End-to-End Edge AI Service Provisioning Framework in 6G ORAN
It addresses the problem of complex orchestration for network operators in 6G edge AI, though it is incremental as it builds on existing O-RAN and LLM technologies.
This paper tackles the challenge of automating AI service provisioning in 6G Open Radio Access Networks by proposing a framework that uses Large Language Model agents to translate user descriptions into deployable services and network configurations, demonstrating feasibility through a prototype with open-source tools.
With the advent of 6G, Open Radio Access Network (O-RAN) architectures are evolving to support intelligent, adaptive, and automated network orchestration. This paper proposes a novel Edge AI and Network Service Orchestration framework that leverages Large Language Model (LLM) agents deployed as O-RAN rApps. The proposed LLM-agent-powered system enables interactive and intuitive orchestration by translating the user's use case description into deployable AI services and corresponding network configurations. The LLM agent automates multiple tasks, including AI model selection from repositories (e.g., Hugging Face), service deployment, network adaptation, and real-time monitoring via xApps. We implement a prototype using open-source O-RAN projects (OpenAirInterface and FlexRIC) to demonstrate the feasibility and functionality of our framework. Our demonstration showcases the end-to-end flow of AI service orchestration, from user interaction to network adaptation, ensuring Quality of Service (QoS) compliance. This work highlights the potential of integrating LLM-driven automation into 6G O-RAN ecosystems, paving the way for more accessible and efficient edge AI ecosystems.