This dissertation focuses on the design, optimization, and experimental evaluation of NextG RANs integrating Open RAN principles, data-driven control loops, and intelligent resource allocation, demonstrating NextG RANs reconfigurable in real time to meet 6G requirements.
Abstract
Recent years have seen the evolution of the traditional Radio Access Network (RAN) toward more open, programmable, disaggregated, and intelligent architectures, known as an Open RAN. Future Next Generation (NextG) networks are envisioned to be AI-native, enabling data-driven closed-loop optimization of Base Station resources, while Reconfigurable Intelligent Surfaces (RIS) emerge as key enablers for wireless propagation and spectral efficiency toward 6G and beyond. This dissertation focuses on the design, optimization, and experimental evaluation of NextG RANs integrating Open RAN principles, data-driven control loops, and intelligent resource allocation. The work emphasizes cross-layer optimization, including energy-efficient power control, and explores AI-driven network slicing, scheduling, and link adaptation, demonstrating NextG RANs reconfigurable in real time to meet 6G requirements, first analyzing architectural enablers and modeling frameworks, then prototyping and evaluating solutions on experimental platforms and Digital Twins. Main contributions include: (i) Deep Reinforcement Learning (DRL) solutions for network slicing and scheduling; (ii) PandORA, a framework for automatic design, training, and deployment of DRL-based Open RAN applications on the Colosseum wireless network emulator; (iii) physical-layer RIS channel modeling and optimized resource allocation across spectrum bands; (iv) system-level evaluation of RIS-assisted channels for eMBB and URLLC traffic; (v) integration of RIS within Open RAN; (vi) online RL solutions for link adaptation; and (vii) spectrum sharing between cellular and Non-Terrestrial Network links via power control and beamforming. This work provides algorithmic designs, frameworks, and validation from simulation and hardware-in-the-loop emulation to over-the-air 5G testbed experiments, addressing industry and academic needs for wireless research.
This survey formally categorizes state-of-the-art DTN architectures into passive monitoring twins and active control twins, and provides an in-depth evaluation of their underlying enabling technologies, specifically ray-tracing, reconfigurable intelligent surfaces, artificial intelligence, and mobile edge computing.
Charalampos Oikonomidis, E. T. Michailidis, N. Miridakis· 0 citations
Efficient long-term network evolution is becoming increasingly critical in dense 5G-Advanced and beyond cellular systems, where persistent traffic imbalances and localized congestion pose significant challenges that conventional short-term radio resource management alone cannot fully mitigate. This paper proposes a digital twin (DT)-enabled non-real-time (NRT) network evolution framework integrated with a large language model (LLM). Within this architecture, the digital twin provides a high-fidelity, controllable environment for evaluating infrastructure actions, while the LLM serves as a strategic orchestration engine that recommends cost-efficient network upgrades based on observed network states. Unlike traditional optimization methods that require exhaustive mathematical reformulations for each specific scenario, the proposed framework leverages the reasoning capabilities of LLMs to interpret operator objectives and constraints in natural language, generating structured evolution plans. The considered NRT action space encompasses antenna upgrades, bandwidth expansion, and new base station (BS) deployment. A techno-economic formulation is introduced to jointly evaluate load reduction performance and overall economic expenditure. Numerical results in a dense cellular scenario demonstrate that the framework effectively reduces peak resource utilization and provides diverse, coordinated evolution strategies tailored to varying network conditions.
Yukai Wang, Janghee Woo, G. Hahm et al.· International Conference on...· 0 citations
CIS-RAN is proposed, a novel 6G RAN architecture built on three pillars of cooperative, intelligent, and service-based design that enables flexible collaboration across distributed RAN nodes and multi-dimensional domains, integrates intelligence throughout the network, and supports advanced RAN capability exposure as services.
Xiaoyun Wang, Nan Li, Qi Sun et al.· Science China Information Sc...· 0 citations
As the transition toward sixth-generation (6G) wireless networks accelerates, the demand for ultra-low latency and high energy efficiency has become paramount. Traditional Mobile Edge Computing (MEC) frameworks face significant challenges in highly dynamic and interference-limited environments. This survey explores a synergistic architectural framework that integrates Fluid Antenna Systems (FAS), Reconfigurable Intelligent Surfaces (RIS), and Hybrid Non-Orthogonal Multiple Access (NOMA)-MEC to address these requirements. We investigate how FAS-enabled port selection enhances channel disparity for optimized NOMA pairing, while RIS-controlled interference landscapes provide the stability necessary for robust Successive Interference Cancellation (SIC) decoding. This comprehensive survey provides a detailed roadmap for future research, highlighting the critical role of programmable physical layers in enabling the next generation of intelligent edge computing systems.
Kiet Nguyen Tuan Tran, Huy Dang Mac, Tung Son Do et al.· International Conference on...· 0 citations
The risk of cross-domain cascading failures in cyber–physical power systems (CPPSs) has become increasingly significant. The existing studies generally employ communication networks with static routing and fixed bandwidth allocation, which are insufficient to cope with dynamic load fluctuations and unexpected faults. To address these limitations, this paper incorporates the flexible optical-layer resource scheduling capability of software-defined optical networks (SDONs) and proposes an SDON-enabled CPPS model along with a control network optimization method. First, a three-layer CPPS architecture based on the SDON framework is constructed to characterize the interaction mechanism between the control layer and the data forwarding layer, as well as the fault propagation paths. Second, a control network optimization configuration model with the objective of minimizing energy consumption is established in which primary–backup routing schemes and wavelength resources are jointly designed using a mixed-integer linear programming approach. Finally, with load shedding rate adopted as the evaluation metric, a multidimensional vulnerability assessment method for CPPSs is proposed. The simulation results demonstrate that, compared with random control networks, the optimized CPPS reduces the average energy consumption by 53.6% and 34.2% under single-fault and multiple-fault scenarios, respectively, while the load shedding rate is reduced by 23% and 37.2%, thereby verifying the effectiveness of the proposed method.
Intent-Based Networking (IBN) has emerged as a promising paradigm for simplifying network management by allowing operators and applications to specify high-level service objectives rather than low-level device configurations. Early IBN research was mainly developed in Software-Defined Networking (SDN), Network Function Virtualization (NFV), transport networks, core networks, and data-center environments, where programmability, virtualization, and relatively stable infrastructure models enabled intent translation, orchestration, and assurance. However, realizing IBN in end-to-end mobile networks is more challenging because the Radio Access Network (RAN) is highly dynamic, wireless-channeldependent, mobility-sensitive, and governed by multiple control timescales. The emergence of Open RAN (O-RAN) changes this landscape by making the RAN programmable, disaggregated, data-driven, and control-lable through non-real-time and near-real-time intelligent control loops. This survey reviews the evolution of IBN from SDN/NFV-enabled automation toward O-RAN-driven end-to-end intent-based networking for 5G-Advanced and 6G. We discuss architectural mechanisms, key challenges, recent advances in AI-driven and agentic IBN, and future research directions including Large Language Model (LLM)-based intent translation, contractbased O-RAN slicing, digital twin-assisted validation, and trustworthy closed-loop orchestration.
Dongwook Won, Thanh Thien-An Dang, Ton That Tam Dinh et al.· International Conference on...· 0 citations