To bridge the digital divide, space-ground integrated networks (SGINs) are expected to deliver artificial intelligence (AI) services to every corner of the world. One key mission of SGINs is to support federated learning (FL) at a global scale. However, existing space-ground integrated FL frameworks involve ground stations or costly inter-satellite links, entailing excessive training latency and communication costs. To overcome these limitations, we propose an infrastructure-freefederated learning framework based on amodeldispersal (FedMeld) strategy, which exploits periodic movement patterns and store-carry-forward capabilities of satellites to enable parameter mixing across large-scale geographical regions. We theoretically show that FedMeld leads to global model convergence and quantify the effects of round interval and mixing ratio between adjacent areas on its learning performance. Based on the theoretical results, we formulate a joint optimization problem to design the staleness control and mixing ratio (SC-MR) for minimizing the training loss. By decomposing the problem into sequential SC and MR subproblems without compromising the optimality, we derive the round interval solution in a closed form and the mixing ratio in a semi-closed form to achieve theoptimallatency-accuracy tradeoff. Experiments using various datasets demonstrate that FedMeld achieves superior model accuracy while significantly reducing communication costs as compared with traditional FL schemes for SGINs.

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant storage/memory burden for an edge device. To address this challenge, we consider a scenario where experts are dispersed across an edge network for distributed inference. Based on the popular Top-$K$expert selection strategy, we formulate a latency minimization problem by optimizing expert caching on edge servers under storage constraints. When$K=1$, the problem reduces to a monotone submodular maximization problem with knapsack constraints, for which we design a greedy-based algorithm with a$(1 - 1/e)$-approximation guarantee. For the general case where$K\geq 1$, expert co-activation within the same MoE layer introduces non-submodularity, which renders greedy methods ineffective. To tackle this issue, we propose a successive greedy decomposition method to decompose the original problem into a series of subproblems, with each being solved by a dynamic programming approach. Furthermore, we design an accelerated algorithm based on the max-convolution technique to obtain the approximate solution with a provable guarantee in polynomial time. Simulation results on various MoE models demonstrate that our method significantly reduces inference latency compared to existing baselines.

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm of edge model caching. In this paper, we develop a novel model placement framework, called parameter-sharing model caching (TrimCaching). TrimCaching exploits the key observation that a wide range of AI models, such as convolutional neural networks or large language models, can share a significant proportion of parameter blocks containing reusable knowledge, thereby improving storage efficiency. To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency. We show that the formulated problem is a submodular maximization problem with submodular constraints, for which no polynomial-time approximation algorithm exists. To tackle this challenge, we study an important special case, where a small fixed number of parameter blocks are shared across models, which often holds in practice. In such a case, a polynomial-time algorithm with a $\left(1-ε\right)/2$-approximation guarantee is developed. Subsequently, we address the original problem for the general case by developing a greedy algorithm. Simulation results demonstrate that the proposed TrimCaching framework significantly improves the cache hit ratio compared with state-of-the-art content caching without exploiting shared parameters in AI models.

The rapid development of the aviation Internet of Things (IoT) has positioned in-flight connectivity (IFC) as one of its critical applications. Space-air–ground integrated networks (SAGINs) are essential for ensuring the performance of IFC by enabling seamless and reliable connectivity. However, most existing research treats satellites merely as transparent forwarding nodes and overlooks their potential caching capabilities to enhance IFC data rates. In this article, we explore an IFC-oriented SAGIN where satellites and ground stations (GSs) work together to transmit content to airborne passengers, thereby facilitating airborne communication. By categorizing files into cached (instantly accessible via satellites) and noncached files (available only through GSs), this article pioneers the integration of multiple intersatellite links (ISLs) into the IFC framework, thus innovating the content delivery process for both types of files. To minimize the average delay of content delivery, we formulate the corresponding optimization problems: 1) for cached files, we propose an exact penalty-based method to determine the satellite association scheme and 2) for noncached files, we present an efficient algorithm based on alternating optimization to jointly optimize satellite association and GS bandwidth allocation. Our proposed framework is low in complexity, paving the way for high-speed Internet connectivity for aviation passengers. Finally, simulation results are provided to demonstrate the effectiveness of our proposed IFC framework for SAGIN.

Space-air-ground integrated networks (SAGIN) are pivotal for achieving uninterrupted in-flight connectivity (IFC). Most existing studies, however, merely treat satellites as transparent forwarding nodes, and overlook their caching capabilities in enhancing the IFC data rate. In this paper, we consider an IFC-oriented SAGIN, where the satellites collaboratively deliver the content to airborne passengers to facilitate airborne communication. Considering the cached files instantaneously accessible via satellites, this work pioneers the integration of multiple inter-satellite links (ISLs) into the IFC framework, thereby innovating the content delivery process. To minimize the average delay of content delivery, we formulate an optimization problem and propose an exact penalty-based method to derive the satellite association scheme. Our proposed framework has a low complexity and thus paves the way for high-speed Internet connectivity to aviation passengers. Finally, simulation results are presented to demonstrate the effectiveness of our proposed IFC framework for SAGIN.

To achieve truly seamless global intelligent connectivity, non-terrestrial networks (NTN) mainly composed of low earth orbit (LEO) satellites and drones are recognized as important components of the future 6G network architecture. Meanwhile, the rapid advancement of the Internet of Things (IoT) has led to the proliferation of numerous applications with stringent requirements for timely information delivery. The Age of Information (AoI), a critical performance metric for assessing the freshness of data in information update systems, has gained significant importance in this context. However, existing modeling and analysis work on AoI mainly focuses on terrestrial networks, and the distribution characteristics of ground nodes and the high dynamics of satellites have not been fully considered, which poses challenges for more accurate evaluation. Against this background, we model the ground nodes as a hybrid distribution of Poisson point process (PPP) and Poisson cluster process (PCP) to capture the impact of ground node distribution on the AoI of status update packet transmission supported by UAVs and satellites in NTN, and the visibility and cross-traffic characteristics of satellites are additionally considered. We derived the average AoI for the system in these two different situations and examined the impact of various network parameters on AoI performance.The simulation results verified the effectiveness of the proposed modeling and analysis method.

Satellites and civil aircrafts (CAs) with computing ability are valuable access platforms, making it possible for Internet of Things (IoT) devices to offload their computation-intensive tasks in remote areas without network infrastructures. Unlike existing works mainly focused on the static scenarios or the interaction between any two types of local, edge and cloud nodes, we propose an innovative multi-tier hybrid parallel computation architecture in CA-augmented space-air-ground integrated networks (CAA-SAGIN). Specifically, devices perform local computing, CAs and satellites act as edge servers, and ground stations of satellite networks operate cloud computing. Aiming to minimize the weighted sum of end-to-end (E2E) delay and energy consumption, we formulate a partial computation offloading problem by jointly considering access strategy, transmit power, computing resource allocation, offloading ratio and delay tolerance. The platform selection exists both within and between layers, and there are inner- and inter-coupling relationships between communication and computing resources. The issue is solved by the proposed multi-tier partial task offloading (MPTO) algorithm. The original problem is firstly decomposed into primal and master subproblems by generalized benders decomposition (GBD) method, and parallel successive convex approximation (SCA) theory is utilized to transform the multi-variable NP-hard master problem into a convex one. Simulation results demonstrate the convergence and optimality of the MPTO algorithm and the advantages of this multi-tier hybrid computation offloading system. Also, the optimal tradeoff between E2E delay and energy consumption can be achieved by the MPTO algorithm.

Space-air-ground integrated networks (SAGIN) have become a research hotspot facing the next generation of communications. The theoretical analysis for non-terrestrial networks (NTN) is significant before applying them in practical scenarios, but the existing works failed to provide a general analysis approach for NTN. Against this background, multiple satellites and civil aircrafts (CAs) are modeled as 3-D binomial point processes (BPPs) in the given finite space in this paper, and we desire to investigate the coverage performance of downlink CA augmented-SAGIN (CAA-SAGIN). Considering the sectorized beam pattern of platforms, we provide a detailed analysis of the different distributions of the serving and interfering platforms and derive the Laplace transform of the interference under shadowed-Rician fading channels. Then, the exact and closed-form expressions are obtained for the general cases with interference and the particular cases without interference via stochastic geometry. The approximations and boundary values are derived by adopting the existing mathematical theories. We analyze the effects of different parameters on the coverage probability of satellite and CA networks, and prove the validity of the derived analytical expressions, approximations, and bounds. Moreover, this work paves the way from the system level to exploit the generic coverage performance of NTN.

Massive Internet of Things (MIoT) devices in the areas without cellular networks have difficulties transmitting data to the network. Since the vehicles have sufficient energy resources and the number of vehicles is high, vehicles passing through these areas can collect MIoT data and relay data to the cellular networks. In this paper, considering the limited energy resources of MIoT devices, we formulate an Energy Efficiency of Packet Uploading (EEPU) Maximization strategy to help MIoT devices upload more packets with less energy consumption to the vehicle. Also, considering the uncertainty of the vehicle arrival, we control the packet forwarding rate between devices to achieve the goal of MIoT device queue stability. The above optimization problem can be solved by the proposed EEPU Maximization Algorithm. Numerical results show that the energy efficiency of the proposed strategy is superior to other strategies, and our proposed strategy can allow a higher packet forwarding rate on the premise of ensuring queue stability.

Although 5G networks have been gradually commercialized, many scenarios like emergency areas and remote regions still exist with vast communication problems. In this paper, we provide capacity analysis for the novel network architecture called civil-aircraft augmented space-air-ground integrated networks (CAA-SAGIN). First, we discuss the influence of the spatial distribution of civil aircraft (CA) and satellites on the Rician factor. Then, based on the derived moment generating function related to small-fading variables, we deduce the closed-form expressions of ergodic capacity under nearest association strategies. The numerical results demonstrate that CA networks can provide significant ergodic capacity with the multi-platform association strategy. The benefits of CA networks are proved quantitatively, and our works can provide a reference for the design of future SAGIN.

Nowadays, massive Internet of Things (MIoT) devices play an essential role due to their easy deployment. In remote areas, although MIoT devices have difficulties accessing cellular networks directly, they can upload their collected information via the passing mobile carriers like vehicles. Considering the limited transmission range of MIoT devices and significant signaling overhead, it is necessary to preprocess these data before sending them to the vehicles. In this paper, we first formulate an energy-minimization problem to determine the optimal number of cluster heads and the optimal size of files while guaranteeing the transmission delay. After selecting cluster heads, a routing strategy is devised to enhance the link reliability further. The above optimization problems can be solved by the proposed Multi-Layer Clustering-Routing (MLCR) Algorithm. Numerical results prove the efficiency of the proposed MLCR Algorithm in MIoT data preprocessing and show a tradeoff problem between energy consumption and route reliability.

In order to meet mobile users’ unprecedented communication demands and the goal of global seamless communication, space–air–ground-integrated networks (SAGINs) have attracted lots of attention in recent years. The existing works related on air segment mainly discussed unmanned aerial vehicles (UAVs), airships, and balloons near the space. However, they neglected many other valuable resources, such as civil aircrafts (CAs). Moreover, communication problems for remote areas and emergency scenarios (such as disasters and hot-spot areas) have not been solved thoroughly. Motivated by these facts, we introduce CAs to enhance the current SAGIN and present a novel architecture called “CAs augmented space–air–ground-integrated vehicular networks” (CAA-SAGIVNs). The proposed network architecture makes breakthrough in three main aspects: 1) a normal network architecture; 2) collaboration with multiple sky access platforms (SAPs); and 3) service-oriented fair allocation. Although CAA-SAGIVN can bring out many benefits, it also faces more challenges due to its high mobility and cross-layer characteristics. Therefore, we provide an exhaustive review of state-of-the-art works on modeling, mobility management, solutions of service-oriented allocation in SAGIN. On the basis of the preliminary investigation and discussion, some open issues are identified as possible future research directions.

Although 5G networks have enabled mobile users to get a better experience, task scheduling remains challenging for massive Internet of Things (IoT) devices in remote areas. This paper investigates the task scheduling problem for delay-aware IoT applications in civil aircraft-augmented space-air-ground integrated networks (CAA-SAGIN), where the normalized sky access platforms (SAPs) can collect and forward the terrestrial tasks. Specifically, we first propose an access control scheme for a non-preemptive priority queuing system and a transmission control scheme with cross-layer optimization. Secondly, considering the uncertain distribution of the transmission numbers and generated data, we formulate a robust two-stage stochastic optimization problem of delay minimization. With the proposed robust task scheduling with risk aversion (RTS-RA) algorithm, the original problem can be decomposed into two subproblems, which can be further transformed into tractable semi-definite program (SDP) problems respectively. Simulation results show that the cross-layer optimization scheme can achieve a good tradeoff between delay and throughput. Also, the RTS-RA algorithm outperforms the exiting offloading schemes in terms of end-to-end delay, transmitted data, and energy consumption with lower computational complexity.