Large language models (LLMs) have demonstrated powerful capability to solve practical problems through complex step-by-step reasoning. Specifically designed LLMs have begun to be integrated into terrestrial communication networks. However, relevant research in the field of satellite communications remains exceedingly rare. To address this gap, we introduce SCNOC-Agentic, a novel architecture especially designed to integrate the management and control of satellite communication systems in LLMs. SCNOC-Agentic incorporates four components tailored to the characteristics of satellite communications: intent refinement, multi-agent workflow, personalized long-term memory, and graph-based retrieval. Furthermore, we define four typical real-world scenarios that can be effectively addressed by integrating with LLMs: network task planning, carrier and cell optimization, fault analysis of satellites, and satellite management and control. Utilizing the SCNOC-Agentic framework, a series of open-source LLMs have achieved outstanding performance on the four tasks under various baselines, including zero-shot CoT, CoT-5, and self-consistency. For example, qwen2.5-70B with SCNOC-Agentic significantly improves the parameter generation accuracy in the network task planning task from 15.6% to 32.2%, while llama-3.3-70B increases from 16.2% to 29.0%. In addition, ablation studies were conducted to validate the importance of each proposed component within the SCNOC-Agentic framework.
The rapid advancement of low-Earth-orbit (LEO) satellite constellations and unmanned aerial vehicles (UAVs) has positioned space–air–ground integrated networks as a key enabler of large-scale IoT services. However, ensuring reliable end-to-end operation remains challenging due to heterogeneous IoT–UAV link conditions and rapidly varying satellite visibility. This work proposes a two-stage optimization framework that jointly minimizes UAV energy consumption during IoT data acquisition and ensures stable UAV–LEO offloading through a demand-aware satellite association strategy. The first stage combines gradient-based refinement with combinatorial path optimization, while the second stage triggers handover only when the remaining offloading demand cannot be met. Simulation results show that the framework reduces UAV energy consumption by over 20% and shortens flight distance by more than 30% in dense deployments. For satellite offloading, the demand-aware strategy requires only 2–3 handovers—versus 7–9 under greedy selection—and lowers packet loss from 0.47–0.60% to 0.13–0.20%. By improving both stages simultaneously, the framework achieves consistent end-to-end performance gains across varying IoT densities and constellation sizes, demonstrating its practicality for future SAGIN deployments.
In light of the increasing scarcity of frequency spectrum resources for satellite communication systems based on the transparent transponder, fast and efficient satellite resource allocation algorithms have become key to improving the overall resource occupancy. In this paper, we propose a reinforcement learning-based Multi-Branch Deep Q-Network (MBDQN), which introduces TL-Branch and RP-Branch to extract features of satellite resource pool state and task state simultaneously, and Value-Branch to calculate the action-value function. On the one hand, MBDQN improves the average resource occupancy performance (AOP) through the selection of multiple actions, including task selection and resource priority actions. On the other hand, the trained MBDQN is more suitable for online deployment and significantly reduces the runtime overhead due to the fact that MBDQN does not need iteration in the test phase. Experiments on both non-zero waste and zero waste datasets demonstrate that our proposed method achieves superior performance compared to the greedy or heuristic methods on the generated task datasets.
Unmanned aerial vehicle (UAV)-assisted satellite downlink transmission is a promising solution for improving coverage and throughput under challenging propagation conditions. However, the achievable performance gains are fundamentally constrained by the coupling between access transmission and the satellite–UAV backhaul, especially when decode-and-forward (DF) relaying and hybrid multiple access are employed. In this paper, we investigate the problem of end-to-end downlink sum-rate maximization in a UAV-assisted satellite network with hybrid non-orthogonal multiple access (NOMA)/orthogonal multiple access (OMA) transmission. We propose a performance-driven end-to-end optimization framework, in which UAV placement is optimized as an outer-layer control variable through an iterative procedure. For each candidate UAV position, a greedy transmission mode selection mechanism and a KKT-based satellite-to-UAV backhaul bandwidth allocation scheme are jointly executed in the inner layer to evaluate the resulting end-to-end downlink performance, whose feedback is then used to update the UAV position until convergence. Simulation results show that the proposed framework consistently outperforms benchmark schemes without requiring additional spectrum or transmit power. Under low satellite elevation angles, the proposed design improves system sum rate and spectral efficiency by approximately 25–35% compared with satellite-only NOMA transmission. In addition, the average user rate is increased by up to 37% under moderate network sizes, while maintaining stable relative gains as the number of users increases, confirming the effectiveness and scalability of the proposed approach.
Space–air–ground integrated networks (SAGINs) enable flexible content delivery through satellite–UAV–ground cooperation, yet time-varying user demand and dynamic backhaul conditions pose significant challenges to efficient UAV caching. To address these challenges, this paper proposes PCICaching, a backhaul-aware and prediction-driven UAV caching framework that integrates LSTM-based popularity forecasting, cache-aware user association, and conditionally activated cooperative caching. Under normal satellite backhaul conditions, PCICaching operates in a latency-oriented mode and reduces average content delivery latency by up to 33.9% and 38.9% compared with representative GTGA-based and history-based baselines, respectively. When backhaul connectivity degrades, the proposed C3 mechanism enlarges cluster-level content coverage and maintains service continuity with only a moderate latency increase of approximately 14.2%. Moreover, the proposed sequential decomposition enables scalable online operation with per-update execution time below 100 ms. These results demonstrate that PCICaching provides a structurally adaptive and computationally efficient solution for UAV-assisted caching in SAGINs, effectively balancing latency efficiency and content availability under time-varying demand and infrastructure uncertainty.