GRU-Based MCS Selection for UAV Communication in 5G Environment

This paper proposes a modulation and coding scheme (MCS) selection method using Gated Recurrent Unit (GRU) to improve the transmission speed and communication quality between Unmanned Aerial Vehicles (UAVs) and ground stations in the 5G NR (New Radio) environment. The proposed system assumes a Time Division Duplex (TDD) mode and measures the Signal-to-Noise Ratio (SNR) at the receiver. The proposed method predicts the SNR at future transmission points based on the measured channel information using GRU, and then selects the MCS level accordingly. Simulation results show that the proposed GRU-based MCS selection outperforms conventional methods such as the average methods, recent-value method, and Convolutional Neural Network (CNN) model in terms of lower communication outage probability and higher transmission speed across all speeds. Thus, it can contribute to enhancing communication performance in 5G UAV communication environments.