LSTM Based Multiple Beamforming for 5G HAPS IoT Networks

This article proposes a novel 5G Internet of Things (IoT) networks with High Altitude Platform Station (HAPS) in the sky. In this proposed method, the 5G HAPS that consists of airplane and uniform rectangular array (URA) can achieve reliable connections between ground gateway (GW) and user equipments (UEs), at the same time GW requires the relative position information of the HAPS. HAPS is susceptible to various factors in the sky, resulting in system capacity reduction. Correspondingly, we propose a direction of arrival (DoA) prediction method based on the latest Long Short-Term Memory (LSTM) model to solve the above problems. Simulation results show that our approach makes a significant improvement to the 5G Internet of Things networks with High Altitude Platform Station.