A Routing Method with Link Information-based Rule Selection in Non-Terrestrial Networks

Non-terrestrial networks (NTN) are a promising approach in beyond 5G/6G era to provide ubiquitous connectivity to everywhere, including uncovered or underserved areas. NTN enables covering wide areas from the sky by employing satellites and unmanned aerial vehicles (UAVs) as movable network nodes such as base stations and routers. In contrast, the node mobility of NTN introduces dynamic changes in the network topology, which decreases the opportunities and duration of NTN-ground communication. In addition, dynamic changes in the communication environment, such as weather, cause link quality and availability to fluctuate. Therefore, NTN brings challenges in keeping the packet delivery rate high due to its dynamic changes in topology and communication environment. This paper proposes a routing method with link information-based path calculation rule selection in NTN. The proposed method calculates paths according to the rules selected by the link information-based rule selection model using machine learning (ML). The rule selection model is trained with the dataset based on simulations of various training scenarios of an NTN. Simulation results for two evaluation scenarios demonstrate that the proposed method outperforms the existing routing methods in terms of packet delivery rate even under severe weather conditions. The results also show that each of the multiple path calculation rules contributes to increasing the packet delivery rate.