OptiRoute LSTM: A New Framework for Efficient Predictive Inter-Satellite Routing

Satellite networks are one of the most important components that fulfill the world’s need for connectivity. To ensure that communication is efficient and reliable, robust routing algorithms are a must. Because, although it is true that certain routing characteristics may not be permanently and continuously flawless, a routing technique must effectively adapt to modifications in such network characteristics. The new routing method uses a Long Short-Term Memory (LSTM) model to manage dynamic metrics for Low Earth Orbit satellite networks. This LSTM model is aimed at predicting the optimal routing direction on the premise that a satellite is soon to be, by looking back through old satellite position data. Through simulation and analysis, the upgraded algorithm with LSTM prediction brought large profit in network efficiency, which includes lowering end-to-end delay (reduction of average packet life time) and raising throughput. These results underscore just how important is this research into satellite networks.

I. Introduction

The ever-increasing demand for ubiquitous connectivity and coverage are fueling the development of satellite-based Non-Terrestrial Network (NTN) as an effective supplementary solution to existing terrestrial networks in providing services over uncovered or under-served geographical areas. The uniqueness of satellite networks lie in their capability to provide wide coverage and connectivity over the regions that are expensive or difficult to cover with terrestrial networks (i.e., rural areas, vessels, airplanes, deserts etc.). Given the reliance of the world economy on satellite networks, having a fast, reliable, and efficient connection is one of the most important requirements of the network [1]. Routing algorithms, which design the path through which packets are routed from source to destination, thus become an important constraint in satellite networks [2].