Skip to content
Open access

AI-Enabled Hierarchical Network Selection in Integrated 6G TN-NTN Architectures

Sep 2026 · Electronics · 0 citations · 22 references

TL;DR

An altitude-aware Deep Learning framework is proposed that casts multi-tier network selection as a seven-class classification problem spanning standalone TN, LEO, HAPS, and UAV access as well as their TN-assisted multi-connectivity combinations, as the three NTN tiers differ by up to four orders of magnitude in altitude and are therefore not interchangeable from a latency and throughput perspective.

Abstract

Sixth-generation (6G) wireless systems target ubiquitous connectivity by integrating terrestrial network (TNs) and non-terrestrial network (NTN) cooperation, including low-Earth-orbit (LEO) satellites, high-altitude platform stations (HAPS), and unmanned aerial vehicles (UAVs). In such a vertically stratified architecture characterized by massive multi-connectivity, the selection of the most suitable tier or tier-combination for each mobile user is a complicated task, as the decision depends jointly on the propagation environment, user requirements, and the instantaneous characteristics of the topology. This paper proposes an altitude-aware Deep Learning (DL) framework that casts multi-tier network selection as a seven-class classification problem spanning standalone TN, LEO, HAPS, and UAV access as well as their TN-assisted multi-connectivity combinations, as the three NTN tiers differ by up to four orders of magnitude in altitude and are therefore not interchangeable from a latency and throughput perspective. A fifteen-feature dataset is generated through extensive Monte Carlo simulations based on standardized channel and geometry models, including 3GPP TR 38.901 terrestrial pathloss and line-of-sight probability, satellite-constellation elevation angles, and air-to-ground link geometry for HAPS and UAV. A deep neural network (DNN) is trained on the resulting dataset and assessed using stratified five-fold cross-validation. The proposed model achieves an overall classification accuracy of 92.8% with a macro-averaged F1-score of 0.87 and a single-sample inference latency of approximately 1.8 ms, well within typical 6G handover budgets. The results demonstrate that requirement- and geometry-aware tier selection can be performed accurately, enabling real-time decision-making in ambiguous multi-connectivity configurations for 6G networks.

Read PDF

Similar papers

Open access 2026

NCP-DRL: Geometry-Aware Deep Reinforcement Learning for Real-Time Transmission in Multi-HAP-Assisted Satellite Networks

Non-terrestrial networks (NTNs) integrating low Earth orbit (LEO) satellites and high-altitude platforms (HAPs) are expected to play an important role in beyond-fifth-generation (B5G) and sixth-generation (6G) wireless systems by providing wide-area coverage and resilient connectivity. However, the coexistence of multi...

Mamadou Aliou Diallo, Hui Zhao, M. Muthanna et al. · 0 citations
Open access 2026

AI-Native Handover Management for 6G Networks Leveraging O-RAN Architecture

This paper places the terrestrial-satellite UAV handover decision inside the near-real-time RIC as an xApp, using a deep reinforcement learning (DRL) framework that combines a Deep Q-Network (DQN) with Prioritized Experience Replay (PER) and a reward shaped to weigh the long-term cost of switching against the reliabili...

Anirudh Warrier, Saba Al-Rubaye · 0 citations
Preprint Oct 2026

Hierarchical RIS Association for FR3 Space-Air-Ground Integrated Networks

The growing demand for diverse sixth-generation (6G) applications requires efficient connectivity, seamless service continuity, and extended network coverage. Although terrestrial infrastructures can effectively serve most wireless user equipment (UE), communication reliability may be significantly degraded in remote o...

Muddasir Rahim, Irfan Azam, S. Cherkaoui · 0 citations
Review Open access 2026

A Survey on Reinforcement Learning Methods for Seamless Connectivity in 6G Non-Terrestrial Networks: Algorithms and Key Findings

This paper presents a comprehensive tutorial on RL-based methods for seamless 6G NTN connectivity, identifying 14 optimization challenges across four categories of NTN characteristics, and surveys state-of-the-art RL approaches, and analyzes their suitability under real-world NTN conditions.

Soyi Jung, Huiyeon Jang, Seoyeong Park et al. · 0 citations
Conference Open access Sep 2026

AI-Enabled Resource Management for Non-Terrestrial Network Integrated 6G Communication Systems

Non-Terrestrial Networks (NTN) are expected to play a main role in sixth-generation (6G) wireless communication systems by extending connectivity beyond the limitations of terrestrial infrastructure and enabling near global coverage. This article proposes an AI-enabled resource management framework for integrated NTN–6...

Slock Ahuja, Praveen Kumar Sharma, C. Parmar et al. · 0 citations

Optimized deep learning architectures for radio intelligence in 6G networks

The transition from Fifth Generation of Cellular Networks (5G) and 5G-Advanced toward Sixth-Generation Mobile Networks (6G) is redefining wireless communication systems as Artificial Intelligence (AI)-native infrastructures, where intelligence is embedded throughout the communication architecture and pushed closer to t...

Germán David Góez-Sánchez · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.