Toward Fusion Intelligence of Open Radio Access Network with Federated Learning: A Survey

Abstract

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.