight-heritage hardware for autonomous spacecraft operations.<n>We integrate a resource-constrained Large Language Model (LLM) agent with a reinforcement learning controller in an asynchronous architecture tailored for space-qualified platforms.
  arXiv  Detail & Related papers  (2025-09-16T08:52:13Z)
• Joint AoI and Handover Optimization in Space-Air-Ground Integrated Network [48.485907216785904]
  Low Earth orbit (LEO) satellite constellations offer promising solutions with global coverage and reduced latency.<n>Yet struggle with intermittent coverage and intermittent communication windows due to orbital dynamics.<n>Our three-layer design employs hybrid free-space optical (FSO) links for high-capacity satellite-to-ground communication and reliable radio frequency (RF) links for HAP-to-ground transmission.
  arXiv  Detail & Related papers  (2025-09-16T06:16:56Z)
• AI-Driven Collaborative Satellite Object Detection for Space Sustainability [29.817805350971366]
  The growing density of satellites in low-Earth orbit (LEO) presents serious challenges to space sustainability.<n>Traditional ground-based tracking systems are constrained by latency and coverage limitations.<n>We propose a novel satellite clustering framework that enables the collaborative execution of deep learning (DL)-based space object detection tasks across multiple satellites.
  arXiv  Detail & Related papers  (2025-08-01T16:31:55Z)
• A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks [2.5774044809669663]
  Low Earth Orbit (LEO) satellites are emerging as key components of 6G networks.<n>We propose a novel semi-supervised federated learning framework tailored for LEO satellite networks with hierarchical aggregation.<n>Our proposal can significantly reduce processing time (up to 3x) and energy consumption (up to 4x) compared to other comparative methods.
  arXiv  Detail & Related papers  (2025-07-30T02:47:14Z)
• Demand-Aware Beam Hopping and Power Allocation for Load Balancing in Digital Twin empowered LEO Satellite Networks [6.8053434130447625]
  Low-Earth orbit (LEO) satellites utilizing beam hopping (BH) technology offer extensive coverage, low latency, high bandwidth, and significant flexibility. Traditional beam hopping (BH) methods fail to address issues such as satellite interference, overlapping coverage, and mobility. This paper explores a Digital Twin (DT)-based collaborative resource allocation network for multiple LEO satellites with overlapping coverage areas.
  arXiv  Detail & Related papers  (2024-10-29T01:32:11Z)
• SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework [19.59862482196897]
  We propose SatFed, a resource-efficient satellite-assisted heterogeneous FL framework. SatFed implements freshness-based model prioritization queues to optimize the use of highly constrained satellite-ground bandwidth. Experiments with real-world LEO satellite networks demonstrate that SatFed achieves superior performance and robustness compared to state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2024-09-20T13:44:00Z)
• Learning Emergent Random Access Protocol for LEO Satellite Networks [51.575090080749554]
  We propose a novel grant-free random access solution for LEO SAT networks, dubbed emergent random access channel protocol (eRACH) eRACH is a model-free approach that emerges through interaction with the non-stationary network environment. Compared to RACH, we show from various simulations that our proposed eRACH yields 54.6% higher average network throughput.
  arXiv  Detail & Related papers  (2021-12-03T07:44:45Z)
• Deep Learning Aided Routing for Space-Air-Ground Integrated Networks Relying on Real Satellite, Flight, and Shipping Data [79.96177511319713]
  Current maritime communications mainly rely on satellites having meager transmission resources, hence suffering from poorer performance than modern terrestrial wireless networks. With the growth of transcontinental air traffic, the promising concept of aeronautical ad hoc networking relying on commercial passenger airplanes is potentially capable of enhancing satellite-based maritime communications via air-to-ground and multi-hop air-to-air links. We propose space-air-ground integrated networks (SAGINs) for supporting ubiquitous maritime communications, where the low-earth-orbit satellite constellations, passenger airplanes, terrestrial base stations, ships, respectively, serve as the space-, air-,
  arXiv  Detail & Related papers  (2021-10-28T14:12:10Z)
• Integrating LEO Satellite and UAV Relaying via Reinforcement Learning for Non-Terrestrial Networks [51.05735925326235]
  A mega-constellation of low-earth orbit (LEO) satellites has the potential to enable long-range communication with low latency. We study the problem of forwarding packets between two faraway ground terminals, through an LEO satellite selected from an orbiting constellation. To maximize the end-to-end data rate, the satellite association and HAP location should be optimized. We tackle this problem using deep reinforcement learning (DRL) with a novel action dimension reduction technique.
  arXiv  Detail & Related papers  (2020-05-26T05:39:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.