Openness and programmability in the O-RAN architecture enable closed-loop control of the Radio Access Network (RAN). Artificial Intelligence (AI)-driven xApps, in the near-realtime RAN Intelligent Controller (RIC), can learn from network data, anticipate future conditions, and dynamically adapt radio configurations. However, their development and adoption are hindered by the complexity of low-level RAN control and monitoring message models exposed over the O-RAN E2 interface, limited interoperability across heterogeneous RAN software stacks, and the lack of developer-friendly frameworks. In this paper, we introduce xDevSM, a framework that significantly lowers the barrier to xApp development by unifying observability and control in O-RAN deployments. By exposing a rich set of Key Performance Measurements (KPMs) and enabling fine-grained radio resource management controls, xDevSM provides the essential foundation for practical AI-driven xApps. We validate xDevSM on real-world testbeds, leveraging Commercial Off-the-Shelf (COTS) devices together with heterogeneous RAN hardware, including Universal Software Radio Peripheral (USRP)-based Software-defined Radios (SDRs) and Foxconn radio units, and show its seamless interoperability across multiple open-source RAN software stacks. Furthermore, we discuss and evaluate the capabilities of our framework through four O-RAN-based scenarios of high interest: (i) KPM-based monitoring of network performance, (ii) slice-level Physical Resource Block (PRB) allocation control across multiple User Equipments (UEs) and slices, (iii) mobility-aware handover control, and (iv) an AI-based sliceisolation xApp that uses a LinUCB contextual bandit to tune perslice PRB quotas online, showing that xDevSM can implement intelligent closed-loop applications, laying the groundwork for learning-based optimization in heterogeneous RAN deployments. Finally, we characterize the runtime overhead of xDevSM under sustained high-rate E2 traffic, reporting indication processing latency, control round-trip time, delivery stability, and Central Processing Unit (CPU)/memory footprint of the xApp pod, and show that the framework operates well within the O-RAN Near- Real-Time (Near-RT) RIC control-loop budget. xDevSM is open source and available as a foundational tool for the research community.
Feraudo, A., Maxenti, S., Lacava, A., Bonati, L., Bellavista, P., Polese, M., et al. (2026). xDevSM: An Open-Source Framework for Portable, AI-Ready xApps Across Heterogeneous O-RAN Deployments. IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 23, 7636-7649 [10.1109/tnsm.2026.3733344].
xDevSM: An Open-Source Framework for Portable, AI-Ready xApps Across Heterogeneous O-RAN Deployments
Feraudo, Angelo;Bellavista, Paolo;
2026
Abstract
Openness and programmability in the O-RAN architecture enable closed-loop control of the Radio Access Network (RAN). Artificial Intelligence (AI)-driven xApps, in the near-realtime RAN Intelligent Controller (RIC), can learn from network data, anticipate future conditions, and dynamically adapt radio configurations. However, their development and adoption are hindered by the complexity of low-level RAN control and monitoring message models exposed over the O-RAN E2 interface, limited interoperability across heterogeneous RAN software stacks, and the lack of developer-friendly frameworks. In this paper, we introduce xDevSM, a framework that significantly lowers the barrier to xApp development by unifying observability and control in O-RAN deployments. By exposing a rich set of Key Performance Measurements (KPMs) and enabling fine-grained radio resource management controls, xDevSM provides the essential foundation for practical AI-driven xApps. We validate xDevSM on real-world testbeds, leveraging Commercial Off-the-Shelf (COTS) devices together with heterogeneous RAN hardware, including Universal Software Radio Peripheral (USRP)-based Software-defined Radios (SDRs) and Foxconn radio units, and show its seamless interoperability across multiple open-source RAN software stacks. Furthermore, we discuss and evaluate the capabilities of our framework through four O-RAN-based scenarios of high interest: (i) KPM-based monitoring of network performance, (ii) slice-level Physical Resource Block (PRB) allocation control across multiple User Equipments (UEs) and slices, (iii) mobility-aware handover control, and (iv) an AI-based sliceisolation xApp that uses a LinUCB contextual bandit to tune perslice PRB quotas online, showing that xDevSM can implement intelligent closed-loop applications, laying the groundwork for learning-based optimization in heterogeneous RAN deployments. Finally, we characterize the runtime overhead of xDevSM under sustained high-rate E2 traffic, reporting indication processing latency, control round-trip time, delivery stability, and Central Processing Unit (CPU)/memory footprint of the xApp pod, and show that the framework operates well within the O-RAN Near- Real-Time (Near-RT) RIC control-loop budget. xDevSM is open source and available as a foundational tool for the research community.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.



