The Open Radio Access Network (O-RAN) NearReal-Time RAN Intelligent Controller (Near-RT RIC) hosts xApps that perform per-User-Equipment (UE) closed-loop control over the E2 interface, and proactive control of handover, scheduling, and anomaly response depends on the freshness of the underlying counters. Surveyed per-UE xApps that explicitly describe their E2 binding rely on Periodic Report subscriptions through E2 Service Model for Key Performance Measurement (E2SM-KPM), which forces every measurement to wait for a configured reporting period before reaching the Near-RT RIC. This paper surveys seven per-UE Near-RT RIC xApp works published between 2023 and 2026 and aligns them with the Measurement Event trigger style introduced in E2SM-KPM v7.0 (2025). The new trigger style enables cell-condition-gated per-UE reporting through REPORT Service Styles 3 and 5, while perUE-bound event conditions remain explicitly out of scope and constitute a clean specification-evolution opportunity. Closing the gap between Periodic-only xApp practice and the Measurement Event primitive opens a class of event-driven per-UE xApps that the current control loop cannot support.
Thanh Thien-An Dang, Dongwook Won, Juyoung Kim et al.· International Conference on...· 1 citation
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
