Min Sheng

Zhanwei Wang, Huiling Yang, Min Sheng et al.

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.

Qian Chen, Xianhao Chen, Min Sheng et al.

As satellite networks evolve to support increasingly diverse services and artificial general intelligence (AGI), large language models (LLMs) are emerging as a critical foundation for future space systems. However, deploying LLMs on satellites is hindered by stringent constraints on onboard memory, computation, and energy. In this context, the mixture-of-experts (MoE) architecture emerges as a promising solution, leveraging sparse expert activation to enable scalable model inference. By harnessing the architectural advantages of MoE, this article provides a comprehensive overview of SpaceMoE, a new paradigm for distributed MoE inference in satellite networks. We first review recent industrial progress and emerging standardization trends that motivate the evolution toward space AGI systems. Then, we introduce the fundamentals and architectural evolution of SpaceMoE. Subsequently, we discuss three fundamental design problems in SpaceMoE, namely expert placement, expert selection, and hidden-state transmission and routing, highlighting how satellite-specific factors such as dynamic topology, battery degradation, and thermal limits fundamentally reshape their solutions. Finally, we outline promising research directions for realizing scalable, efficient, and sustainable on-orbit MoE inference in future satellite networks.

Wei Li, Min Sheng

Dynamic link failures disrupt the connectivity and geometric symmetry of the constellation structure, thereby increasing protocol overhead and degrading the effective capacity for traffic transport. The fundamental relationship between constellation size and effective capacity under protocol overhead constraints remains unclear. To this end, we define capacity scalability as the ratio of constellation capacity under non-failure conditions to protocol overhead. Specifically, if ISL states follow a two-state discrete Markov chain and the maintenance period is $k \geq 1$, the upper bound of capacity scalability under the uniform traffic pattern is $O(1/n)$, where $n$ is the number of satellites. With perfect information about the constellation topology, the upper bound can be achieved via shortest-path routing. For any given protocol, there exists an optimal constellation deployment scale in terms of capacity scalability. When the constellation size is below this optimum scale, capacity scalability increases with constellation size, thereby improving effective capacity. Increasing the maintenance period $k$ can improve capacity scalability, but it does not change the fact that the capacity scalability converges to zero when the constellation size exceeds the optimal scale.

Wei Li, Min Sheng, Junyu Liu et al.

One key challenge in designing resilient large-scale wireless ad hoc networks is to understand how random node failures affect fundamental network performance. In this work, we show that both network capacity and delay scale as \scalebox{0.65}{$\textstyle Θ\left(\sqrt{\frac{n(1-q)}{\log n}}\right)$}, where $n$ is the total number of nodes and $q$ is the node failure probability. The network capacity degenerates to the classical result given by P. Gupta and P. R. Kumar when $q=0$. Based on these results, we find that even with the same number of non-faulty nodes, a network with $n$ nodes and node failure probability $q$ has lower network capacity than a failure-free network with $n(1-q)$ nodes. To compensate for the network capacity loss caused by random node failures, at least $ε(n,q) nq$ redundant nodes are required, where $ε(n,q)>1$. We further prove that the optimal trade-off between network capacity and delay remains $O(1)$ regardless of node failures, implying that high network capacity and low delay cannot be achieved simultaneously. These results demonstrate robustness against stochastic variations in wireless channels.

Chenxi Zhao, Min Sheng, Junyu Liu et al.

The limited energy and computing resources of unmanned aerial vehicles (UAVs) hinder the application of aerial artificial intelligence. The utilization of split inference in UAVs garners significant attention due to its effectiveness in mitigating computing and energy requirements. However, achieving energy-efficient split inference in UAVs remains complex considering of various crucial parameters such as energy level and delay constraints, especially involving multiple tasks. In this paper, we present a two-timescale approach for energy minimization in split inference, where discrete and continuous variables are segregated into two timescales to reduce the size of action space and computational complexity. This segregation enables the utilization of tiny reinforcement learning (TRL) for selecting discrete transmission modes for sequential tasks. Moreover, optimization programming (OP) is embedded between TRL's output and reward function to optimize the continuous transmit power. Specifically, we replace the optimization of transmit power with that of transmission time to decrease the computational complexity of OP since we reveal that energy consumption monotonically decreases with increasing transmission time. The replacement significantly reduces the feasible region and enables a fast solution according to the closed-form expression for optimal transmit power. Simulation results show that the proposed algorithm can achieve a higher probability of successful task completion with lower energy consumption.

Ziwei Cai, Min Sheng, Junju Liu et al.

The utilization of existing terrestrial infrastructures to provide coverage for aerial users is a potentially low-cost solution. However, the already deployed terrestrial base stations (TBSs) result in weak ground-to-air (G2A) coverage due to the down-tilted antennas. Furthermore, achieving optimal coverage across the entire airspace through antenna adjustment is challenging due to the complex signal coverage requirements in three-dimensional space, especially in the vertical direction. In this paper, we propose a cooperative tri-point (CoTP) model-based method that utilizes cooperative beams to enhance the G2A coverage extension. To utilize existing TBSs for establishing effective cooperation, we prove that the cooperation among three TBSs can ensure G2A coverage with a minimum coverage overlap, and design the CoTP model to analyze the G2A coverage extension. Using the model, a cooperative coverage structure based on Delaunay triangulation is designed to divide triangular prism-shaped subspaces and corresponding TBS cooperation sets. To enable TBSs in the cooperation set to cover different height subspaces while maintaining ground coverage, we design a cooperative beam generation algorithm to maximize the coverage in the triangular prism-shaped airspace. The simulation results and field trials demonstrate that the proposed method can efficiently enhance the G2A coverage extension while guaranteeing ground coverage.

Weijia Han, Huiyan Sang, Min Sheng et al.

In cognitive radio (CR) technology, the trend of sensing is no longer to only detect the presence of active primary users. A large number of applications demand for more comprehensive knowledge on primary user behaviors in spatial, temporal, and frequency domains. To satisfy such requirements, we study the statistical relationship among primary users by introducing a Bayesian network (BN) based framework. How to learn such a BN structure is a long standing issue, not fully understood even in the statistical learning community. Besides, another key problem in this learning scenario is that the CR has to identify how many variables are in the BN, which is usually considered as prior knowledge in statistical learning applications. To solve such two issues simultaneously, this paper proposes a BN structure learning scheme consisting of an efficient structure learning algorithm and a blind variable identification scheme. The proposed approach incurs significantly lower computational complexity compared with previous ones, and is capable of determining the structure without assuming much prior knowledge about variables. With this result, cognitive users could efficiently understand the statistical pattern of primary networks, such that more efficient cognitive protocols could be designed across different network layers.