Cellular Bandwidth Prediction for Highly Automated Driving - Evaluation of Machine Learning Approaches based on Real-World Data

Florian Jomrich, Alexander Herzberger, Tobias Meuser, Björn Richerzhagen, Ralf Steinmetz, Cornelius Wille

Abstract

To enable highly automated driving and the associated comfort services for the driver, vehicles require a reliable and constant cellular data connection. However, due to their mobility vehicles experience significant fluctuations in their connection quality in terms of bandwidth and availability. To maintain constantly high quality of service, these fluctuations need to be anticipated and predicted before they occur. To this end, different techniques such as connectivity maps and online throughput estimations exist. In this paper, we investigate the possibilities of a large-scale future deployment of such techniques by relying solely on lowcost hardware for network measurements. Therefore, we conducted a measurement campaign over three weeks in which more than 74,000 throughput estimates with correlated network quality parameters were obtained. Based on this data set—which we make publicly available to the community—we provide insights in the challenging task of network quality prediction for vehicular scenarios. More specifically, we analyze the potential of machine learning approaches for bandwidth prediction and assess their underlying assumptions.

Download


Paper Citation


in Harvard Style

Jomrich F., Herzberger A., Meuser T., Richerzhagen B., Steinmetz R. and Wille C. (2018). Cellular Bandwidth Prediction for Highly Automated Driving - Evaluation of Machine Learning Approaches based on Real-World Data.In Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-293-6, pages 121-132. DOI: 10.5220/0006692501210132


in Bibtex Style

@conference{vehits18,
author={Florian Jomrich and Alexander Herzberger and Tobias Meuser and Björn Richerzhagen and Ralf Steinmetz and Cornelius Wille},
title={Cellular Bandwidth Prediction for Highly Automated Driving - Evaluation of Machine Learning Approaches based on Real-World Data},
booktitle={Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2018},
pages={121-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006692501210132},
isbn={978-989-758-293-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Cellular Bandwidth Prediction for Highly Automated Driving - Evaluation of Machine Learning Approaches based on Real-World Data
SN - 978-989-758-293-6
AU - Jomrich F.
AU - Herzberger A.
AU - Meuser T.
AU - Richerzhagen B.
AU - Steinmetz R.
AU - Wille C.
PY - 2018
SP - 121
EP - 132
DO - 10.5220/0006692501210132