Building AI Service Repositories for On-Demand Service Orchestration in 6G AI-RAN

2025-04-13

AI Summary

Current AI service orchestration in 6G AI-RAN lacks a structured service repository and environment-adaptation mechanisms. Method: This paper proposes the first plug-and-play AI service warehouse framework tailored for AI-RAN. It (1) systematically identifies key attributes of context-aware orchestration across air-interface, edge, and cloud layers; (2) designs an open-source LLM-assisted toolchain enabling automated AI service packaging, containerization, and infrastructure-aware runtime performance profiling; and (3) supports cross-domain dynamic orchestration decisions. Contribution/Results: We introduce the first reusable, production-deployable AI service asset library for AI-RAN and empirically validate that infrastructure-specific performance modeling significantly improves orchestration efficiency. In the Cranfield case study, manual coding effort was substantially reduced, confirming the framework’s practical effectiveness.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Efficient ML / Green AI
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Efficient orchestration of AI services in 6G AI-RAN requires well-structured, ready-to-deploy AI service repositories combined with orchestration methods adaptive to diverse runtime contexts across radio access, edge, and cloud layers. Current literature lacks comprehensive frameworks for constructing such repositories and generally overlooks key practical orchestration factors. This paper systematically identifies and categorizes critical attributes influencing AI service orchestration in 6G networks and introduces an open-source, LLM-assisted toolchain that automates service packaging, deployment, and runtime profiling. We validate the proposed toolchain through the Cranfield AI Service repository case study, demonstrating significant automation benefits, reduced manual coding efforts, and the necessity of infrastructure-specific profiling, paving the way for more practical orchestration frameworks.

Problem

• Lack of frameworks for AI service repositories in 6G AI-RAN
• Overlooking practical orchestration factors in current literature
• Need for automated AI service packaging and deployment tools

Innovation

• LLM-assisted toolchain automates service packaging
• Open-source solution for AI service repositories
• Infrastructure-specific profiling for 6G AI-RAN