Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems
Cell-free massive MIMO systems consist of many distributed access points with simple components that jointly serve the users. In millimeter wave bands, only a limited set of predetermined beams can be supported. In a network that consolidates these technologies, downlink analog beam selection stands...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9475518/ |
| _version_ | 1818658412393660416 |
|---|---|
| author | Cenk M. Yetis Emil Bjornson Pontus Giselsson |
| author_facet | Cenk M. Yetis Emil Bjornson Pontus Giselsson |
| author_sort | Cenk M. Yetis |
| collection | DOAJ |
| description | Cell-free massive MIMO systems consist of many distributed access points with simple components that jointly serve the users. In millimeter wave bands, only a limited set of predetermined beams can be supported. In a network that consolidates these technologies, downlink analog beam selection stands as a challenging task for the network sum-rate maximization. Low-cost digital filters can improve the network sum-rate further. In this work, we propose low-cost joint designs of analog beam selection and digital filters. The proposed joint designs achieve significantly higher sum-rates than the disjoint design benchmark. Supervised machine learning (ML) algorithms can efficiently approximate the input-output mapping functions of the beam selection decisions of the joint designs with low computational complexities. Since the training of ML algorithms is performed off-line, we propose a well-constructed joint design that combines multiple initializations, iterations, and selection features, as well as beam conflict control, i.e., the same beam cannot be used for multiple users. The numerical results indicate that ML algorithms can retain 99–100% of the original sum-rate results achieved by the proposed well-constructed designs. |
| first_indexed | 2024-12-17T03:56:58Z |
| format | Article |
| id | doaj.art-a554ae0be18d4bb8b85b4c77a9037752 |
| institution | Directory Open Access Journal |
| issn | 2644-125X |
| language | English |
| last_indexed | 2024-12-17T03:56:58Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj.art-a554ae0be18d4bb8b85b4c77a90377522022-12-21T22:04:36ZengIEEEIEEE Open Journal of the Communications Society2644-125X2021-01-0121647166210.1109/OJCOMS.2021.30948239475518Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO SystemsCenk M. Yetis0https://orcid.org/0000-0002-6198-4555Emil Bjornson1https://orcid.org/0000-0002-5954-434XPontus Giselsson2Department of Automatic Control, Lund University, Lund, SwedenDepartment of Electrical Engineering (ISY), Linköping University, Linköping, SwedenDepartment of Automatic Control, Lund University, Lund, SwedenCell-free massive MIMO systems consist of many distributed access points with simple components that jointly serve the users. In millimeter wave bands, only a limited set of predetermined beams can be supported. In a network that consolidates these technologies, downlink analog beam selection stands as a challenging task for the network sum-rate maximization. Low-cost digital filters can improve the network sum-rate further. In this work, we propose low-cost joint designs of analog beam selection and digital filters. The proposed joint designs achieve significantly higher sum-rates than the disjoint design benchmark. Supervised machine learning (ML) algorithms can efficiently approximate the input-output mapping functions of the beam selection decisions of the joint designs with low computational complexities. Since the training of ML algorithms is performed off-line, we propose a well-constructed joint design that combines multiple initializations, iterations, and selection features, as well as beam conflict control, i.e., the same beam cannot be used for multiple users. The numerical results indicate that ML algorithms can retain 99–100% of the original sum-rate results achieved by the proposed well-constructed designs.https://ieeexplore.ieee.org/document/9475518/Cell-freemillimeter wavehybrid architectureanalog beamformingdigital beamformingbeam training |
| spellingShingle | Cenk M. Yetis Emil Bjornson Pontus Giselsson Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems IEEE Open Journal of the Communications Society Cell-free millimeter wave hybrid architecture analog beamforming digital beamforming beam training |
| title | Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems |
| title_full | Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems |
| title_fullStr | Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems |
| title_full_unstemmed | Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems |
| title_short | Joint Analog Beam Selection and Digital Beamforming in Millimeter Wave Cell-Free Massive MIMO Systems |
| title_sort | joint analog beam selection and digital beamforming in millimeter wave cell free massive mimo systems |
| topic | Cell-free millimeter wave hybrid architecture analog beamforming digital beamforming beam training |
| url | https://ieeexplore.ieee.org/document/9475518/ |
| work_keys_str_mv | AT cenkmyetis jointanalogbeamselectionanddigitalbeamforminginmillimeterwavecellfreemassivemimosystems AT emilbjornson jointanalogbeamselectionanddigitalbeamforminginmillimeterwavecellfreemassivemimosystems AT pontusgiselsson jointanalogbeamselectionanddigitalbeamforminginmillimeterwavecellfreemassivemimosystems |