A Large-Scale Dataset of 4G, NB-IoT, and 5G Non-Standalone Network Measurements

Mobile networks have become highly complex systems. In order to better understand how network features affect performance and suggest additional improvements, it is crucial to examine them from an empirical perspective. In the following, we present a large-scale dataset of measurements collected over fourth generation (4G) and fifth generation (5G) operational networks, providing Long Term Evolution (LTE), Narrowband Internet of Things (NB-IoT) and 5G New Radio (NR) connectivity. We collected our dataset during a period of seven weeks in Rome, Italy, by performing several tests on the infrastructures of two major mobile network operators (MNOs). The open-sourced dataset has enabled multi-faceted analyses of network deployment, coverage, and end-user performance, and can be further used for designing and testing artificial intelligence (AI) and machine learning (ML) solutions for network optimization tasks. If you use our dataset in your research, we kindly request that you cite the following paper: K. Kousias et al., "A Large-Scale Dataset of 4G, NB-IoT, and 5G Non-Standalone Network Measurements," in IEEE Communications Magazine, vol. 62, no. 5, pp. 44-49, May 2024, doi: 10.1109/MCOM.011.2200707.移动网络已成为高度复杂的系统。为更深入地理解网络特性对性能的影响并提出优化改进方向，从实证视角开展研究至关重要。下文将介绍我们在商用第四代（4G）与第五代（5G）网络中采集的大规模实测数据集，涵盖长期演进（Long Term Evolution，LTE）、窄带物联网（Narrowband Internet of Things，NB-IoT）以及5G新空口（5G New Radio，NR）三类连接场景。本次数据集采集工作于意大利罗马开展，为期七周，针对两家主流移动网络运营商（Mobile Network Operators，MNOs）的基础设施完成了多组测试。该开源数据集可支持网络部署、覆盖范围与终端用户性能等多维度分析，还可进一步用于设计与测试面向网络优化任务的人工智能（Artificial Intelligence，AI）及机器学习（Machine Learning，ML）解决方案。 若您在研究中使用本数据集，恳请引用以下论文： K. Kousias 等，"A Large-Scale Dataset of 4G, NB-IoT, and 5G Non-Standalone Network Measurements"，载于《IEEE Communications Magazine》，第62卷第5期，第44-49页，2024年5月，DOI: 10.1109/MCOM.011.2200707。