Large Artificial Intelligence Model Guided Deep Reinforcement Learning for Resource Allocation in Non Terrestrial Networks

Large AI Model (LAM) have been proposed to applications of Non-Terrestrial Networks (NTN), that offer better performance with its great generalization and reduced task specific trainings. In this paper, we propose a Deep Reinforcement Learning (DRL) agent that is guided by a Large Language Model (LLM). The LLM operates as a high level coordinator that generates textual guidance that shape the reward of the DRL agent during training. The results show that the LAM-DRL outperforms the traditional DRL by 40% in nominal weather scenarios and 64% in extreme weather scenarios compared to heuristics in terms of throughput, fairness, and outage probability.

Empirical 3D Channel Modeling for Cellular-Connected UAVs: A Triple-Layer Machine Learning Approach

This work proposes an empirical air to ground (A2G) propagation model specifically designed for cellular connected unmanned aerial vehicles (UAVs). An in depth aerial drive test was carried out within an operating Long Term Evolution (LTE) network, gathering thorough measurements of key network parameters. Rigid preprocessing and statistical analysis of these data produced a strong foundation for training a new triple layer machine learning (ML) model. The proposed ML framework employs a systematic hierarchical approach. Accordingly, the first two layers, Stepwise Linear Regression (STW) and Ensemble of Bagged Trees (EBT) generate predictions independently, meanwhile, the third layer, Gaussian Process Regression (GPR), explicitly acts as an aggregation layer, refining these predictions to accurately estimate Key Performance Indicators (KPIs) such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength (RSSI), and Path Loss (PL). Compared to traditional single layer ML or computationally intensive ray tracing approaches, the proposed triple layer ML framework significantly improves predictive accuracy and robustness, achieving around 99 percent accuracy in training and above 90 percent in testing while utilizing a minimal but effective feature set log transformed 3D and 2D propagation distances, azimuth, and elevation angles. This streamlined feature selection substantially reduces computing complexity, thus enhancing scalability across various operating environments. The proposed frameworks practicality and efficacy for real world deployment in UAV integrated cellular networks are further demonstrated by comparative analyses, which underscore its substantial improvement.