A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks
The goal of this paper is to evaluate the performance of an adaptive beamforming approach in fifth-generation millimeter-wave multicellular networks, where massive multiple-input multiple-output configurations are employed in all active base stations of the considered orientations. In this context,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9869669/ |
| _version_ | 1828421097519841280 |
|---|---|
| author | Spyros Lavdas Panagiotis K. Gkonis Zinon Zinonos Panagiotis Trakadas Lambros Sarakis Konstantinos Papadopoulos |
| author_facet | Spyros Lavdas Panagiotis K. Gkonis Zinon Zinonos Panagiotis Trakadas Lambros Sarakis Konstantinos Papadopoulos |
| author_sort | Spyros Lavdas |
| collection | DOAJ |
| description | The goal of this paper is to evaluate the performance of an adaptive beamforming approach in fifth-generation millimeter-wave multicellular networks, where massive multiple-input multiple-output configurations are employed in all active base stations of the considered orientations. In this context, beamforming is performed with the help of a predefined set of configurations that can deal with various traffic scenarios by properly generating highly directional beams on demand. In parallel, a machine learning (ML) beamforming approach based on the k-nearest neighbors (<inline-formula> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>-NN) approximation has been considered as well, which is trained in order to generate the appropriate beamforming configurations according to the spatial distribution of throughput demand. Performance is evaluated statistically, via a developed system level simulator that executes Monte Carlo simulations in parallel. Results indicate that the achievable spectral efficiency (SE) and energy efficiency (EE) values are aligned with other state of the art approaches, with reduced hardware and algorithmic complexity, since per user beamforming calculations are omitted. In particular, considering a two-tier cellular orientation, then in the non-ML approach EE and SE can reach up to 5 Mbits/J and 36 bps/Hz, respectively. Both metrics attain the aforementioned values when the ML-assisted beamforming framework is considered. However, beamforming complexity is further reduced, since the ML approach provides a direct mapping among the considered throughput demand and appropriate beamforming configuration. |
| first_indexed | 2024-12-10T15:23:30Z |
| format | Article |
| id | doaj.art-6eab05665b5e4742a755796f621e7157 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T15:23:30Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6eab05665b5e4742a755796f621e71572022-12-22T01:43:36ZengIEEEIEEE Access2169-35362022-01-0110915979160910.1109/ACCESS.2022.32026409869669A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular NetworksSpyros Lavdas0https://orcid.org/0000-0002-6228-6724Panagiotis K. Gkonis1https://orcid.org/0000-0001-8846-1044Zinon Zinonos2https://orcid.org/0000-0001-9049-0346Panagiotis Trakadas3https://orcid.org/0000-0002-5146-5954Lambros Sarakis4https://orcid.org/0000-0002-3890-5476Konstantinos Papadopoulos5Department of Computer Science, Neapolis University Pafos, Paphos, CyprusDepartment of Digital Industry Technologies, National and Kapodistrian University of Athens, Dirfies Messapies, GreeceDepartment of Computer Science, Neapolis University Pafos, Paphos, CyprusDepartment of Port Management and Shipping, National and Kapodistrian University of Athens, Dirfies Messapies, GreeceDepartment of Digital Industry Technologies, National and Kapodistrian University of Athens, Dirfies Messapies, GreeceDepartment of Digital Industry Technologies, National and Kapodistrian University of Athens, Dirfies Messapies, GreeceThe goal of this paper is to evaluate the performance of an adaptive beamforming approach in fifth-generation millimeter-wave multicellular networks, where massive multiple-input multiple-output configurations are employed in all active base stations of the considered orientations. In this context, beamforming is performed with the help of a predefined set of configurations that can deal with various traffic scenarios by properly generating highly directional beams on demand. In parallel, a machine learning (ML) beamforming approach based on the k-nearest neighbors (<inline-formula> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>-NN) approximation has been considered as well, which is trained in order to generate the appropriate beamforming configurations according to the spatial distribution of throughput demand. Performance is evaluated statistically, via a developed system level simulator that executes Monte Carlo simulations in parallel. Results indicate that the achievable spectral efficiency (SE) and energy efficiency (EE) values are aligned with other state of the art approaches, with reduced hardware and algorithmic complexity, since per user beamforming calculations are omitted. In particular, considering a two-tier cellular orientation, then in the non-ML approach EE and SE can reach up to 5 Mbits/J and 36 bps/Hz, respectively. Both metrics attain the aforementioned values when the ML-assisted beamforming framework is considered. However, beamforming complexity is further reduced, since the ML approach provides a direct mapping among the considered throughput demand and appropriate beamforming configuration.https://ieeexplore.ieee.org/document/9869669/5Gmassive MIMOmillimeter-wave transmissionmachine learningadaptive beamforming |
| spellingShingle | Spyros Lavdas Panagiotis K. Gkonis Zinon Zinonos Panagiotis Trakadas Lambros Sarakis Konstantinos Papadopoulos A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks IEEE Access 5G massive MIMO millimeter-wave transmission machine learning adaptive beamforming |
| title | A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks |
| title_full | A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks |
| title_fullStr | A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks |
| title_full_unstemmed | A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks |
| title_short | A Machine Learning Adaptive Beamforming Framework for 5G Millimeter Wave Massive MIMO Multicellular Networks |
| title_sort | machine learning adaptive beamforming framework for 5g millimeter wave massive mimo multicellular networks |
| topic | 5G massive MIMO millimeter-wave transmission machine learning adaptive beamforming |
| url | https://ieeexplore.ieee.org/document/9869669/ |
| work_keys_str_mv | AT spyroslavdas amachinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT panagiotiskgkonis amachinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT zinonzinonos amachinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT panagiotistrakadas amachinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT lambrossarakis amachinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT konstantinospapadopoulos amachinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT spyroslavdas machinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT panagiotiskgkonis machinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT zinonzinonos machinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT panagiotistrakadas machinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT lambrossarakis machinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks AT konstantinospapadopoulos machinelearningadaptivebeamformingframeworkfor5gmillimeterwavemassivemimomulticellularnetworks |