In this work, firstly we propose an artificial neural network (ANN) based channel modeling and simulation framework to playback a measurement channel to overcome the shortcomings of traditional geometry based stochastic modelling (GBSM) and simulation approach which is unable to predict a time or position-varying channel to match with real environment. Secondly, we implement the framework based on channel measurements performed at 28 GHz in a large waiting hall at Qingdao high-speed railway station, China. Thirdly, we validate the proposed framework by comparisons of the large scale channel parameters (LSCPs) and small scale channel parameters (SSCPs) extracted from the measured, ANN and GBSM simulation channels. The results show that the ANN-based framework can playback the measured channels accurately, while GBSM-based simulated channels have large deviations. This work offers a solution to playback the measured channels accurately to be used in 5G and beyond radio system research and engineering applications, while it's also able to be applied in future channel predictions in case of large amount of measured data available.
Bibliographical noteFunding Information:
Manuscript received October 1, 2019; revised January 15, 2020; accepted February 17, 2020. Date of publication June 22, 2020; date of current version August 28, 2020. This work was supported in part by the National Nature Science Foundation of China (NSFC) under Grant 61771194 and Grant 61931001, in part by the Science and Technology Project of State Grid Corporation of China under Grant SGSDDK00KJJS1900405, and in part by the Key Program of Beijing Municipal Natural Science Foundation under Grant 17L20052. (Corresponding author: Fei Du.) Xiongwen Zhao, Fei Du, Suiyan Geng, Zihao Fu, Zhongyu Wang, Yu Zhang, and Zhenyu Zhou are with the School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China (e-mail: firstname.lastname@example.org).
© 1983-2012 IEEE.
- 5G and beyond
- Position or time-varying channel
- artificial neural network
- channel modeling and simulation
- millimeter wave
- virtual array