Robust WMMSE Precoder With Deep Learning Design for Massive MIMO

In this paper, we investigate the downlink robust precoding with imperfect channel state information (CSI) for massive multiple-input-multiple-output (MIMO) communications. With the estimated channel and channel error statistics, the general design of the robust precoder is to maximize the ergodic s...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on communications Ročník 71; číslo 7; s. 3963 - 3976
Hlavní autoři:	Shi, Junchao, Lu, An-An, Zhong, Wen, Gao, Xiqi, Li, Geoffrey Ye
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.07.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Antennas Channel estimation Channel models Deep learning deep learning design Downlink Ergodic processes imperfect CSI Instructional design Lower bounds Massive MIMO MIMO communication neural network Neural networks Precoding Robust WMMSE precoder Robustness Sums
ISSN:	0090-6778, 1558-0857
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In this paper, we investigate the downlink robust precoding with imperfect channel state information (CSI) for massive multiple-input-multiple-output (MIMO) communications. With the estimated channel and channel error statistics, the general design of the robust precoder is to maximize the ergodic sum rate subject to the total transmit power constraint. To make the problem more tractable, we find a lower bound of the ergodic sum rate and propose the robust weighted minimum mean-squared-error (WMMSE) precoder to maximize the bound. We characterize the structure of the precoding vectors by low-dimensional parameters, which are learned directly from the available CSI through a neural network. As such, the precoding vectors can be immediately computed without iterations. To extend the deep learning design to multi-antennas users, we present a flexible approach that allows the various antenna configurations at the user side to be handled. Simulation results show that the deep learning design can significantly reduce the computational complexity compared with the existing precoder designs while achieving near optimal performance.
AbstractList	In this paper, we investigate the downlink robust precoding with imperfect channel state information (CSI) for massive multiple-input-multiple-output (MIMO) communications. With the estimated channel and channel error statistics, the general design of the robust precoder is to maximize the ergodic sum rate subject to the total transmit power constraint. To make the problem more tractable, we find a lower bound of the ergodic sum rate and propose the robust weighted minimum mean-squared-error (WMMSE) precoder to maximize the bound. We characterize the structure of the precoding vectors by low-dimensional parameters, which are learned directly from the available CSI through a neural network. As such, the precoding vectors can be immediately computed without iterations. To extend the deep learning design to multi-antennas users, we present a flexible approach that allows the various antenna configurations at the user side to be handled. Simulation results show that the deep learning design can significantly reduce the computational complexity compared with the existing precoder designs while achieving near optimal performance.
Author	Gao, Xiqi Shi, Junchao Li, Geoffrey Ye Lu, An-An Zhong, Wen
Author_xml	– sequence: 1 givenname: Junchao orcidid: 0000-0002-6459-8908 surname: Shi fullname: Shi, Junchao email: jcshi@seu.edu.cn organization: National Mobile Communications Research Laboratory, Southeast University, Nanjing, China – sequence: 2 givenname: An-An orcidid: 0000-0003-0193-6372 surname: Lu fullname: Lu, An-An email: aalu@seu.edu.cn organization: National Mobile Communications Research Laboratory, Southeast University, Nanjing, China – sequence: 3 givenname: Wen surname: Zhong fullname: Zhong, Wen email: wzhong@seu.edu.cn organization: National Mobile Communications Research Laboratory, Southeast University, Nanjing, China – sequence: 4 givenname: Xiqi orcidid: 0000-0001-9107-6593 surname: Gao fullname: Gao, Xiqi email: xqgao@seu.edu.cn organization: National Mobile Communications Research Laboratory, Southeast University, Nanjing, China – sequence: 5 givenname: Geoffrey Ye orcidid: 0000-0002-7894-2415 surname: Li fullname: Li, Geoffrey Ye organization: Department of Electrical and Electronic Engineering, Imperial College London, London, U.K
BookMark	eNp90M9LwzAUwPEgCm7Tf0A8BDx35keTpjdlTh2sTHSyY0ja15kxm5l0gv-9ndtBPHgKD_J5D759dNz4BhC6oGRIKcmv56NZUQwZYXzImcxVmh-hHhVCJUSJ7Bj1CMlJIrNMnaJ-jCtCSEo476GbZ2-3scWLongZ46cApa8g4IVr3_AdwAZPwYTGNctuim7Z4NoHXJgY3SfgYlLMztBJbdYRzg_vAL3ej-ejx2Q6e5iMbqdJyXLZJpVJCStFbRUwaUtepYpTClJkVgkjuFW2AkY55ZDbUlAupKwzlVaWgaqJ5QN0td-7Cf5jC7HVK78NTXdSM8Uzynna4QFS-19l8DEGqHXpWtM637TBuLWmRO966Z9eetdLH3p1lP2hm-DeTfj6H13ukQOAX4CSTJKcfwNg9Xam
CODEN	IECMBT
CitedBy_id	crossref_primary_10_1109_TSP_2025_3574005 crossref_primary_10_1007_s11277_024_10919_5 crossref_primary_10_1109_TWC_2025_3541644 crossref_primary_10_3390_s24165188 crossref_primary_10_1109_LWC_2024_3483893 crossref_primary_10_1109_JSAC_2024_3460084 crossref_primary_10_1109_OJCOMS_2025_3586560 crossref_primary_10_1109_JSAC_2025_3536504
Cites_doi	10.1109/MWC.2019.1800601 10.1109/TWC.2007.360373 10.1109/TSP.2011.2147784 10.1109/TAP.2014.2310220 10.1109/LWC.2017.2757490 10.1109/LCOMM.2021.3063707 10.1109/TWC.2021.3052973 10.1109/TWC.2020.3028365 10.1109/MCOM.2014.6736761 10.1109/TWC.2020.3033334 10.1109/TWC.2010.092810.091092 10.1016/j.acha.2019.06.004 10.1109/TSP.2017.2675862 10.1007/BF02551274 10.15325/BLTJ.2015.2407793 10.1109/ICASSP39728.2021.9414561 10.1109/SPAWC.2013.6612065 10.1109/LWC.2021.3075996 10.1109/ISWCS.2012.6328433 10.1109/WCL.2012.022012.110206 10.1109/TIT.2003.817421 10.1109/T-WC.2008.070851 10.1109/TCOMM.2004.840638 10.1109/TWC.2020.3035843 10.1007/s11432-015-5390-y 10.1109/TCOMM.2021.3105569 10.1016/0893-6080(91)90009-T 10.1109/TCOMM.2019.2960361 10.1017/CBO9780511804441 10.1109/GLOCOM.2018.8647574 10.1109/TCOMM.2019.2912383
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TCOMM.2023.3269849
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-0857
EndPage	3976
ExternalDocumentID	10_1109_TCOMM_2023_3269849 10107609
Genre	orig-research
GrantInformation_xml	– fundername: National Key R&D Program of China the Jiangsu Province Basic Research Project the Key R&D Plan of Jiangsu Province the National Natural Science Foundation of China the Huawei Cooperation Project grantid: 2018YFB1801103; BK20192002; BE2022067; 61801113; 61960206006 funderid: 10.13039/501100001809
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACKIV ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD HZ~ H~9 IAAWW IBMZZ ICLAB IES IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 ZCA ZCG AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c296t-da402c5fb8e26bc3d48311e657b85a53b8bde21313e9bc513566f784db2e8f0b3
IEDL.DBID	RIE
ISICitedReferencesCount	18
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001035493400013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0090-6778
IngestDate	Mon Jun 30 08:33:15 EDT 2025 Tue Nov 18 22:20:18 EST 2025 Sat Nov 29 04:08:26 EST 2025 Wed Aug 27 02:18:06 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c296t-da402c5fb8e26bc3d48311e657b85a53b8bde21313e9bc513566f784db2e8f0b3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-6459-8908 0000-0002-7894-2415 0000-0003-0193-6372 0000-0001-9107-6593
PQID	2837133431
PQPubID	85472
PageCount	14
ParticipantIDs	proquest_journals_2837133431 ieee_primary_10107609 crossref_citationtrail_10_1109_TCOMM_2023_3269849 crossref_primary_10_1109_TCOMM_2023_3269849
PublicationCentury	2000
PublicationDate	2023-07-01
PublicationDateYYYYMMDD	2023-07-01
PublicationDate_xml	– month: 07 year: 2023 text: 2023-07-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on communications
PublicationTitleAbbrev	TCOMM
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref34 ref15 ref14 ref31 ref30 ref11 ref10 ref32 ref2 goodfellow (ref26) 2016 ref1 ref17 ref16 ref19 ref18 nair (ref27) 2010 ref24 ref23 ref25 ref20 ref22 ref21 kingma (ref33) 2015 ref28 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref8 doi: 10.1109/MWC.2019.1800601 – start-page: 1 year: 2015 ident: ref33 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Represent (ICLR) – ident: ref5 doi: 10.1109/TWC.2007.360373 – ident: ref24 doi: 10.1109/TSP.2011.2147784 – ident: ref32 doi: 10.1109/TAP.2014.2310220 – ident: ref7 doi: 10.1109/LWC.2017.2757490 – ident: ref18 doi: 10.1109/LCOMM.2021.3063707 – ident: ref11 doi: 10.1109/TWC.2021.3052973 – ident: ref31 doi: 10.1109/TWC.2020.3028365 – ident: ref2 doi: 10.1109/MCOM.2014.6736761 – ident: ref9 doi: 10.1109/TWC.2020.3033334 – ident: ref1 doi: 10.1109/TWC.2010.092810.091092 – ident: ref30 doi: 10.1016/j.acha.2019.06.004 – ident: ref21 doi: 10.1109/TSP.2017.2675862 – ident: ref28 doi: 10.1007/BF02551274 – start-page: 807 year: 2010 ident: ref27 article-title: Rectified linear units improve restricted Boltzmann machines publication-title: Proc IEEE Int Conf Mach Learn (ICML) – ident: ref3 doi: 10.15325/BLTJ.2015.2407793 – ident: ref10 doi: 10.1109/ICASSP39728.2021.9414561 – ident: ref16 doi: 10.1109/SPAWC.2013.6612065 – ident: ref19 doi: 10.1109/LWC.2021.3075996 – ident: ref25 doi: 10.1109/ISWCS.2012.6328433 – year: 2016 ident: ref26 publication-title: Deep Learning – ident: ref14 doi: 10.1109/WCL.2012.022012.110206 – ident: ref23 doi: 10.1109/TIT.2003.817421 – ident: ref6 doi: 10.1109/T-WC.2008.070851 – ident: ref4 doi: 10.1109/TCOMM.2004.840638 – ident: ref12 doi: 10.1109/TWC.2020.3035843 – ident: ref15 doi: 10.1007/s11432-015-5390-y – ident: ref20 doi: 10.1109/TCOMM.2021.3105569 – ident: ref29 doi: 10.1016/0893-6080(91)90009-T – ident: ref13 doi: 10.1109/TCOMM.2019.2960361 – ident: ref34 doi: 10.1017/CBO9780511804441 – ident: ref22 doi: 10.1109/GLOCOM.2018.8647574 – ident: ref17 doi: 10.1109/TCOMM.2019.2912383
SSID	ssj0004033
Score	2.5395923
Snippet	In this paper, we investigate the downlink robust precoding with imperfect channel state information (CSI) for massive multiple-input-multiple-output (MIMO)...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	3963
SubjectTerms	Antennas Channel estimation Channel models Deep learning deep learning design Downlink Ergodic processes imperfect CSI Instructional design Lower bounds Massive MIMO MIMO communication neural network Neural networks Precoding Robust WMMSE precoder Robustness Sums
Title	Robust WMMSE Precoder With Deep Learning Design for Massive MIMO
URI	https://ieeexplore.ieee.org/document/10107609 https://www.proquest.com/docview/2837133431
Volume	71
WOSCitedRecordID	wos001035493400013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1558-0857 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004033 issn: 0090-6778 databaseCode: RIE dateStart: 19720101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA9ueNCDnxOnU3LwJpvtkjYvN2U69NApfqC30iSvOpBtbJ1_v0na6UAUvLWQlPJ7yftI3vs9Qk4CE2uurfbjAbrTKmRtgExZgRjIMgjiXOS-2YQYDODlRd5Vxeq-FgYRffIZdtyjv8s3Yz13R2V2h4fuIknWSE0IURZrfRdBBqyinHT57AIWFTKBPHvs3SZJxzUK71hvRYIjzlyyQr6tyg9d7A1Mf_Ofv7ZFNipPkl6Uot8mKzjaIetL_IK75Px-rOazgj4nycMVvXPBr8EpfR4Wb_QScUIrdtVX--YSOaj1YGli3WmrAmlyk9w2yFP_6rF33a5aJrR1V8ZF22Q2HtRRrgC7sdLMcGBhiHEkFERZxBQog92QhQyl0lHIrDeXC-BGdRHyQLE9Uh-NR7hPqFYguLSGDSDngpvMQpkbyUGxiDPImiRcQJjqik_ctbV4T31cEcjUw5462NMK9iY5_ZozKdk0_hzdcEAvjSwxbpLWQlRpteNmqWPxsfG29YcOfpl2SNbc18tc2xapF9M5HpFV_VEMZ9Njv5g-AWuTw20
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB6xgLS7B95oy9MHbquWJHaS8Q3EQyBIQdAV3KLYngDSqkVtyu_HdlKohEDilki2En1jz8Oe-QZgLzCJFtpqPxGQO60i3kYslBWIwaLAICnT0jebSLtdvL-X102xuq-FISKffEYd9-jv8s1Aj91Rmd3hobtIkj9gLhYiCutyrfcyyIA3pJMuoz3FSY1MIPd7R1dZ1nGtwjvWX5HoqDOn7JBvrPJBG3sTc7r4zZ9bgoXGl2SHtfCXYYb6K_B7imFwFQ5uBmo8qthdlt2esGsX_hoasrun6pEdEz2zhl_1wb65VA5mfViWWYfaKkGWnWdXa_Dv9KR3dNZumia0dSSTqm0KGxHquFRIUaI0NwJ5GFISpwrjIuYKlaEo5CEnqXQccuvPlSkKoyLCMlB8HWb7gz79AaYVpkJa04ZYilSYwkJZGilQ8VhwLFoQTiDMdcMo7hpb_M99ZBHI3MOeO9jzBvYW_H2b81zzaXw5es0BPTWyxrgFWxNR5c2eG-WOx8dG3NYj2vhk2i78POtll_nlefdiE365L9WZt1swWw3HtA3z-qV6Gg13_MJ6BcXAxrQ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Robust+WMMSE+Precoder+With+Deep+Learning+Design+for+Massive+MIMO&rft.jtitle=IEEE+transactions+on+communications&rft.au=Shi%2C+Junchao&rft.au=An-An%2C+Lu&rft.au=Zhong%2C+Wen&rft.au=Gao%2C+Xiqi&rft.date=2023-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0090-6778&rft.eissn=1558-0857&rft.volume=71&rft.issue=7&rft.spage=3963&rft_id=info:doi/10.1109%2FTCOMM.2023.3269849&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0090-6778&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0090-6778&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0090-6778&client=summon