Back to Top

■ Machine Learning based Context-predictive Car-to-cloud Communication Using Multi-layer Connectivity Maps for Upcoming 5G Networks

B. Sliwa, R. Falkenberg, T. Liebig, J. Pillmann, and C. Wietfeld, “Machine Learning Based Context-predictive Car-to-cloud Communication Using Multi-layer Connectivity Maps for Upcoming 5G Networks,” in Proceedings of the 88th Vehicular Technology Conference: VTC2018-Fall, 2018.

Abstract.

Upcoming 5G-based communication networks will be confronted with huge increases in the amount of transmitted sensor data related to massive deployments of static and mobile Internet of Things (IoT) systems. Cars acting as mobile sensors will become important data sources for cloud-based applications like predictive maintenance and dynamic traffic forecast. Due to the limitation of available communication resources, it is expected that the grows in Machine-Type Communication (MTC) will cause severe interference with Human-to-human (H2H) communication. Consequently, more efficient transmission methods are highly required. In this paper, we present a probabilistic scheme for efficient transmission of vehicular sensor data which leverages favorable channel conditions and avoids transmissions when they are expected to be highly resource-consuming. Multiple variants of the proposed scheme are evaluated in comprehensive realworld experiments. Through machine learning based combination of multiple context metrics, the proposed scheme is able to achieve up to 164% higher average data rate values for sensor applications with soft deadline requirements compared to regular periodic transmission.

Bibtex Entry.

@article{DBLP:journals/corr/abs-1805-06603,
  author    = {Benjamin Sliwa and
               Thomas Liebig and
               Robert Falkenberg and
               Johannes Pillmann and
               Christian Wietfeld},
  title     = {Machine learning based context-predictive car-to-cloud communication
               using multi-layer connectivity maps for upcoming 5G networks},
  journal   = {CoRR},
  volume    = {abs/1805.06603},
  year      = {2018},
  url       = {http://arxiv.org/abs/1805.06603},
  archivePrefix = {arXiv},
  eprint    = {1805.06603},
  timestamp = {Mon, 13 Aug 2018 16:47:16 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1805-06603},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}