Real-time mobile broadband quality of service prediction using AI-driven customer-centric approach

Statistical methods employed in evaluating the quality of service (performance) of mobile broadband (MBB) networks face drawbacks relating to the accurate and reliable processing of the huge amounts of heterogenous real time traffic data generated from MBB networks. Since the traffic patterns experi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Advances in Computing and Engineering Jg. 5; H. 1; S. 1 - 19
Hauptverfasser: Akinlabi, Ayokunle A., Dahunsi, Folasade M., Popoola, Jide J., Okegbemi, Lawrence B.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Academy Publishing Center 18.06.2025
Schlagworte:
ISSN:2735-5977, 2735-5985
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Statistical methods employed in evaluating the quality of service (performance) of mobile broadband (MBB) networks face drawbacks relating to the accurate and reliable processing of the huge amounts of heterogenous real time traffic data generated from MBB networks. Since the traffic patterns experienced in MBB networks are largely complex, highly dynamic and heterogenous in nature; hence, statistical methods may not adjust adequately to the changing network conditions. The highlighted gap can be addressed by machine learning (ML), as it has been effectively used in the past to support the analysis and knowledge discovery of communication systems’ traffic data through identification of intricate and hidden patterns. This paper presents the application of ML techniques to predict MBB QoS in real-time, using a custom-built mobile application (MBPerf) that collects five (5) network metrics (DNS lookup, speeds, latency, signal strength), location information and device characteristics across diverse network conditions in South West of Nigeria. The QoS modeling task was carried out using MBPerf pre-processed dataset. Three (3) classification algorithms including Random Forest (RF), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were trained using the QoS dataset and then evaluated in order to determine the most effective model based on certain evaluation metrics – accuracy, precision, F1-Score and recall. Following hyperparameter tuning to improve the model's performance, the selected model was deployed in a real-world network environment to classify QoS into "Above Average," "Average," and "Below Average," categories. Mobile customers receive real-time notifications with actionable insights based on the predicted QoS class, empowering them to optimize their usage and troubleshoot issues. From the performance results obtained for the 3 ML models trained with MBPerf dataset, SVM (95%) and XGBoost (97%) significantly outperformed RF (59%) in terms of accuracy. However, the performance difference between SVM and XGBoost models are not significant. Interestingly, the 3 models showed great capability to accurately make predictions on the three QoS categories (classes) as depicted by the ROC-AUC and mlogloss curves. Lastly, the feature importance plot shows that QoS is the collective effect of service performance and not a function QoS metrics only that determines the degree of satisfaction of a user of the service. This Artificial Intelligence (AI) powered system promotes a more transparent and efficient MBB experience for all stakeholders in Nigeria's fast evolving digital landscape.Received on, 05 May 2025 Accepted on, 26 May 2025 Published on, 18 June 2025
AbstractList Statistical methods employed in evaluating the quality of service (performance) of mobile broadband (MBB) networks face drawbacks relating to the accurate and reliable processing of the huge amounts of heterogenous real time traffic data generated from MBB networks. Since the traffic patterns experienced in MBB networks are largely complex, highly dynamic and heterogenous in nature; hence, statistical methods may not adjust adequately to the changing network conditions. The highlighted gap can be addressed by machine learning (ML), as it has been effectively used in the past to support the analysis and knowledge discovery of communication systems’ traffic data through identification of intricate and hidden patterns. This paper presents the application of ML techniques to predict MBB QoS in real-time, using a custom-built mobile application (MBPerf) that collects five (5) network metrics (DNS lookup, speeds, latency, signal strength), location information and device characteristics across diverse network conditions in South West of Nigeria. The QoS modeling task was carried out using MBPerf pre-processed dataset. Three (3) classification algorithms including Random Forest (RF), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were trained using the QoS dataset and then evaluated in order to determine the most effective model based on certain evaluation metrics – accuracy, precision, F1-Score and recall. Following hyperparameter tuning to improve the model's performance, the selected model was deployed in a real-world network environment to classify QoS into "Above Average," "Average," and "Below Average," categories. Mobile customers receive real-time notifications with actionable insights based on the predicted QoS class, empowering them to optimize their usage and troubleshoot issues. From the performance results obtained for the 3 ML models trained with MBPerf dataset, SVM (95%) and XGBoost (97%) significantly outperformed RF (59%) in terms of accuracy. However, the performance difference between SVM and XGBoost models are not significant. Interestingly, the 3 models showed great capability to accurately make predictions on the three QoS categories (classes) as depicted by the ROC-AUC and mlogloss curves. Lastly, the feature importance plot shows that QoS is the collective effect of service performance and not a function QoS metrics only that determines the degree of satisfaction of a user of the service. This Artificial Intelligence (AI) powered system promotes a more transparent and efficient MBB experience for all stakeholders in Nigeria's fast evolving digital landscape.Received on, 05 May 2025 Accepted on, 26 May 2025 Published on, 18 June 2025
Author Popoola, Jide J.
Akinlabi, Ayokunle A.
Dahunsi, Folasade M.
Okegbemi, Lawrence B.
Author_xml – sequence: 1
  givenname: Ayokunle A.
  surname: Akinlabi
  fullname: Akinlabi, Ayokunle A.
– sequence: 2
  givenname: Folasade M.
  surname: Dahunsi
  fullname: Dahunsi, Folasade M.
– sequence: 3
  givenname: Jide J.
  surname: Popoola
  fullname: Popoola, Jide J.
– sequence: 4
  givenname: Lawrence B.
  surname: Okegbemi
  fullname: Okegbemi, Lawrence B.
BookMark eNo9kE9PwjAYhxuDiYh8Ai_9Aptv23Vbj4SgkpCYGD03XfsOS8Y6u0HCt3eA4fT7c3gOzyOZtKFFQp4ZpJzlnL8slquUA5cpyJSlTAh-R6a8EDKRqpSTWy-KBzLv-x0AcMWFKtmUVJ9ommTwe6T7UPkGaRWDcZVpHf09mMYPJxpq2mM8eou0i-i8HXxo6aH37ZYu1omL_ogttYd-CHuMicV2iN5S03Ujyv48kfvaND3O_3NGvl9XX8v3ZPPxtl4uNollUvLEZa7ILFNFVZYZoCxrkCq3RoqCKQlYj0PVqlQqZ06CKAuJ3ILK8VwAxYysr1wXzE530e9NPOlgvL4cIW61iYO3DWqrAKFyTtVGZMaaSnCHtspqzFRWAh9Z4sqyMfR9xPrGY6Av1vVoXZ-ta5Ca6bN18Qd16neq
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.21622/ACE.2025.05.1.1332
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2735-5985
EndPage 19
ExternalDocumentID oai_doaj_org_article_c90e0bdd9fa34acab32decb4fe494802
10_21622_ACE_2025_05_1_1332
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
ID FETCH-LOGICAL-c1552-d4d74c197b8840e58f0596ca5371950ef96c9f989961d503875e2c096e75e20e3
IEDL.DBID DOA
ISSN 2735-5977
IngestDate Fri Oct 03 12:50:36 EDT 2025
Sat Nov 29 07:51:12 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1552-d4d74c197b8840e58f0596ca5371950ef96c9f989961d503875e2c096e75e20e3
OpenAccessLink https://doaj.org/article/c90e0bdd9fa34acab32decb4fe494802
PageCount 19
ParticipantIDs doaj_primary_oai_doaj_org_article_c90e0bdd9fa34acab32decb4fe494802
crossref_primary_10_21622_ACE_2025_05_1_1332
PublicationCentury 2000
PublicationDate 2025-06-18
PublicationDateYYYYMMDD 2025-06-18
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-06-18
  day: 18
PublicationDecade 2020
PublicationTitle Advances in Computing and Engineering
PublicationYear 2025
Publisher Academy Publishing Center
Publisher_xml – name: Academy Publishing Center
SSID ssj0002923981
Score 2.295055
Snippet Statistical methods employed in evaluating the quality of service (performance) of mobile broadband (MBB) networks face drawbacks relating to the accurate and...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 1
SubjectTerms cellular network: mobile broadband
crowdsourcing
extreme gradient boosting
machine learning
quality of service
random forest
support vector machine
Title Real-time mobile broadband quality of service prediction using AI-driven customer-centric approach
URI https://doaj.org/article/c90e0bdd9fa34acab32decb4fe494802
Volume 5
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2735-5985
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002923981
  issn: 2735-5977
  databaseCode: DOA
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ3LS8NAEMYXKR68iKJifbEHj67Ns9s91lJRkCKi0tuyOzuRHpqWtBX8751JWqknL96SEEL49jVfMvsbIa416i7qGJWH3CnqIZnyWeaUNwCm6wF1vY_7_UmPRr3x2DxvlfrinLAGD9wI1wETYeRDMIVLMwfOp0lA8FmBDDZpMJIU9WyZKZ6DE8NcO3ZbtDzniiFrDXIoibtJ0ukPhmQNk5yhnfEt2bTk17K0Re-vl5n7A7G_jg9lv3mvQ7GD5ZHwLxTOKS4DL6czT-NY-mrmgndlkM2uyC85K-SiGfdyXvHfF1Zcclr7h-w_qlDxtCZhRcHeFCtVJ2VOQG6Y4sfi7X74OnhQ6-IICpiapkIWdAax0Z70jTDvFVxIB1yeaq7sigWdmMKQnerGgZkvOscEyLAgH0SYnohWOSvxVEhAE1IN_EkUMogKR6sZuSivAVJPKrXFzUYbO28YGJa8Qy2lJSktS2mj3MaWpWyLO9bv51YGWNcXqFntulntX8169h8PORd7_Gqc2RX3LkRrWa3wUuzC53KyqK7qHvMNAhnFMQ
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Real-time+mobile+broadband+quality+of+service+prediction+using+AI-driven+customer-centric+approach&rft.jtitle=Advances+in+Computing+and+Engineering&rft.au=Ayokunle+A.+Akinlabi&rft.au=Folasade+M.+Dahunsi&rft.au=Jide+J.+Popoola&rft.au=Lawrence+B.+Okegbemi&rft.date=2025-06-18&rft.pub=Academy+Publishing+Center&rft.issn=2735-5977&rft.eissn=2735-5985&rft.volume=5&rft.issue=1&rft.spage=1&rft.epage=19&rft_id=info:doi/10.21622%2FACE.2025.05.1.1332&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_c90e0bdd9fa34acab32decb4fe494802
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2735-5977&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2735-5977&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2735-5977&client=summon