Interplanetary communication presents a unique set of challenges that are rarely encountered in terrestrial networking environments. These include extreme transmission delays, intermittent connectivity, and dynamically evolving network topologies resulting from planetary motion and space weather conditions. This technical study introduces a novel Artificial Intelligence (AI)-driven approach that addresses these challenges through the integration of Delay-Tolerant Networking (DTN) principles with hybrid satellite architectures, specifically tailored for deep-space data exchange. The proposed framework leverages advanced machine learning algorithms to enable dynamic and adaptive routing strategies capable of mitigating variable delays and network disruptions. By continuously analyzing link stability and delay patterns, the AI component intelligently reroutes data packets across ground stations and relay satellites to ensure continuity in communication between planetary nodes. To evaluate the performance of the AI-enhanced DTN model, a set of simulated scenarios representing Earth-Mars and Earth-Moon communication environments was developed. These scenarios were benchmarked against conventional DTN protocols using high-fidelity network simulation tools. Key performance metrics such as delivery ratio, end-to-end latency, and network resource utilization were measured. The findings reveal that the AI-augmented system significantly outperforms traditional routing techniques, offering enhanced reliability and efficiency in interplanetary data transmission. Overall, the research demonstrates the viability of incorporating AI into space networking protocols. It sets the foundation for future autonomous deep-space missions, where intelligent communication systems will be essential to maintain robust links across vast and unpredictable cosmic distances.

Keywords: Interplanetary Internet, AI- grounded routing, Delay- Tolerant Networking( DTN), satellite networks, space communication, network simulation