This paper proposes a unified Radio Access Network (RAN) planning and dimensioning framework specifically designed for the heterogeneous requirements of sixth-generation (6G) systems. Addressing the limitations of static fifth-generation (5G) planning tools, the proposed methodology mathematically integrates terrestrial, aerial, and non-terrestrial (NTN) domains into a closed-loop optimization engine. The framework couples physically consistent multi-band propagation models (sub-6 GHz to THz) with an Artificial Intelligence (AI)-driven solver that utilizes Pseudo-Spatio-Temporal Residual Networks (PST-ResNet) for traffic prediction and a Self-Coordinated Dynamic Swarm Control System (SC-DSCS) for resource allocation. Unlike generic architectural surveys, this work explicitly formulates the dimensioning problem to jointly optimize site placement, Reconfigurable Intelligent Surface (RIS) phase-shifts, and Fluid Antenna System (FAS) configurations under strict coverage and latency constraints. Validated through extensive system-level simulations across Urban Ultra-Dense, Industrial Internet of Things (IoT), and Smart City scenarios, the results demonstrate that the proposed AI-driven framework achieves a 22% improvement in coverage probability and up to 30% gains in energy efficiency compared to static 5G baselines. The study provides quantitative design guidelines for deploying sustainable, latency-aware 6G infrastructures, bridging the gap between theoretical channel models and practical network dimensioning.

The transition from Fifth Generation (5G) New Radio (NR) systems to Beyond 5G (B5G) and Sixth Generation (6G) networks requires innovative architectures capable of supporting ultra-high data rates, sub-millisecond latency, and massive connection densities in dense urban environments. This paper proposes a comprehensive design methodology for a mini-cluster architecture operating in sub-THz (0.1–0.3 THz) and THz (0.3–3 THz) frequency bands. The proposed framework aims to enhance existing 5G infrastructure while enabling B5G/6G capabilities, with a particular focus on hotspot coverage and mission-critical applications in dense urban environments. The architecture integrates mini Base Stations (mBS), Distributed Edge Computing Units (DECUs), and Intelligent Reflecting Surfaces (IRS) for coverage enhancement and blockage mitigation. Detailed link budget analysis, coverage and capacity planning, and propagation modeling tailored to complex urban morphologies are performed for representative case study cities, Quito and Guayaquil (Ecuador). Simulation results demonstrate up to 100 Gbps peak data rates, sub 100 μs latency, and tenfold energy efficiency gains over conventional 5G deployments. Additionally, the proposed framework highlights the growing importance of THz communications in the 5G evolution towards B5G and 6G systems, where ultra-dense, low-latency, and energy-efficient mini-cluster deployments play a key role in enabling next-generation connectivity for critical and immersive services. Beyond the studied cities, the proposed framework can be generalized to other metropolitan areas facing similar propagation and capacity challenges, providing a scalable pathway for early-stage sub-THz/THz deployments in B5G/6G networks.

The transition to Beyond fifth generation of wireless networks (B5G) and sixth generation of wireless networks (6G) exposes the severe interference and coverage limitations of conventional cell-centric architectures. To overcome these bottlenecks, this paper presents a scalable four-layer radio network planning framework that jointly optimizes the deployment of distributed active antenna arrays and passive reconfigurable intelligent surfaces (RISs). The proposed framework integrates a digital twin (DT) loop within an Open-RAN (O-RAN) architecture, employing multi-agent deep reinforcement learning (MADRL) and fractional programming (FP) for real-time joint active and passive beamforming optimization. Extensive Monte Carlo simulations in a dense urban environment demonstrate a 45% increase in spectral efficiency, a 30% reduction in uplink interference, and an 84% reduction in coverage holes compared to legacy 5G networks. Ultimately, these results provide network operators with a cost-effective, standards-compliant blueprint to extend non-line-of-sight (NLOS) coverage by 40% without incurring the prohibitive capital expenditure (CAPEX) of dense active hardware deployments. Furthermore, the proposed architecture demonstrates a competitive 10–15% margin of improvement in spectral efficiency over recent state-of-the-art DRL-based RIS frameworks.

This paper examines the secrecy outage probability (SOP) in Fluid Reconfigurable Intelligent Surfaces (FRIS) and contrasts their performance against two alternative RIS architectures: a traditional planar RIS and a compact RIS layout. To characterize the end-to-end FRIS channel, a maximum likelihood estimation (MLE) approach is introduced, while a Q-learning algorithm is employed to adaptively select the spatial positions of FRIS elements. Numerical evaluations show that optimizing element placement in FRIS significantly improves SOP compared to conventional RIS without phase adaptation. However, these improvements become less evident once the conventional RIS implements optimized beamforming (BF) and phase-shift (PS) control. In addition, FRIS maintains a clear advantage over compact RIS designs with optimized BF and PS, mainly due to its lower spatial correlation. Results further indicate that reducing the inter-element distance negatively impacts SOP, highlighting the importance of spatial diversity. Moreover, the proposed MLE-based channel modeling and learning-driven optimization framework offer a scalable and data-efficient methodology for exploring secrecy performance. These findings establish FRIS as a promising architecture for improving physical layer security in spatially constrained and correlation-limited wireless environments.

As Sixth Generation (6G) networks evolve toward a unified terrestrial and non-terrestrial ecosystem, maintaining optimal Quality of Service (QoS) across highly dynamic environments remains a formidable challenge. This paper proposes a high-fidelity Digital Twin (DT)-driven framework for Automatic Quality, Coverage, and Capacity Optimization (AQCCO), specifically tailored for integrated Unmanned Aerial Vehicle (UAV) and Non-Terrestrial Network (NTN) systems. By leveraging a multilayer DT architecture, we construct a real-time virtual mirror of the physical network, enabling predictive fault diagnosis and proactive resource orchestration. At the core of our solution is a Multi-Agent Reinforcement Learning (MARL) approach that jointly optimizes UAV trajectories, satellite beamforming, and Reconfigurable Intelligent Surface (RIS) configurations. Extensive simulations conducted in diverse urban and rural scenarios validate the framework, demonstrating an average improvement of 15.3 dB in SINR, a 23.6% boost in coverage, and an 89.4% increase in network throughput. Furthermore, the system achieves an energy efficiency gain of 31.2% while maintaining a sub-50 ms decision-making latency. The framework ensures rapid service recovery under emergency conditions with sub-second response times, providing network operators with an intelligent, demand-responsive tool for optimizing key performance indicators (KPIs) in the 6G era.