A Novel Framework for Proactive Cnf Orchestration in 6G Ntn

The increasing complexity of 5G and beyond networks, particularly with the integration of Non-Terrestrial Networks (NTNs), demands more dynamic and intelligent approaches to Radio Access Network (RAN) optimization. This paper presents a novel framework for closed-loop NTN RAN optimization centered on proactive Containerized Network Function (CNF) orchestration. By leveraging Artificial Intelligence (AI) to anticipate virtual resource needs, the proposed framework enables efficient, real-time deployment and scaling of CNFs, significantly enhancing the resilience and adaptability of NTN systems. Our architecture leverages Machine Learning to predict crucial metrics such as CPU usage, memory, and bandwidth, and pre-allocate virtual resources, thereby reducing latency associated with reactive orchestration methods. This proactive approach ensures optimal allocation of limited NTN resources, improves network performance, and mitigates cold-start delays of containers. Through experimental analysis of AI-based forecasting models, our work proposes a proactive framework for CNF orchestration, demonstrating its potential to enable sustainable, scalable, and efficient CNF optimization tailored for 6G NTN solutions.