Deep Unfolding WMMSE Algorithm and Architecture Co-design for Relay-assisted Carrier Aggregation and MU-MIMO Systems

Low latency and high throughput are critical to enhance immersive Extended Reality (XR) experiences. To overcome the limitations of XR devices' battery and antenna constraints, we investigate a relay-assisted carrier aggregation (RACA) system that transmits data across two frequency bands. Howe...

Full description

Saved in:
Bibliographic Details
Published in:IEEE International Symposium on Circuits and Systems proceedings pp. 1 - 5
Main Authors: Chen, Chi-Wei, Liu, Shu-Kae, Wu, An-Yeu Andy
Format: Conference Proceeding
Language:English
Published: IEEE 25.05.2025
Subjects:
carrier aggregation
Convergence
deep unfolding
Engines
Hardware
MU-MIMO
Optimization
Pipelines
Program processors
Relay
Relays
Throughput
Transforms
Transmitting antennas
WMMSE
ISSN:2158-1525
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Low latency and high throughput are critical to enhance immersive Extended Reality (XR) experiences. To overcome the limitations of XR devices' battery and antenna constraints, we investigate a relay-assisted carrier aggregation (RACA) system that transmits data across two frequency bands. However, the iterative weighted minimum mean square error (WMMSE) algorithm used for maximizing data rate incurs long latency. To address this, we propose a deep unfolding WMMSE (UWMMSE) with trainable step sizes in each layer to accelerate convergence via gradient descent. Furthermore, we reschedule serial updates into parallel updates, omit a less-sensitive precoder update for balanced computation, and develop hardware-friendly approximations to simplify matrix inversion and square root operations. To satisfy real-time communication, we implement the first dual-mode UWMMSE hardware engine with folding and pipeline techniques that reduces area by 75% compared to direct mapping and supports MU-MIMO precoder optimization. This engine achieves 1.3x higher hardware efficiency than prior generalized eigenvalue decomposition (GEVD)-based MU-MIMO processors, completing 4 iterations of UWMMSE within 0.4 µs.
AbstractList Low latency and high throughput are critical to enhance immersive Extended Reality (XR) experiences. To overcome the limitations of XR devices' battery and antenna constraints, we investigate a relay-assisted carrier aggregation (RACA) system that transmits data across two frequency bands. However, the iterative weighted minimum mean square error (WMMSE) algorithm used for maximizing data rate incurs long latency. To address this, we propose a deep unfolding WMMSE (UWMMSE) with trainable step sizes in each layer to accelerate convergence via gradient descent. Furthermore, we reschedule serial updates into parallel updates, omit a less-sensitive precoder update for balanced computation, and develop hardware-friendly approximations to simplify matrix inversion and square root operations. To satisfy real-time communication, we implement the first dual-mode UWMMSE hardware engine with folding and pipeline techniques that reduces area by 75% compared to direct mapping and supports MU-MIMO precoder optimization. This engine achieves 1.3x higher hardware efficiency than prior generalized eigenvalue decomposition (GEVD)-based MU-MIMO processors, completing 4 iterations of UWMMSE within 0.4 µs.
Author Liu, Shu-Kae
Wu, An-Yeu Andy
Chen, Chi-Wei
Author_xml – sequence: 1
  givenname: Chi-Wei
  surname: Chen
  fullname: Chen, Chi-Wei
  email: wilbur@access.ee.ntu.edu.tw
  organization: Graduate Institute of Electrical Engineering, National Taiwan University,Taipei,Taiwan
– sequence: 2
  givenname: Shu-Kae
  surname: Liu
  fullname: Liu, Shu-Kae
  email: jasonliu@access.ee.ntu.edu.tw
  organization: Graduate Institute of Electrical Engineering, National Taiwan University,Taipei,Taiwan
– sequence: 3
  givenname: An-Yeu Andy
  surname: Wu
  fullname: Wu, An-Yeu Andy
  email: andywu@ntu.edu.tw
  organization: Graduate Institute of Electrical Engineering, National Taiwan University,Taipei,Taiwan
BookMark eNo1kMtOwzAUBQ0CCVr6Byz8Ayl-xHa8jEKBSo0qESqWlRvfpEapU9lm0b-nvFZHGh3NYiboyo8eEMKUzCkl-mHZVGUjJFFszggT3zDnXBQXaKaVLrggXMiCk0t0y6goMiqYuEGTGD8IYYRIdovSI8ARb3w3Dtb5Hr_XdbPA5dCPwaX9ARtvcRnavUvQps8AuBozC9H1HndjwK8wmFNmYnQxgcWVCcFBwGXfB-hNcqP_MdSbrF7Wa9yczrdDvEPXnRkizP52ipqnxVv1kq3Wz8uqXGVO85QJq2knLdsZa4hmmipNzkgTqcDmPNeGdqawO5K3jILkTIIA1bVQ5EruFJ-i-1-rA4DtMbiDCaftfyP-BRipXg4
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ISCAS56072.2025.11043358
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350356830
EISSN 2158-1525
EndPage 5
ExternalDocumentID 11043358
Genre orig-research
GrantInformation_xml – fundername: MediaTek
  funderid: 10.13039/501100004164
– fundername: National Science and Technology Council
  funderid: 10.13039/501100020950
GroupedDBID -~X
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i93t-5d91f6d2bada09291790d919067ed4349a1fa8db04c21e6326e5e7fce8476b73
IEDL.DBID RIE
IngestDate Wed Aug 27 01:38:44 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-5d91f6d2bada09291790d919067ed4349a1fa8db04c21e6326e5e7fce8476b73
PageCount 5
ParticipantIDs ieee_primary_11043358
PublicationCentury 2000
PublicationDate 2025-May-25
PublicationDateYYYYMMDD 2025-05-25
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-May-25
  day: 25
PublicationDecade 2020
PublicationTitle IEEE International Symposium on Circuits and Systems proceedings
PublicationTitleAbbrev ISCAS
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020062
Score 2.2925735
Snippet Low latency and high throughput are critical to enhance immersive Extended Reality (XR) experiences. To overcome the limitations of XR devices' battery and...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms carrier aggregation
Convergence
deep unfolding
Engines
Hardware
MU-MIMO
Optimization
Pipelines
Program processors
Relay
Relays
Throughput
Transforms
Transmitting antennas
WMMSE
Title Deep Unfolding WMMSE Algorithm and Architecture Co-design for Relay-assisted Carrier Aggregation and MU-MIMO Systems
URI https://ieeexplore.ieee.org/document/11043358
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxQALryLe8sCaNi_b8RiFVnRIqRQqulVOfC6VIKlKisS_x3YflIGBLbIUR_JF-b7Ld98dQveKBrlhpo5HGNcJCnGNvssdpTjPiQxNTyk7bIINBtF4zIdrs7r1wgCALT6Dtrm0Wr6siqX5VdbRUBUGAYkaqMEYXZm1ttmVcQNuSnVc3ulnSZxpOGfGbeWT9ubeX1NULIj0jv75-GPU-rHj4eEWaE7QHpSn6HCnk-AZqh8A5nik3xYrJuGXNM26OH6bVjr5f33HopQ43tEMcFI50hZvYM1asSmJ-3I0jzZBlzgRCzPIDsdTnY1PbezsDunISfvpE163OW-hrNd9Th6d9UAFZ8aD2iGSe4pKPxdSuJoWmeZceolrwAIZBiEXnhKRzN2w8D2gmtgBAaYK0AhGcxaco2ZZlXCBsDDfBcUiJYGEAqKcR1TvaeZYUxpxdYla5vgm81XHjMnm5K7-WL9GByZIRpX3yQ1q1osl3KL94rOefSzubJy_AZEEqBM
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwELWgIAEXtiJ2fODqtlmcxMcotKKiKZXSit4qJ7ZLJUiqkiLx93jchXLgwC2yFCvyRHkzmXnvIXSvPCeFzJRY1Ge6QKEN6O8yohRjKRUuaEoZswm_2w2GQ9ZbktUNF0ZKaYbPZA0uTS9fFNkcfpXVNVS5jkODbbQD1lnWgq61rq-AD7ga1mmwejuJwkQDug98K5vWVnf_8lExMNI6_OcDHKHqDyEP99ZQc4y2ZH6CDja0BE9R-SDlFA_0-2LaSfgljpMmDt_GhS7_X98xzwUON7oGOCqIMOMbWOetGIbivojOpCHsAkd8BlZ2OBzrenxsomd2iAckbsfPeCl0XkVJq9mPHsnSUoFMmFMSKpilPGGnXPCGToxAnksvMQ1ZUriOy7ileCDShpvZlvR0aiep9FUmNYZ5qe-coUpe5PIcYQ5fBuUHSkjqchmkLPD0nuBk7XkBUxeoCsc3mi40M0ark7v8Y_0O7T32486o0-4-XaF9CBj06G16jSrlbC5v0G72WU4-Zrcm5t97vqta
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%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Symposium+on+Circuits+and+Systems+proceedings&rft.atitle=Deep+Unfolding+WMMSE+Algorithm+and+Architecture+Co-design+for+Relay-assisted+Carrier+Aggregation+and+MU-MIMO+Systems&rft.au=Chen%2C+Chi-Wei&rft.au=Liu%2C+Shu-Kae&rft.au=Wu%2C+An-Yeu+Andy&rft.date=2025-05-25&rft.pub=IEEE&rft.eissn=2158-1525&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FISCAS56072.2025.11043358&rft.externalDocID=11043358