The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
L'acquisition d'informations sur l'état du canal (CSI) côté émetteur constitue un défi majeur dans les systèmes MIMO massifs pour permettre des transmissions à haut rendement. Pour résoudre ce problème, divers schémas de rétroaction CSI ont été proposés, notamment des schémas de rétroaction limités avec une quantification vectorielle basée sur un livre de codes et une rétroaction explicite de matrice de canal. En raison des limitations de la capacité du canal de rétroaction, un problème commun à ces schémas est la représentation efficace du CSI avec un nombre limité de bits côté récepteur et sa reconstruction précise basée sur les bits de rétroaction du récepteur côté émetteur. Récemment, inspirées par des applications réussies dans de nombreux domaines, les technologies d'apprentissage profond (DL) pour l'acquisition de CSI ont suscité un intérêt considérable de la part des chercheurs universitaires et industriels. Compte tenu du mécanisme de rétroaction pratique des réseaux New Radio (NR) de 5e génération (5G), nous proposons respectivement deux schémas de mise en œuvre de l'intelligence artificielle pour CSI (AI4CSI), le récepteur basé sur DL et la conception de bout en bout. Les schémas AI4CSI proposés ont été évalués dans les réseaux 5G NR en termes d'efficacité spectrale (SE), de surcharge de rétroaction et de complexité de calcul, et comparés aux schémas existants. Pour démontrer si ces schémas peuvent être utilisés dans des scénarios réels, nos enquêtes ont utilisé à la fois les données de canaux modélisées et les canaux mesurés pratiquement. Lorsque l'acquisition CSI basée sur DL est appliquée uniquement au récepteur, ce qui a peu d'impact sur l'interface radio, elle fournit un gain SE d'environ 25 % à un niveau de surcharge de rétroaction modéré. Il est possible de le déployer dans les réseaux 5G actuels lors des évolutions 5G. Pour les améliorations CSI de bout en bout basées sur DL, les évaluations ont également démontré leur gain de performances supplémentaire sur SE, qui est de 6 à 26 % par rapport aux récepteurs basés sur DL et de 33 à 58 % par rapport aux schémas CSI existants. Compte tenu de son impact important sur la conception des interfaces aériennes, il s’agira d’une technologie candidate pour les réseaux de 6e génération (6G), dans lesquels une interface aérienne conçue par l’intelligence artificielle peut être utilisée.
Xin WANG
DOCOMO Beijing Communications Laboratories, Co. Ltd.
Xiaolin HOU
DOCOMO Beijing Communications Laboratories, Co. Ltd.
Lan CHEN
DOCOMO Beijing Communications Laboratories, Co. Ltd.
Yoshihisa KISHIYAMA
NTT DOCOMO, INC.
Takahiro ASAI
NTT DOCOMO, INC.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Xin WANG, Xiaolin HOU, Lan CHEN, Yoshihisa KISHIYAMA, Takahiro ASAI, "Deep Learning-Based Massive MIMO CSI Acquisition for 5G Evolution and 6G" in IEICE TRANSACTIONS on Communications,
vol. E105-B, no. 12, pp. 1559-1568, December 2022, doi: 10.1587/transcom.2022EBP3009.
Abstract: Channel state information (CSI) acquisition at the transmitter side is a major challenge in massive MIMO systems for enabling high-efficiency transmissions. To address this issue, various CSI feedback schemes have been proposed, including limited feedback schemes with codebook-based vector quantization and explicit channel matrix feedback. Owing to the limitations of feedback channel capacity, a common issue in these schemes is the efficient representation of the CSI with a limited number of bits at the receiver side, and its accurate reconstruction based on the feedback bits from the receiver at the transmitter side. Recently, inspired by successful applications in many fields, deep learning (DL) technologies for CSI acquisition have received considerable research interest from both academia and industry. Considering the practical feedback mechanism of 5th generation (5G) New radio (NR) networks, we propose two implementation schemes for artificial intelligence for CSI (AI4CSI), the DL-based receiver and end-to-end design, respectively. The proposed AI4CSI schemes were evaluated in 5G NR networks in terms of spectrum efficiency (SE), feedback overhead, and computational complexity, and compared with legacy schemes. To demonstrate whether these schemes can be used in real-life scenarios, both the modeled-based channel data and practically measured channels were used in our investigations. When DL-based CSI acquisition is applied to the receiver only, which has little air interface impact, it provides approximately 25% SE gain at a moderate feedback overhead level. It is feasible to deploy it in current 5G networks during 5G evolutions. For the end-to-end DL-based CSI enhancements, the evaluations also demonstrated their additional performance gain on SE, which is 6%-26% compared with DL-based receivers and 33%-58% compared with legacy CSI schemes. Considering its large impact on air-interface design, it will be a candidate technology for 6th generation (6G) networks, in which an air interface designed by artificial intelligence can be used.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBP3009/_p
Copier
@ARTICLE{e105-b_12_1559,
author={Xin WANG, Xiaolin HOU, Lan CHEN, Yoshihisa KISHIYAMA, Takahiro ASAI, },
journal={IEICE TRANSACTIONS on Communications},
title={Deep Learning-Based Massive MIMO CSI Acquisition for 5G Evolution and 6G},
year={2022},
volume={E105-B},
number={12},
pages={1559-1568},
abstract={Channel state information (CSI) acquisition at the transmitter side is a major challenge in massive MIMO systems for enabling high-efficiency transmissions. To address this issue, various CSI feedback schemes have been proposed, including limited feedback schemes with codebook-based vector quantization and explicit channel matrix feedback. Owing to the limitations of feedback channel capacity, a common issue in these schemes is the efficient representation of the CSI with a limited number of bits at the receiver side, and its accurate reconstruction based on the feedback bits from the receiver at the transmitter side. Recently, inspired by successful applications in many fields, deep learning (DL) technologies for CSI acquisition have received considerable research interest from both academia and industry. Considering the practical feedback mechanism of 5th generation (5G) New radio (NR) networks, we propose two implementation schemes for artificial intelligence for CSI (AI4CSI), the DL-based receiver and end-to-end design, respectively. The proposed AI4CSI schemes were evaluated in 5G NR networks in terms of spectrum efficiency (SE), feedback overhead, and computational complexity, and compared with legacy schemes. To demonstrate whether these schemes can be used in real-life scenarios, both the modeled-based channel data and practically measured channels were used in our investigations. When DL-based CSI acquisition is applied to the receiver only, which has little air interface impact, it provides approximately 25% SE gain at a moderate feedback overhead level. It is feasible to deploy it in current 5G networks during 5G evolutions. For the end-to-end DL-based CSI enhancements, the evaluations also demonstrated their additional performance gain on SE, which is 6%-26% compared with DL-based receivers and 33%-58% compared with legacy CSI schemes. Considering its large impact on air-interface design, it will be a candidate technology for 6th generation (6G) networks, in which an air interface designed by artificial intelligence can be used.},
keywords={},
doi={10.1587/transcom.2022EBP3009},
ISSN={1745-1345},
month={December},}
Copier
TY - JOUR
TI - Deep Learning-Based Massive MIMO CSI Acquisition for 5G Evolution and 6G
T2 - IEICE TRANSACTIONS on Communications
SP - 1559
EP - 1568
AU - Xin WANG
AU - Xiaolin HOU
AU - Lan CHEN
AU - Yoshihisa KISHIYAMA
AU - Takahiro ASAI
PY - 2022
DO - 10.1587/transcom.2022EBP3009
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E105-B
IS - 12
JA - IEICE TRANSACTIONS on Communications
Y1 - December 2022
AB - Channel state information (CSI) acquisition at the transmitter side is a major challenge in massive MIMO systems for enabling high-efficiency transmissions. To address this issue, various CSI feedback schemes have been proposed, including limited feedback schemes with codebook-based vector quantization and explicit channel matrix feedback. Owing to the limitations of feedback channel capacity, a common issue in these schemes is the efficient representation of the CSI with a limited number of bits at the receiver side, and its accurate reconstruction based on the feedback bits from the receiver at the transmitter side. Recently, inspired by successful applications in many fields, deep learning (DL) technologies for CSI acquisition have received considerable research interest from both academia and industry. Considering the practical feedback mechanism of 5th generation (5G) New radio (NR) networks, we propose two implementation schemes for artificial intelligence for CSI (AI4CSI), the DL-based receiver and end-to-end design, respectively. The proposed AI4CSI schemes were evaluated in 5G NR networks in terms of spectrum efficiency (SE), feedback overhead, and computational complexity, and compared with legacy schemes. To demonstrate whether these schemes can be used in real-life scenarios, both the modeled-based channel data and practically measured channels were used in our investigations. When DL-based CSI acquisition is applied to the receiver only, which has little air interface impact, it provides approximately 25% SE gain at a moderate feedback overhead level. It is feasible to deploy it in current 5G networks during 5G evolutions. For the end-to-end DL-based CSI enhancements, the evaluations also demonstrated their additional performance gain on SE, which is 6%-26% compared with DL-based receivers and 33%-58% compared with legacy CSI schemes. Considering its large impact on air-interface design, it will be a candidate technology for 6th generation (6G) networks, in which an air interface designed by artificial intelligence can be used.
ER -