2020년 컴퓨터종합학술대회
Current Result Document :
| 한글제목(Korean Title) |
Channel Prediction in Vehicular Networks: A Gaussian Process Regression-Based Approach |
| 영문제목(English Title) |
Channel Prediction in Vehicular Networks: A Gaussian Process Regression-Based Approach |
| 저자(Author) |
Madyan Alsenwi
Shashi Raj Pandey
Choong Seong Hong
|
| 원문수록처(Citation) |
VOL 47 NO. 01 PP. 1019 ~ 1021 (2020. 07) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Achieving reliable estimates of wireless channels is a key enabler for ultra-reliable low latency communications in 5G and beyond. Due to the highly dynamic nature of vehicular networks, getting prior knowledge about the wireless channels is challenging. In this paper, we propose a channel prediction model to obtain a real-time knowledge about the wireless channels in vehicular networks. Specifically, a Gaussian Process Regression (GPR) based framework is developed that can estimate the statistical channel gain of each V2V link in a distributed manner. Simulation results validate the performance of the proposed approach. In particular, the results show that the proposed GPR model is able to provide robust predictions under uncertainty and hence a reliable channel estimation can be achieved which enhances the transmission performance over the V2V links. |
| 키워드(Keyword) |
Channel prediction
GPR
V2V communications
URLLC
5G.
|
| 파일첨부 |
PDF 다운로드
|
