Abstract:
Modern vehicles and transportation systems are becoming more and more reliant on connectivity for safety applications, remote asset monitoring, on-board infotainment, and...Show MoreMetadata
Abstract:
Modern vehicles and transportation systems are becoming more and more reliant on connectivity for safety applications, remote asset monitoring, on-board infotainment, and autonomous driving. Hence, a reliable communication uplink providing sufficient data rate is essential to deliver the required data between the vehicle and services on the edge or in the cloud. This uplink may use multiple wireless or cellular interfaces in a multi-homed setup, and requires reliable and efficient methods to route data traffic over them. In this context, previous work presented the Multi-Armed Bandit Adaptive Similarity-based Regressor (MABASR) as an approach for interface selection between 3G and 4G links based on real-time estimated data rates. In the scope of this article, the MABASR interface selection algorithm is now extended to handle more than two interfaces, with one interface specifically being 5G. Experimental results based on cellular network measurements are presented to illustrate the performance.
Published in: 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)
Date of Conference: 06-09 September 2022
Date Added to IEEE Xplore: 25 October 2022
ISBN Information: