ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Path Loss Model Based on Machine Learning Using Multi-Dimensional Gaussian Process Regression
Cited 7 time in scopus Download 95 time Share share facebook twitter linkedin kakaostory
Authors
Ki Joung Jang, Sejun Park, Junseok Kim, Youngkeun Yoon, Chung-Sup Kim, Young-Jun Chong, Ganguk Hwang
Issue Date
2022-11
Citation
IEEE Access, v.10, pp.115061-115073
ISSN
2169-3536
Publisher
IEEE
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1109/ACCESS.2022.3217912
Project Code
22HH2700, Development of time-space based spectrum engineering technologies for the preemptive using of frequency, Chong Young Jun
Abstract
For beyond fifth-generation (5G) and future wireless communications, spatial consistency that represents the correlation between propagation channel characteristics in close proximity has become one of the major issues in channel modeling to describe channels more realistically in emerging scenarios such as device-to-device (D2D). In this paper, we propose a novel path loss model based on multi-dimensional Gaussian process regression (GPR) that gives spatial consistency to channels in propagation environment by predicting local shadow fading while fitting large-scale path loss from measured data. The proposed model has a special structure consisting of a radial mean function and a local shadow fading term. In contrast to the log-distance path loss model and other regression-based approaches, the special structure of the proposed model provides good spatial consistency. Moreover, since the proposed model is based on GPR, it provides the uncertainty of the predicted path loss. We validate the performance of the proposed model in terms of prediction accuracy with the measurement datasets from two different indoor environments. Our experiments show that the proposed model predicts better than the log-distance path loss model, especially when spatial correlation gets more significant. The proposed model can be also used to simulate path loss in a general environment after training the measurement data.
KSP Keywords
Channel Characteristics, Channel modeling, Device to Device(D2D), Fifth Generation(5G), Gaussian process regression, Indoor Environment, Prediction accuracy, Propagation Channel, Proposed model, Regression-based, Spatial consistency
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
CC BY