Prediction of Communication Delays in Connected Vehicles and Platoons

Automated vehicles connected through vehicle-to-vehicle communications can use onboard sensor information from adjacent vehicles to provide higher traffic safety or passenger comfort. In particular, automated vehicles forming a platoon can enhance traffic safety by communicating before braking hard. It can also improve fuel efficiency by enabling reduced aerodynamic drag through short gaps. However, packet losses may increase the delay between periodic beacons, especially for the rear vehicles in a platoon. If the connected vehicles can forecast link quality, they can assign different performance levels in terms of inter-vehicle distances and also facilitate the designing of safer braking strategies. This paper proposes a strategy for incorporating machine learning algorithms into, e.g., the lead vehicle of a platoon to enable online training and real-time prediction of communication delays incurred by connected vehicles during runtime. The prediction accuracy and its suitability for making safety-critical decisions during, e.g., emergency braking have been evaluated through rigorous simulations.

I. Introduction

Automated driving and vehicle platoons can improve traffic safety, fuel efficiency, and traffic flow. In addition, connecting the vehicles enables the Following Vehicles (FVs) to react to the speed changes of a Lead Vehicle (LV) through Vehicle-to-Vehicle (V2V) communications. In platooning, the preassigned LV periodically broadcasts its status and attributes, whereas event-driven messages are disseminated when a situation of common interest, e.g., a hazard, occurs. Automated vehicles can also use this platooning strategy in dense traffic situations. A vehicle in front can broadcast its speed periodically to the vehicles behind and also inform them about an intention to brake. In V2V, communication delays are time-varying and can be very high in dense data and road traffic scenarios since packet drops require waiting for the next update [1]. In addition, since the rear vehicles are further away from the LV, they may experience more frequent outages and packet loss due to path loss, shadowing, and fading effects [2]. One solution to this is to maintain short gaps between the vehicles, as this is also good for fuel efficiency. However, even though the likelihood reduces, packet losses may still occur and cause problems with safety since there is less time to react in case, e.g., emergency braking should be necessary. On the other hand, having longer inter-vehicle distances can result in losing contact with the LV and leads to reduced fuel efficiency. To this end, being aware of the experienced communication delay, i.e., the delay between periodic updates from the leading vehicle, is an important factor in order to make suitable control decisions that enables fuel efficiency while providing safety.