6G networks can support global, ubiquitous and seamless connectivity through the convergence of terrestrial and non-terrestrial networks (NTNs). Unlike terrestrial scenarios, NTNs pose unique challenges including propagation characteristics, latency and mobility, owing to the operations in spaceborne and airborne platforms. To overcome all these technical hurdles, this survey paper presents the use of artificial intelligence (AI) techniques in learning and adapting to the complex NTN environments. We begin by providing an overview of NTNs in the context of 6G, highlighting the potential security and privacy issues. Next, we review the existing AI methods adopted for 6G NTN optimization, starting from machine learning (ML), through deep learning (DL) to deep reinforcement learning (DRL). All these AI techniques have paved the way towards more intelligent network planning, resource allocation (RA), and interference management. Furthermore, we discuss the challenges and opportunities in AI-powered NTN for 6G networks. Finally, we conclude by providing insights and recommendations on the key enabling technologies for future AI-powered 6G NTNs.

Data caching is a promising technique to alleviate the data traffic burden from the backhaul and minimize data access delay. However, the cache capacity constraint poses a significant challenge to obtaining content through the cache resource that degrades the caching performance. In this paper, we propose a novel two-tier caching mechanism for data caching on mobile user equipment (UE) and the small base station (SBS) level in ultra-dense 6G heterogeneous networks for reducing data access failure via cache resources. The two-tier caching enables users to retrieve their desired content from cache resources through device-to-device (D2D) communications from neighboring users or the serving SBS. The cache-enabled UE exploits millimeter-wave (mmWave)-based D2D communications, utilizing line-of-sight (LoS) links for high-speed data transmission to content-demanding mobile UE within a limited connection time. In the event of D2D communication failures, a dual-mode hybrid system, combining mmWave and microwave $\mathsf{\mu }$Wave technologies, is utilized to ensure effective data transmission between the SBS and UE to fulfill users’ data demands. In the proposed framework. the data transmission speed is optimized through mmWave signals in line-of-sight (LoS) conditions. In non-LoS scenarios, the system switches to $\mathsf{\mu }$Wave mode for obstacle-penetrating signal transmission. Subsequently, we propose a reinforcement learning (RL) approach to optimize cache decisions through the approximation of the Q action-value function. The proposed technique undergoes iterative learning, adapting to dynamic network conditions to enhance the content placement policy and minimize delay. Extensive simulations demonstrate the efficiency of our proposed approach in significantly reducing network delay compared with benchmark schemes.

6G wireless communication networks are expected to use extremely large-scale antenna arrays (ELAAs) to support higher throughput, massive connectivity, and improved system performance. ELAAs would fundamentally alter wave characteristics, transforming them from plane waves into spherical waves, thereby operating in the near field. Near-field communications (NFC) offer unique advantages to enhance system performance, but also present significant challenges in channel modeling, computational complexity, and beamforming design. The use of machine learning (ML) is emerging as a powerful approach to tackle such challenges and has the capabilities to enable intelligent, secure, and efficient 6G wireless communications. In this survey, we discuss ML-driven approaches for NFC. We first outline the fundamental concepts of NFC and ML. We then discuss ML applications in channel estimation, beamforming design, and security enhancement. We also highlight key challenges (e.g., data privacy and computational overhead). Finally, we discuss open issues and future directions to emphasize the role of advanced ML techniques in near-field system design.

Road sparsity is a major cause of routing instability, leading to intermittent connectivity and increased packet loss. To enhance stability in 6G software-defined vehicular networks (SDVNs), we integrate unmanned aerial vehicles (UAVs) into a dynamic vehicular environment. We propose a novel ground-to-air communication protocol that integrates Dedicated Short Range Communication (DSRC), millimeter-wave (mmWave), and terahertz (THz) bands to address path stability, load balancing among controllers, and technology switching to accommodate diverse vehicular demands. Roadside Units (RSUs) and UAVs act as local controllers (LCs), with RSUs communicating via LTE and UAVs via DSRC. The optimal controller (OC) is selected using supervised learning algorithms, Support Vector Machine (SVM), and Random Forest (RF), to ensure balanced load distribution and to manage stable routing across hybrid wireless technologies. The proposed scheme evaluates multiple UAV roles, including LC, relay, and destination, under different communication interfaces. Simulation results in a highway scenario demonstrate that the hybrid approach outperforms the reference DSRC, mmWave, and THz schemes in terms of packet delivery ratio, end-to-end delay, and routing overhead. Specifically, SVM-based OC selection achieved a maximum packet delivery ratio of 97.94%, with an end-to-end delay as low as 0.089 ms and minimal routing overhead, validating its effectiveness in mitigating road sparsity, improving connectivity, and enhancing network performance.