1 Title

AI Service Platform with O-RAN Toward AI-RAN

Abstract : As 5G commercialization and 6G research accelerate, high-frequency bands are becoming the mainstream spectrum for future communications, emphasizing the critical role of AI in network optimization and decision-making. This study proposes the Distributed MLOps Management Platform (DMMP) to integrate MLOps into the 6G network system, enabling automated model deployment, monitoring, and optimization while exploring its feasibility with O-RAN. Leveraging a subscription-based architecture, DMMP interacts with third-party AI/ML platforms to support power forecasting and network function scheduling, demonstrating high scalability and dynamic orchestration. Its core features include scalable edge model deployment and version management, enhancing AI-RAN’s real-time scheduling and stability in dynamic environments. By integrating with O-RAN, DMMP further strengthens AI-RAN capabilities, laying a robust foundation for the communications industry as it advances into the 6G era.