Logo do repositório
 
Publicação

Deep Learning-Based Receiver for Low-Complexity 6G Partial LIS Architectures

2026-04Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorMarques da Silva, Mário
dc.contributor.authorOrrillo, Héctor
dc.contributor.authorDinis, Rui
dc.contributor.institutionFaculdade de Ciências e Tecnologia (FCT)
dc.contributor.pblMDPI - Multidisciplinary Digital Publishing Institute
dc.date.accessioned2026-07-29T10:13:01Z
dc.date.available2026-07-29T10:13:01Z
dc.date.issued2026-04
dc.descriptionPublisher Copyright: © 2026 by the authors.
dc.description.abstractThe sixth generation (6G) of wireless networks demands extreme energy efficiency and massive connectivity, positioning large intelligent surfaces (LIS) as a pivotal technology. However, the practical deployment of LIS is constrained by the overwhelming computational complexity and power consumption required to process thousands of antenna elements. To address these challenges, this article proposes a deep learning-based receiver architecture that integrates the spatial efficiency of Partial LIS with advanced non-linear detection. By activating only a subset of antenna panels closest to the user terminal (Partial LIS), the system significantly reduces hardware overhead and Radio Frequency (RF) power consumption. To compensate for the performance loss, the multi-user interference (MUI) generated by the linear combining stage, and the increased MUI inherent in a reduced-aperture environment, a specialized Multilayer Perceptron (MLP) network is implemented. Unlike traditional Zero-Forcing (ZF) or Minimum Mean Squared Error (MMSE) receivers, which require energy-intensive matrix inversions for each frequency component, the proposed neural-network-enabled receiver achieves near-optimal performance using low-complexity combining followed by intelligent learning-based interference suppression. Simulation results demonstrate that the proposed hybrid architecture provides a scalable, “green” solution for 6G uplink scenarios. Notably, the deep learning approach is shown to effectively suppress the performance loss of reduced apertures, achieving a BER comparable to traditional linear benchmarks even with a reduced physical aperture, maintaining good Bit Error Rate (BER) performance while dramatically reducing the computational and hardware footprint.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent18
dc.format.extent2552740
dc.identifier.doi10.3390/app16073429
dc.identifier.issn2076-3417
dc.identifier.otherPURE: 169930836
dc.identifier.otherPURE UUID: 6340299b-e8f2-4cae-9dae-2760a780026e
dc.identifier.otherScopus: 105035650828
dc.identifier.otherORCID: /0000-0002-8520-7267/work/222228120
dc.identifier.urihttp://hdl.handle.net/10362/204934
dc.identifier.urlhttps://www.scopus.com/pages/publications/105035650828
dc.language.isoeng
dc.peerreviewedyes
dc.relationinfo:eu-repo/grantAgreement/FCT/Avaliação UID 2023%2F2024/UID%2F05567%2F2025/PT
dc.relationinfo:eu-repo/grantAgreement/FCT/Avaliação UID 2023%2F2024/UID%2F50008%2F2025/PT
dc.subject6G
dc.subjectlarge intelligent surfaces (LIS)
dc.subjectmulti-user interference
dc.subjectneural networks
dc.subjectPartial LIS
dc.subjectSC-FDE
dc.subjectGeneral Materials Science
dc.subjectInstrumentation
dc.subjectGeneral Engineering
dc.subjectProcess Chemistry and Technology
dc.subjectComputer Science Applications
dc.subjectFluid Flow and Transfer Processes
dc.subjectSDG 7 - Affordable and Clean Energy
dc.titleDeep Learning-Based Receiver for Low-Complexity 6G Partial LIS Architecturesen
dc.typejournal article
degois.publication.issue7
degois.publication.titleApplied Sciences (Switzerland)
degois.publication.volume16
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Silva_Orrillo_Dinis_2026_.pdf
Tamanho:
2.43 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)