Cognitive TN–NTN Service Orchestration with Digital Twins and Agentic AI for Resilient 6G Connectivity

Abstract

Sixth-generation (6G) communication requires seamless integration of terrestrial networks (TN) and non-terrestrial networks (NTN) to deliver reliable, intelligent, and ubiquitous connectivity. This paper presents a Cognitive TN–NTN Service Orchestration framework that combines Digital Twins and Agentic Artificial Intelligence (AI) to achieve resilient network management. Digital Twins create real-time virtual replicas of terrestrial infrastructure, satellites, UAVs, and high-altitude platforms for continuous monitoring and prediction. Agentic AI employs autonomous agents to analyze network conditions, optimize routing, perform proactive fault detection, and coordinate service migration during failures or congestion. Reinforcement Learning and Graph Neural Networks support adaptive decision-making across heterogeneous 6G environments. Experimental evaluation indicates improved latency, packet delivery ratio, service availability, orchestration efficiency, and resilience compared with conventional orchestration methods. The proposed framework enables uninterrupted communication for smart cities, autonomous transportation, disaster recovery, industrial automation, maritime networks, and remote healthcare services.