Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling

Terahertz (THz) communications are envisioned as a promising technology for 6G and beyond wireless systems, providing ultra-broad bandwidth and thus Terabit-per-second (Tbps) data rates. However, as foundation of designing THz communications, channel modeling and characterization are fundamental to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, Zhengdong, Li, Yuanbo, Han, Chong
Format: Artikel
Sprache:eng
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Hu, Zhengdong
Li, Yuanbo
Han, Chong
description Terahertz (THz) communications are envisioned as a promising technology for 6G and beyond wireless systems, providing ultra-broad bandwidth and thus Terabit-per-second (Tbps) data rates. However, as foundation of designing THz communications, channel modeling and characterization are fundamental to scrutinize the potential of the new spectrum. Relied on physical measurements, traditional statistical channel modeling methods suffer from the problem of low accuracy with the assumed certain distributions and empirical parameters. Moreover, it is time-consuming and expensive to acquire extensive channel measurement in the THz band. In this paper, a transfer generative adversarial network (T-GAN) based modeling method is proposed in the THz band, which exploits the advantage of GAN in modeling the complex distribution, and the benefit of transfer learning in transferring the knowledge from a source task to improve generalization about the target task with limited training data. Specifically, to start with, the proposed GAN is pre-trained using the simulated dataset, generated by the standard channel model from 3rd generation partnerships project (3GPP). Furthermore, by transferring the knowledge and fine-tuning the pre-trained GAN, the T-GAN is developed by using the THz measured dataset with a small amount. Experimental results reveal that the distribution of PDPs generated by the proposed T-GAN method shows good agreement with measurement. Moreover, T-GAN achieves good performance in channel modeling, with 9 dB improved root-mean-square error (RMSE) and higher Structure Similarity Index Measure (SSIM), compared with traditional 3GPP method.
doi_str_mv 10.48550/arxiv.2301.00981
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2301_00981</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2301_00981</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-4b51ffcf836112cf6d7fe40098716ed896863611d22ed353ca353966a3ee2cdf3</originalsourceid><addsrcrecordid>eNotjz1PwzAYhL0woMIPYMIjDAn-SBxnjCIISKUIyXv0Nn5NLYKL7Ch8_Hqa0uVuuNPpHkKuOMsLXZbsDuK3n3MhGc8ZqzU_J68mQkgOI-0wYITJz0gbO2NMED2MdIPT1z6-J3pjsq7Z3GZbSGipOXR3GKdf2u4gBBzp897i6MPbBTlzMCa8PPmKmId70z5m65fuqW3WGaiKZ8W25M4NTkvFuRicspXDYjlVcYVW10qrJbJCoJWlHOAgtVIgEcVgnVyR6__ZI1P_Gf0HxJ9-YeuPbPIPIVZJFg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling</title><source>arXiv.org</source><creator>Hu, Zhengdong ; Li, Yuanbo ; Han, Chong</creator><creatorcontrib>Hu, Zhengdong ; Li, Yuanbo ; Han, Chong</creatorcontrib><description>Terahertz (THz) communications are envisioned as a promising technology for 6G and beyond wireless systems, providing ultra-broad bandwidth and thus Terabit-per-second (Tbps) data rates. However, as foundation of designing THz communications, channel modeling and characterization are fundamental to scrutinize the potential of the new spectrum. Relied on physical measurements, traditional statistical channel modeling methods suffer from the problem of low accuracy with the assumed certain distributions and empirical parameters. Moreover, it is time-consuming and expensive to acquire extensive channel measurement in the THz band. In this paper, a transfer generative adversarial network (T-GAN) based modeling method is proposed in the THz band, which exploits the advantage of GAN in modeling the complex distribution, and the benefit of transfer learning in transferring the knowledge from a source task to improve generalization about the target task with limited training data. Specifically, to start with, the proposed GAN is pre-trained using the simulated dataset, generated by the standard channel model from 3rd generation partnerships project (3GPP). Furthermore, by transferring the knowledge and fine-tuning the pre-trained GAN, the T-GAN is developed by using the THz measured dataset with a small amount. Experimental results reveal that the distribution of PDPs generated by the proposed T-GAN method shows good agreement with measurement. Moreover, T-GAN achieves good performance in channel modeling, with 9 dB improved root-mean-square error (RMSE) and higher Structure Similarity Index Measure (SSIM), compared with traditional 3GPP method.</description><identifier>DOI: 10.48550/arxiv.2301.00981</identifier><language>eng</language><creationdate>2023-01</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2301.00981$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2301.00981$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hu, Zhengdong</creatorcontrib><creatorcontrib>Li, Yuanbo</creatorcontrib><creatorcontrib>Han, Chong</creatorcontrib><title>Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling</title><description>Terahertz (THz) communications are envisioned as a promising technology for 6G and beyond wireless systems, providing ultra-broad bandwidth and thus Terabit-per-second (Tbps) data rates. However, as foundation of designing THz communications, channel modeling and characterization are fundamental to scrutinize the potential of the new spectrum. Relied on physical measurements, traditional statistical channel modeling methods suffer from the problem of low accuracy with the assumed certain distributions and empirical parameters. Moreover, it is time-consuming and expensive to acquire extensive channel measurement in the THz band. In this paper, a transfer generative adversarial network (T-GAN) based modeling method is proposed in the THz band, which exploits the advantage of GAN in modeling the complex distribution, and the benefit of transfer learning in transferring the knowledge from a source task to improve generalization about the target task with limited training data. Specifically, to start with, the proposed GAN is pre-trained using the simulated dataset, generated by the standard channel model from 3rd generation partnerships project (3GPP). Furthermore, by transferring the knowledge and fine-tuning the pre-trained GAN, the T-GAN is developed by using the THz measured dataset with a small amount. Experimental results reveal that the distribution of PDPs generated by the proposed T-GAN method shows good agreement with measurement. Moreover, T-GAN achieves good performance in channel modeling, with 9 dB improved root-mean-square error (RMSE) and higher Structure Similarity Index Measure (SSIM), compared with traditional 3GPP method.</description><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotjz1PwzAYhL0woMIPYMIjDAn-SBxnjCIISKUIyXv0Nn5NLYKL7Ch8_Hqa0uVuuNPpHkKuOMsLXZbsDuK3n3MhGc8ZqzU_J68mQkgOI-0wYITJz0gbO2NMED2MdIPT1z6-J3pjsq7Z3GZbSGipOXR3GKdf2u4gBBzp897i6MPbBTlzMCa8PPmKmId70z5m65fuqW3WGaiKZ8W25M4NTkvFuRicspXDYjlVcYVW10qrJbJCoJWlHOAgtVIgEcVgnVyR6__ZI1P_Gf0HxJ9-YeuPbPIPIVZJFg</recordid><startdate>20230103</startdate><enddate>20230103</enddate><creator>Hu, Zhengdong</creator><creator>Li, Yuanbo</creator><creator>Han, Chong</creator><scope>GOX</scope></search><sort><creationdate>20230103</creationdate><title>Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling</title><author>Hu, Zhengdong ; Li, Yuanbo ; Han, Chong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-4b51ffcf836112cf6d7fe40098716ed896863611d22ed353ca353966a3ee2cdf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Hu, Zhengdong</creatorcontrib><creatorcontrib>Li, Yuanbo</creatorcontrib><creatorcontrib>Han, Chong</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hu, Zhengdong</au><au>Li, Yuanbo</au><au>Han, Chong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling</atitle><date>2023-01-03</date><risdate>2023</risdate><abstract>Terahertz (THz) communications are envisioned as a promising technology for 6G and beyond wireless systems, providing ultra-broad bandwidth and thus Terabit-per-second (Tbps) data rates. However, as foundation of designing THz communications, channel modeling and characterization are fundamental to scrutinize the potential of the new spectrum. Relied on physical measurements, traditional statistical channel modeling methods suffer from the problem of low accuracy with the assumed certain distributions and empirical parameters. Moreover, it is time-consuming and expensive to acquire extensive channel measurement in the THz band. In this paper, a transfer generative adversarial network (T-GAN) based modeling method is proposed in the THz band, which exploits the advantage of GAN in modeling the complex distribution, and the benefit of transfer learning in transferring the knowledge from a source task to improve generalization about the target task with limited training data. Specifically, to start with, the proposed GAN is pre-trained using the simulated dataset, generated by the standard channel model from 3rd generation partnerships project (3GPP). Furthermore, by transferring the knowledge and fine-tuning the pre-trained GAN, the T-GAN is developed by using the THz measured dataset with a small amount. Experimental results reveal that the distribution of PDPs generated by the proposed T-GAN method shows good agreement with measurement. Moreover, T-GAN achieves good performance in channel modeling, with 9 dB improved root-mean-square error (RMSE) and higher Structure Similarity Index Measure (SSIM), compared with traditional 3GPP method.</abstract><doi>10.48550/arxiv.2301.00981</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2301.00981
ispartof
issn
language eng
recordid cdi_arxiv_primary_2301_00981
source arXiv.org
title Transfer Generative Adversarial Networks (T-GAN)-based Terahertz Channel Modeling
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T14%3A10%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Transfer%20Generative%20Adversarial%20Networks%20(T-GAN)-based%20Terahertz%20Channel%20Modeling&rft.au=Hu,%20Zhengdong&rft.date=2023-01-03&rft_id=info:doi/10.48550/arxiv.2301.00981&rft_dat=%3Carxiv_GOX%3E2301_00981%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true