No abstract

Since the last few years, the Internet of Vehicles (IoV) has gained more interest from the community because of the rapid development of autonomous vehicles, the growing amount of data generated by vehicles' sensors, and the motivation to use this data for different purposes. Given the very dynamic nature of fast moving vehicles, building a network that guarantees the Quality of Service (QoS) is still a challenge. This is why we have developed an original architecture and a programmable objective function to improve QoS on the ever‐changing networks present in the IoV. Simulation results will show that the proposed solution adapts better to mobility by providing better packet delivery ratio up to five times, achieving three times less packet losses and greatly reducing the energy consumption by a factor 10 compared with state of the art solutions, without compromising delay nor throughput usage.

With an increasing amount of connected cars and devices having more and more sensors, the development of smart architectures and algorithms to efficiently transport data is a major concern. The selection of relays to allow users to connect to Internet is an important aspect in networks with high mobility, particularly in low-population areas having poor network coverage. Furthermore, cellular connectivity can be expensive for users. The solution proposed in this paper uses a machine learning based classification algorithm to select the best relays amongst any user based on their mobility profile. Not only this solution can be used on its own to enhance network performance without requiring a dedicated architecture, but it can be coupled with other algorithms as well to increase performance even more. Simulation results will show the proposition is able to scale up to several hundreds of users simultaneously, it improves the delivery rate of packets by up to a factor 2, it increases connectivity, generates less signaling and yields a more stable topology compared to a random selection or the use of static relays.

The ever increasing amount of connected mobile devices and users in the Internet of vehicles and the fact bicycles, electric scooters and users' smartphones are also connected poses a real challenge in terms of ensuring quality of service. The constantly changing topology due to the high‐mobility of devices and users greatly impacts its stability and the connectivity of devices. Furthermore, to ensure safety of people in the case of autonomous vehicles it is of paramount importance to ensure excellent reliability. This is why we have developed a solution that is based on machine learning to classify devices according to their mobility profile and that uses a scoring system to select the best candidates to act as mobile relays amongst devices with a suitable mobility profile. The scoring system allows to find critical locations in terms of user density. This solution does not require a dedicated infrastructure such as road side units. Simulations results will show the proposed solution increases the packet delivery ratio by up to 6%, reduces the energy consumption by up to 30% and increases the efficiency of bandwidth usage without sacrificing the end delay of users and devices compared with the state‐of‐the‐art.