Open Radio Access Network (O-RAN) enables flexible and intelligent radio access network operation through disaggregation, virtualization, open interfaces, and RAN Intelligent Controllers (RICs). At the same time, the data required to train artificial intelligence and machine learning models in O-RAN is naturally distributed across user equipment, base stations, edge clouds, and management entities, which makes centralized learning costly and privacy-sensitive. Federated Learning (FL) has therefore emerged as a promising paradigm for O-RAN intelligence because it enables distributed model training without transferring raw data. In this work, we survey recent studies on the fusion of FL and O-RAN and classify them into three categories: 1) FL-assisted network control, where FL is used as a collaborative learning tool for slicing, offloading, routing, and security; 2) FL training-efficiency optimization, where communication cost, learning latency, resource consumption, and convergence are improved under O-RAN constraints; and 3) integrated approaches that jointly consider network performance and FL efficiency. Based on this taxonomy, we discuss open research challenges, including device heterogeneity, mobility, RIC integration, communication-efficient learning, and security threats, such as model poisoning and inference attacks.
Junsuk Oh, Donghyun Lee, Chunghyun Lee et al.· International Conference on...· 0 citations
Unmanned aerial vehicle (UAV) communications are a promising enabler for 6G networks, offering flexible deployment and strong line-of-sight channel conditions. Effective UAV operation requires jointly optimizing trajectory and user scheduling to balance throughput and information freshness. This paper proposes a proximal policy optimization (PPO)-based deep reinforcement learning (DRL) framework that controls UAV movement and user scheduling together via a joint MultiDiscrete action space. We formulate a Markov decision process for a 8-user, $1000 \times 1000 \mathrm{~m}^{2}$ service area with a 3GPP TR 36.777-compliant channel model, where the agent selects both its next position and which user to serve at each time slot. The proposed PPO policy achieves 85.75 Mbps mean throughput, a 24.4% improvement over the AoI-greedy baseline, while reducing mean AoI by 87.7% compared to the throughput-greedy baseline, reaching a Pareto-optimal trade-off between the two competing objectives. An ablation study over the AoI penalty weight confirms a clear throughput-AoI trade-off, validating the joint design.
Quang Tuan Do, Tung Son Do, Thanh Phung Truong et al.· International Conference on...· 0 citations
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