The deployment of high-speed Uncrewed Aerial Vehicles (UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers. While Deep Reinforcement Learning (DRL) offers rapid tactical control, it lacks the zero-shot strategic reasoning required to quickly adapt to dynamic Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). Conversely, Large Language Models (LLMs) excel at semantic reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control. To bridge this gap, we propose a novel Hierarchical LLM-driven control framework. A massive cloud-based LLM deployed on a High-Altitude Platform Station (HAPS) manages slow-timescale global load balancing, while lightweight edge-LLMs on individual UAVs translate local observations into tactical sub-goals. These sub-goals guide a fast-timescale physical DRL controller to execute collision-free, handover-aware trajectories. Simulation results demonstrate that our agentic architecture significantly reduces collision rates and improves aggregate system throughput compared to existing baselines.
Zijiang Yan, Hao Zhou, W. Jaafar et al.· 0 citations
We consider a downlink multicell multiple-input multiple-output (MIMO) system in an urban region, with a focus on improving the capacity of cell-edge user equipments (UEs). These UEs typically experience lower rates than near UEs because of shadowing, path loss, and inter-cell interference (ICI). To address this issue, we integrate a high-altitude platform station (HAPS) with the terrestrial network as a relay for edge-UE transmissions. We assume that the HAPS operates in full-duplex (FD) mode and exploits its large physical size to enhance passive self-interference (SI) suppression by separating its transmit and receive antennas. In the proposed scheme, each terrestrial base station (BS) forwards edge-UE data to the FD-HAPS, which then relays the data to the intended edge UEs. To design beams at both BSs and HAPS, we formulate a sum-rate maximization problem for under total transmit-power and minimum quality-of-service (QoS) constraints. To solve the resulting non-convex problem, we develop a centralized algorithm based on successive convex approximation (SCA) and alternating optimization (AO) for fast convergence. Simulation results show that relaying information via FD-HAPS significantly improves the capacity of cell-edge UEs compared with a terrestrial-only network.
Low Earth Orbit (LEO) satellite constellations enable global low-latency connectivity but face challenges due to weather-dependent link variability, orbital dynamics, and heterogeneous ground infrastructure. In this paper, we propose a hybrid LEO-terrestrial architecture that integrates Software-Defined Networking (SDN) ground station clusters with repeater-assisted reception and a structured fallback mechanism. We develop a stochastic model that captures weather-driven reliability, correlated repeater behavior, and multi-path reception, and formulate an optimization problem to minimize the expected communication delay. To address the intractability of this problem in large-scale, partially observable environments, we design a fully decentralized Multi-Agent Reinforcement Learning (MARL) framework based on Proximal Policy Optimization (PPO), where each satellite makes decisions using only local observations. The reward is aligned with the analytical delay objective, ensuring consistency between the model and learned policies. Simulation results across diverse scenarios demonstrate that the proposed approach reduces the mean delay by 40-60% and significantly decreases fallback usage compared to baseline methods. These results highlight the effectiveness of the proposed framework in enabling adaptive and delay-efficient control in next-generation LEO satellite systems.
Wafa Hasanain, Pablo G. Madoery, H. Yanikomeroglu et al.· IEEE Open Journal of the Com...· 0 citations
The growing demand for adaptive, resilient communication in software-defined networking (SDN)-enabled low Earth orbit (LEO) satellite networks underscores the importance of optimized SDN controller management. In particular, the overhead introduced by setup penalties and constraints on controller capacity significantly impacts key performance metrics, including satellite-to-controller delay, reassignment frequency, and the number of concurrently active controllers. These factors collectively influence the network’s ability to provide low-latency services while maintaining resource utilization in dynamic orbital environments. To investigate these dynamics, we develop a simulation framework based on OMNeT++ and INET, extending the open-source satellite simulator OS3 with enhanced satellite mobility and dynamic routing. The framework integrates SDN functionality into LEO satellite networks using the OpenFlow protocol, enabling centralized, programmable control with real-time adaptability. A central challenge in such networks is not only assigning satellites to appropriate controllers, but also dynamically activating and deactivating SDN controllers to match evolving topologies and traffic demands. To address this, we consider the baseline Dynamic Satellite-to-Controller Assignment (DSCA), the proposed Optimal Dynamic Satellite-to-Controller Assignment (Opt-DSCA), and their scalable heuristic variants (H-DSCA and H-Opt-DSCA). Opt-DSCA jointly minimizes satellite-to-controller delay and the number of active controllers, while incorporating setup penalties and activation costs to discourage unnecessary satellite migrations and redundant controller utilization. Simulation results reveal that both setup penalties and controller activation thresholds are critical determinants of system behavior across both optimization-based and heuristic schemes. Lower penalties enhance adaptability but result in more frequent reassignments and higher variability in controller state transitions. Conversely, higher penalties improve robustness by limiting controller switching, though at the cost of reduced flexibility and increased latency. These findings highlight the necessity of jointly optimizing reassignment policies and controller activation strategies to support robust, low-latency, and resource-aware SDN architectures for large-scale LEO satellite constellations.
Wafa Hasanain, Pablo G. Madoery, H. Yanikomeroglu et al.· IEEE Open Journal of the Com...· 0 citations
Simulation results demonstrate that the proposed GNN-RSMA interference management algorithm outperforms conventional multiple access schemes while achieving fairness and worst-user performance comparable to successive convex approximation (SCA)-based optimization at only a fraction of its computational cost.