LLM-Enabled NWDAF: A Step Toward AI-Native 6G Network Intelligence

The Network Data Analytics Function (NWDAF) is central to enabling zero-touch network management in fifth-generation(5G) networks by supporting real-time analytics and closed-loop automation. Despite its critical role, open-source NWDAFimplementations remain limited in scope and accessibility. In this paper, we develop an open-source NWDAF, compatiblewith the open-source core network Free5GC, that collects network data via subscriptions to Network Functions (NFs), andalso includes an integrated Large Language Model (LLM) interface that enables natural language interaction with humanoperators. The interface processes user intents, encodes them using a semantic embedding model, and maps them to one ofseven predefined intent categories to trigger analytics queries or event subscription commands. This architecture abstracts thecomplexity of traditional interfaces, allowing non-expert users to manage network analytics and subscriptions with ease. Thesystem supports Access and Management Function (AMF) and Session Management Function (SMF) event subscriptions,real-time monitoring, and analytics retrieval via Prometheus, all accessible through a conversational interface. By bridgingAI-driven intent recognition with standardized network analytics, our implementation enhances operator usability and providesa foundation towards AI-native 6G networks. The source code and datasets generated during the current study are available inthe github repository, https://github.com/HenokDanielbfg/testbed.