A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks

Effectively managing network congestion in 5G systems is crucial for ensuring seamless connectivity and optimal resource utilization. In this study, an operational scheme based on hotspot prediction for Virtual Small Cell (VSC) is presented, which aims to improve coverage, reduce delay and improve e...

Full description

Saved in:
Bibliographic Details
Main Authors: Aws Majeed Ghalib Alawadi, Hadi Seyedarabi, Reza Afrouzian, Javad Musevi Niya
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015958/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710642437554176
author Aws Majeed Ghalib Alawadi
Hadi Seyedarabi
Reza Afrouzian
Javad Musevi Niya
author_facet Aws Majeed Ghalib Alawadi
Hadi Seyedarabi
Reza Afrouzian
Javad Musevi Niya
author_sort Aws Majeed Ghalib Alawadi
collection DOAJ
description Effectively managing network congestion in 5G systems is crucial for ensuring seamless connectivity and optimal resource utilization. In this study, an operational scheme based on hotspot prediction for Virtual Small Cell (VSC) is presented, which aims to improve coverage, reduce delay and improve energy efficiency in 5G networks for congested locations. For this purpose, at first, using the location map of users, the location of hotspots is predicted by an Ensemble deep learning algorithm. Ensemble deep learning algorithm in this research combines the advantages of GRU and GRN networks and creates an efficient and accurate deep model that is more accurate than previous approaches that used single networks. Then, the information of hotspots is used to form VSCs and finally the adaptive beamforming operation is performed. To optimally allocate resources, genetic algorithm has been used so that the answer of the problem is not trapped in the local optimum. Simulation on the Telecom Italia dataset demonstrates a 10.13% RMSE, showing superior hotspot prediction accuracy compared to existing methods. Also, the numerical results of this study show that by using the hotspots prediction results, the energy efficiency of the system based on VSC operation and adaptive beamforming can be significantly improved.
format Article
id doaj-art-a91ba5bbb73745af9c816dab1b8aa6f4
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a91ba5bbb73745af9c816dab1b8aa6f42025-08-20T03:14:50ZengIEEEIEEE Access2169-35362025-01-011310943510945010.1109/ACCESS.2025.357411911015958A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G NetworksAws Majeed Ghalib Alawadi0https://orcid.org/0009-0001-5005-3528Hadi Seyedarabi1https://orcid.org/0000-0001-6652-2467Reza Afrouzian2https://orcid.org/0000-0002-6968-0409Javad Musevi Niya3https://orcid.org/0000-0002-4330-005XFaculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranFaculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranMiyaneh Faculty of Engineering, University of Tabriz, Miyaneh, IranFaculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranEffectively managing network congestion in 5G systems is crucial for ensuring seamless connectivity and optimal resource utilization. In this study, an operational scheme based on hotspot prediction for Virtual Small Cell (VSC) is presented, which aims to improve coverage, reduce delay and improve energy efficiency in 5G networks for congested locations. For this purpose, at first, using the location map of users, the location of hotspots is predicted by an Ensemble deep learning algorithm. Ensemble deep learning algorithm in this research combines the advantages of GRU and GRN networks and creates an efficient and accurate deep model that is more accurate than previous approaches that used single networks. Then, the information of hotspots is used to form VSCs and finally the adaptive beamforming operation is performed. To optimally allocate resources, genetic algorithm has been used so that the answer of the problem is not trapped in the local optimum. Simulation on the Telecom Italia dataset demonstrates a 10.13% RMSE, showing superior hotspot prediction accuracy compared to existing methods. Also, the numerical results of this study show that by using the hotspots prediction results, the energy efficiency of the system based on VSC operation and adaptive beamforming can be significantly improved.https://ieeexplore.ieee.org/document/11015958/5Gmultiple input and multiple output (MIMO)beamformingdeep learninggraph recurrent network (GRN)gate recurrent unit (GRU)
spellingShingle Aws Majeed Ghalib Alawadi
Hadi Seyedarabi
Reza Afrouzian
Javad Musevi Niya
A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks
IEEE Access
5G
multiple input and multiple output (MIMO)
beamforming
deep learning
graph recurrent network (GRN)
gate recurrent unit (GRU)
title A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks
title_full A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks
title_fullStr A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks
title_full_unstemmed A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks
title_short A Hotspot Prediction Scheme Based on Ensemble Learning With Adaptive Beamforming for Virtual Small Cell in 5G Networks
title_sort hotspot prediction scheme based on ensemble learning with adaptive beamforming for virtual small cell in 5g networks
topic 5G
multiple input and multiple output (MIMO)
beamforming
deep learning
graph recurrent network (GRN)
gate recurrent unit (GRU)
url https://ieeexplore.ieee.org/document/11015958/
work_keys_str_mv AT awsmajeedghalibalawadi ahotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT hadiseyedarabi ahotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT rezaafrouzian ahotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT javadmuseviniya ahotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT awsmajeedghalibalawadi hotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT hadiseyedarabi hotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT rezaafrouzian hotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks
AT javadmuseviniya hotspotpredictionschemebasedonensemblelearningwithadaptivebeamformingforvirtualsmallcellin5gnetworks