In this paper, we propose a graph convolutional network (GCN)-based cooperative localization method for 5G mobile networks using round-trip time (RTT) and angle of arrival (AoA) measurements. Implemented in an Urban Macrocell (UMa) scenario with non-line-of-sight (NLOS) conditions and high measurement noise, our approach enhances localization accuracy and reduces computational complexity. Compared with existing cooperative and non-cooperative methods, our simulation results demonstrate that the proposed method satisfies the 3GPP Release 17 requirements, achieving a horizontal accuracy of less than 0.94 m for 90% of user equipments (UEs) and a computational time of 0.60 ms even in non-line of sight (NLOS) environments. This method leverages sidelink-positioning reference signals (SLPRS) to facilitate device-to-device positioning without base station communication, proving effective in challenging environments.
GCN-based Cooperative Localization using Sidelink Communication in 3GPP Urban Environment
2024-10-07
1251892 byte
Conference paper
Electronic Resource
English
Throughput Performance of 3GPP LTE System in Railway Environment
British Library Conference Proceedings | 2017
|European Patent Office | 2022
|