Project Grant 2549233

The National Science Foundation Division of Information and Intelligent Systems awarded North Carolina State University $133,333 on October 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop ARMANI, a collaborative research framework embedding artificial intelligence into the core of next-generation wireless network management and control.

ARMANI addresses three critical limitations in open radio access network (O-RAN) management. The framework introduces a shared learning substrate within the RAN Intelligent Controller that allows modular network applications (xApps and rApps) to exchange learned representations, coordinate decisions, and resolve conflicts. It designs orchestration mechanisms that dynamically co-locate AI workloads alongside radio access network functions, leveraging idle compute capacity through fine-grained observability and predictive scaling. The work develops a foundation model-driven reasoning layer that fuses multimodal telemetry streams, including key performance measurements and device logs, to deliver proactive, context-aware control through multi-modal AI alignment of large language models and time series encoders.

The project operates as a collaborative research effort between Yale University and North Carolina State University. Performance occurs in Raleigh, North Carolina, with a period of performance from October 1, 2026, through September 30, 2029. The framework has potential to improve efficiency, reliability, and adaptability of next-generation wireless networks, benefiting critical applications including public safety communications, autonomous systems, and immersive media.