DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis

Future mobile use cases such as teleoperation rely on highly available mobile networks. Due to the nature of the mobile access channel and the inherent competition, the availability may be restricted in certain initially unknown areas or timespans. We automated mobile network data acquisition using...

Full description

Saved in:
Bibliographic Details
Main Authors: Hendrik Schippers, Melina Geis, Stefan Bocker, Christian Wietfeld
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Transactions on Machine Learning in Communications and Networking
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10976440/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850189547498897408
author Hendrik Schippers
Melina Geis
Stefan Bocker
Christian Wietfeld
author_facet Hendrik Schippers
Melina Geis
Stefan Bocker
Christian Wietfeld
author_sort Hendrik Schippers
collection DOAJ
description Future mobile use cases such as teleoperation rely on highly available mobile networks. Due to the nature of the mobile access channel and the inherent competition, the availability may be restricted in certain initially unknown areas or timespans. We automated mobile network data acquisition using a smartphone application and dedicated hardware to address this challenge, providing detailed connectivity insights. DoNext, a massive dataset of 4G and 5G mobile network data and active measurements, was collected over two years in Dortmund, Germany. To the best ofour knowledge, it is the most extensive openly available mobile dataset. Machine learning methods were applied to the data to demonstrate its utility inkey performance indicator prediction. Radio environmental maps facilitating key performance indicator predictions and application planning across different locations are generated through spatial aggregation for in-advance predictions. We also showcase signal strength modeling with transfer learning for arbitrary locations in individual mobile network cells, covering private and restricted areas. By openly providing the dataset, we aim to enable other researchers to develop and evaluate their machine-learning methods without conducting extensive measurement campaigns.
format Article
id doaj-art-4f8bdce420ed490e86d87d5c8386f94b
institution OA Journals
issn 2831-316X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Machine Learning in Communications and Networking
spelling doaj-art-4f8bdce420ed490e86d87d5c8386f94b2025-08-20T02:15:35ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2025-01-01358560410.1109/TMLCN.2025.356423910976440DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network AnalysisHendrik Schippers0https://orcid.org/0000-0003-2584-7104Melina Geis1https://orcid.org/0000-0003-3256-1921Stefan Bocker2https://orcid.org/0000-0003-1967-7794Christian Wietfeld3https://orcid.org/0000-0001-7653-2589Communication Networks Institute (CNI), TU Dortmund University, Dortmund, GermanyCommunication Networks Institute (CNI), TU Dortmund University, Dortmund, GermanyCommunication Networks Institute (CNI), TU Dortmund University, Dortmund, GermanyCommunication Networks Institute (CNI), TU Dortmund University, Dortmund, GermanyFuture mobile use cases such as teleoperation rely on highly available mobile networks. Due to the nature of the mobile access channel and the inherent competition, the availability may be restricted in certain initially unknown areas or timespans. We automated mobile network data acquisition using a smartphone application and dedicated hardware to address this challenge, providing detailed connectivity insights. DoNext, a massive dataset of 4G and 5G mobile network data and active measurements, was collected over two years in Dortmund, Germany. To the best ofour knowledge, it is the most extensive openly available mobile dataset. Machine learning methods were applied to the data to demonstrate its utility inkey performance indicator prediction. Radio environmental maps facilitating key performance indicator predictions and application planning across different locations are generated through spatial aggregation for in-advance predictions. We also showcase signal strength modeling with transfer learning for arbitrary locations in individual mobile network cells, covering private and restricted areas. By openly providing the dataset, we aim to enable other researchers to develop and evaluate their machine-learning methods without conducting extensive measurement campaigns.https://ieeexplore.ieee.org/document/10976440/5G new radio6Gdatasetmachine learningpredictive QoSmulti-MNO
spellingShingle Hendrik Schippers
Melina Geis
Stefan Bocker
Christian Wietfeld
DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis
IEEE Transactions on Machine Learning in Communications and Networking
5G new radio
6G
dataset
machine learning
predictive QoS
multi-MNO
title DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis
title_full DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis
title_fullStr DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis
title_full_unstemmed DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis
title_short DoNext: An Open-Access Measurement Dataset for Machine Learning-Driven 5G Mobile Network Analysis
title_sort donext an open access measurement dataset for machine learning driven 5g mobile network analysis
topic 5G new radio
6G
dataset
machine learning
predictive QoS
multi-MNO
url https://ieeexplore.ieee.org/document/10976440/
work_keys_str_mv AT hendrikschippers donextanopenaccessmeasurementdatasetformachinelearningdriven5gmobilenetworkanalysis
AT melinageis donextanopenaccessmeasurementdatasetformachinelearningdriven5gmobilenetworkanalysis
AT stefanbocker donextanopenaccessmeasurementdatasetformachinelearningdriven5gmobilenetworkanalysis
AT christianwietfeld donextanopenaccessmeasurementdatasetformachinelearningdriven5gmobilenetworkanalysis