CoChat
Sign Up
Cited by 49Advanced Wireless Communication TechnologiesAdvanced MIMO Systems OptimizationMillimeter-Wave Propagation and Modeling

The DOI matches its Crossref record.

Algorithm-Unrolling-Based Distributed Optimization for RIS-Assisted Cell-Free Networks

Open access
Xu, Wangyang, An, Jiancheng, Li, Hongbin, Gan, Lu, Yuen, Chau·2024·IEEE Internet of Things Journal
DOI 10.1109/jiot.2023.3288072
Open this paper in CoChat — free accountOpen PDF

Abstract

The user-centric cell-free network has emerged as an appealing technology to improve the wireless communication’s capacity of the Internet of Things (IoT) networks thanks to its ability to eliminate intercell interference effectively. However, the cell-free network inevitably brings in higher hardware cost and backhaul overhead as a larger number of base stations (BSs) are deployed. Additionally, severe channel fading in high-frequency bands constitutes another crucial issue that limits the practical application of the cell-free network. In order to address the above challenges, we amalgamate the cell-free system with another emerging technology, namely reconfigurable intelligent surface (RIS), which can provide high spectrum and energy efficiency with low hardware cost by reshaping the wireless propagation environment intelligently. To this end, we formulate a weighted sum-rate (WSR) maximization problem for RIS-assisted cell-free systems by jointly optimizing the BS precoding matrix and the RIS reflection coefficient vector. Subsequently, we transform the complicated WSR problem to a tractable optimization problem and propose a distributed cooperative alternating direction method of multipliers (ADMMs) to fully utilize parallel computing resources. Inspired by the model-based algorithm unrolling concept, we unroll our solver to a learning-based deep distributed ADMM (D2-ADMM) network framework. To improve the efficiency of the D2-ADMM in distributed BSs, we develop a monodirectional information exchange strategy with a small signaling overhead. In addition to benefiting from domain knowledge, D2-ADMM adaptively learns hyperparameters and nonconvex solvers of the intractable RIS design problem through data-driven end-to-end training. Finally, numerical results demonstrate that the proposed D2-ADMM achieves around 210% improvement in capacity compared with the distributed noncooperative algorithm and almost 96% compared with the centralized algorithm.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jiot.2023.3288072

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 59

  1. 10.1109/JIOT.2018.2792326 · DOI
  2. 10.1109/JIOT.2014.2337336 · DOI
  3. 10.1109/MNET.2019.1800418 · DOI
  4. 10.1109/MCOM.2014.6815896 · DOI
  5. 10.1109/TCOMM.2013.090513.120848 · DOI
  6. 10.1109/MCOM.2014.6736752 · DOI
  7. 10.1109/TWC.2017.2655515 · DOI
  8. 10.1109/GlobalSIP.2014.7032191 · DOI
  9. 10.1109/JSAC.2016.2544498 · DOI
  10. 10.1109/TWC.2013.090513.130142 · DOI
  11. 10.1109/MCOM.2003.1186553 · DOI
  12. 10.1109/JIOT.2020.3030675 · DOI
  13. 10.1109/TWC.2017.2698449 · DOI
  14. 10.1109/TWC.2019.2941478 · DOI
  15. 10.1109/SPAWC.2015.7227028 · DOI
  16. 10.1109/JSAC.2017.2719924 · DOI
  17. 10.12676/j.cc.2019.02.001 · DOI
  18. 10.1109/MCOM.001.1900107 · DOI
  19. 10.1109/TWC.2019.2922609 · DOI
  20. 10.1109/TCCN.2021.3128605 · DOI
  21. 10.1109/TCOMM.2021.3127924 · DOI
  22. 10.1109/LWC.2022.3176666 · DOI
  23. 10.1109/TWC.2019.2952117 · DOI
  24. 10.1109/TGCN.2019.2908228 · DOI
  25. 10.1109/TWC.2019.2948841 · DOI
  26. 10.1109/LWC.2021.3126389 · DOI
  27. 10.1109/MCOM.2018.1700199 · DOI
  28. 10.1109/TSP.2018.2812750 · DOI
  29. 10.1109/LWC.2021.3082773 · DOI
  30. 10.1109/MWC.001.1900534 · DOI
  31. 10.1109/lcomm.2023.3278683 · DOI
  32. 10.1109/jsac.2023.3288261 · DOI · Paper page
  33. 10.1109/MCOM.001.2100671 · DOI
  34. 10.1109/ICCWorkshops50388.2021.9473521 · DOI
  35. 10.1109/LCOMM.2021.3062275 · DOI
  36. 10.1109/TSP.2021.3088755 · DOI
  37. 10.1109/LWC.2020.3045884 · DOI
  38. 10.1109/TGCN.2022.3143226 · DOI · Paper page
  39. 10.1109/mwc.010.2200312 · DOI · Paper page
  40. 10.1109/TCCN.2022.3188153 · DOI
  41. 10.1109/MWC.021.2000376 · DOI
  42. 10.1109/MWC.2019.1900027 · DOI
  43. 10.1109/twc.2022.3224291 · DOI
  44. 10.1109/MSP.2020.3016905 · DOI
  45. Xin, Maximal sparsity with deep networks?, 29, 4347
  46. Liu, ALISTA: Analytic weights are as good as learned weights in LISTA, 1
  47. Chen, Theoretical linear convergence of unfolded ISTA and its practical weights and thresholds, 31, 1
  48. 10.1109/TPAMI.2018.2883941 · DOI
  49. 10.1109/JSTSP.2020.3003170 · DOI
  50. 10.1109/TCI.2020.2964202 · DOI
  51. Zhang, 2018, Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration, arXiv:1805.07709 · arXiv
  52. Hershey, 2014, Deep unfolding: Model-based inspiration of novel deep architectures, arXiv:1409.2574 · arXiv
  53. 10.1109/ICASSP.2019.8683124 · DOI
  54. 10.1109/LSP.2020.2998357 · DOI
  55. 10.1109/TSP.2018.2812748 · DOI
  56. 10.1109/TSP.2018.2812733 · DOI
  57. 10.1109/LCOMM.2019.2955442 · DOI
  58. 10.1109/JSTSP.2016.2523903 · DOI
  59. 10.1109/TWC.2020.2987027 · DOI

Cited by

Sorted by citations

See all 49

Metadata

Authors
Xu, W., An, J., Li, H., Gan, L., & Yuen, C.
Affiliations
  • University of Electronic Science and Technology of China (CN)
  • Singapore University of Technology and Design (SG)
  • Stevens Institute of Technology (US)
  • Nanyang Technological University (SG)
ORCID
Venue
IEEE Internet of Things Journal
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2024-01-01
Volume
11
Issue
1
Pages
944-957
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
DOI
10.1109/jiot.2023.3288072
OpenAlex
W4381327854
Cited by
49
References
0
Citations by year
2026: 8 · 2025: 19 · 2024: 19
FWCI
3.65
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Internet of Things Journal (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • DR-NTU (Nanyang Technological University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • Sichuan Science and Technology Program (2023YFSY0008, 2023YFG0291)
  • Ministry of Education, Singapore, through its MOE Tier 2 (MOE-T2EP50220-0019)
  • National Science Foundation (ECCS-1923739, ECCS-2212940, CCF-2316865)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced MIMO Systems Optimization
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Millimeter-Wave Propagation and Modeling
Keywords
reconfigurable intelligent surface, cell-free networks, algorithm unrolling, distributed optimization, weighted sum rate maximization, alternating direction method of multipliers, RIS reflection coefficient optimization, deep learning, non-convex optimization, fading channels, Internet of Things

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review