Authors:
Florian Jomrich
1
;
Alexander Herzberger
2
;
Tobias Meuser
3
;
Björn Richerzhagen
3
;
Ralf Steinmetz
3
and
Cornelius Wille
2
Affiliations:
1
Opel Automobile GmbH and TU Darmstadt, Germany
;
2
Technical University of Applied Sciences Bingen, Germany
;
3
TU Darmstadt, Germany
Keyword(s):
Cellular Networks, Connectivity Map, LTE, Throughput Prediction, Machine Learning, Mobile, Vehicular.
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 qual
ity prediction for vehicular scenarios. More specifically, we analyze the
potential of machine learning approaches for bandwidth prediction and assess their underlying assumptions.
(More)