.png){kind=icon}
.png){kind=icon}
Return
SIM-Empowered LAINs: A Unified Channel Model-Driven Optimization Framework
.png){kind=icon}
PRE
AI
DOI：10.1109/mwc.2026.3687488.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Motivated by the transformative potential of integrating uncrewed aerial vehicles (UAVs) and stacked intelligent metasurfaces (SIMs) into low-altitude aerial intelligent networks (LAINs), this article provides a comprehensive investigation of UAV-SIM technologies within integrated sensing and communication (ISAC) systems. By synergizing physical mobility with real-time electromagnetic wavefront manipulation, the UAV-SIM paradigm is poised to significantly enhance system performance across diverse operational scenarios. Despite these promising prospects, deploying UAV-SIM technology in LAINs faces substantial bottlenecks, particularly in the accurate characterization of complex air-to-ground propagation environments and the design of efficient optimization algorithms. To address these challenges, we propose a unified channel model-driven optimization framework tailored to ensure reliable quality of service for UAV-SIM-enabled LAINs. Utilizing the 3GPP TR 38.901 channel model as a realistic benchmark, this framework establishes a rigorous foundation for synthesizing and validating resource allocation strategies, ultimately yielding superior system capacity and reliability. Furthermore, to improve the robustness and efficiency of end-to-end information processing, we develop a deep reinforcement learning (DRL) scheme based on the mixture-of-experts architecture. This specialized approach facilitates the optimal management of network resources, thereby enabling highly efficient signal transmission. Finally, we outline open research directions and emerging trends to stimulate future investigations in the realm of UAV-SIM-enabled LAINs.
Keywords:
SIM
LAINs
channel model
DRL
ISAC
Journal
IF:
11.5
Papers:
2.7K
Citations:
1.3W
View more organizations