Reliable Moon-Earth communication is essential for long-term human presence on the Moon. Ensuring reliable communication requires careful consideration of various factors, including the choice of communication protocols. For high-latency deep-space links, the Bundle Protocol (BP) is designed to handle disruptions. At the same time, the Artemis program envisions IP-based wireless technologies, such as Wi-Fi and mobile networks, on the lunar surface. However, since these two approaches rely on different protocol stacks, a gateway is needed to bridge IP and BP, allowing end devices to communicate seamlessly without BP awareness. This paper presents a gateway bridging IP and BP networks and evaluates three implementations based on their termination layer. Through emulated Moon-Earth communication experiments, we show that application performance varies significantly with termination layer selection, highlighting the need for mission-specific gateway design.

This paper proposes an IP forwarding information base (FIB) encoding leveraging an emerging data structure called a learned index , which uses machine learning to associate key-position pairs in a key-value store. A learned index for FIB lookups is expected to yield a more compact representation and faster lookups compared to existing FIBs based on tries or hash tables, at the cost of efficient FIB updates, which is difficult to support with a learned index. We optimize our implementation for lookup speed, exploiting that for efficient FIB lookups it is enough to approximate the key-position pairs with a piece-wise linear function, instead of having to learn the key-position pairs. The experiments using real BGP routing information snapshots suggest that the size of the proposed FIB is compact and lookup speed is sufficiently fast regardless of the length of matched prefixes.