Abstract
Vehicular big data is anticipated to become the “new oil” of the automotive industry which fuels the development of novel crowdsensing-enabled services. However, the tremendous amount of transmitted vehicular sensor data represents a massive challenge for the cellular network. A promising method for achieving relief which allows to utilize the existing network resources in a more efficient way is the utilization of intelligence on the end-edge-cloud devices. Through machine learning-based identification and exploitation of highly resource efficient data transmission opportunities, the client devices are able to participate in overall network resource optimization process. In this work, we present a novel client-based opportunistic data transmission method for delay-tolerant applications which is based on a hybrid machine learning approach: Supervised learning is applied to forecast the currently achievable data rate which serves as the metric for the reinforcement learning-based data transfer scheduling process. In addition, unsupervised learning is applied to uncover geospatially-dependent uncertainties within the prediction model. In a comprehensive real world evaluation in the public cellular networks of three German Mobile Network Operator (MNO), we show that the average data rate can be improved by up to 223% while simultaneously reducing the amount of occupied network resources by up to 89%. As a side-effect of preferring more robust network conditions for the data transfer, the transmission-related power consumption is reduced by up to 73%. The price to pay is an increased Age of Information (AoI) of the sensor data.
Highlights
The various sensing and communication capabilities of modern vehicles have brought up vehicular crowdsensing [1], [2] as a novel method for acquiring various kinds of measurement data
In downlink transmission direction, the differences between the considered prediction models are less significant. This observation can be explained through consideration of the findings of [31]: In downlink direction, the resulting data rate is mostly related to the cell load which is partially represented by the RSRQ
The knowledge about these mechanisms does not explicitly allow us to compensate the undesired effects, it can be exploited within the opportunistic data transmission processes as a measurement for the uncertainty of the prediction model: Transmissions should be avoided if the prediction model is currently in an unreliable state and does not allow to make a precise statement about the achievable end-to-end performance
Summary
The various sensing and communication capabilities of modern vehicles have brought up vehicular crowdsensing [1], [2] as a novel method for acquiring various kinds of measurement data. It is expected that the vehicle-as-a-sensor approach will catalyze the development of data-driven applications such as distributed creation of High Definition (HD) environmental maps, traffic monitoring, predictive maintenance, road roughness detection, and distributed weather sensing [3]. The applications do not require immediate data delivery but specify soft deadlines within which the received information is considered meaningful. In their empirical analysis, the authors of [5] analyzed the properties of 32 existing crowdsensing systems from which 23 were found to be compatible with storeand-forward data delivery mechanisms. The Automotive Edge Computing Consortium (AECC) has analyzed the requirements for distributed construction of HD
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
