This website requires JavaScript.

FAIR: Towards Impartial Resource Allocation for Intelligent Vehicles with Automotive Edge Computing

Haoxin WangJiang XieMuhana Magboul Ali Muslam
Dec 2022
The emerging vehicular connected applications, such as cooperative automateddriving and intersection collision warning, show great potentials to improvethe driving safety, where vehicles can share the data collected by a variety ofon-board sensors with surrounding vehicles and roadside infrastructures.Transmitting and processing this huge amount of sensory data introduces newchallenges for automotive edge computing with traditional wirelesscommunication networks. In this work, we address the problem of traditionalasymmetrical network resource allocation for uplink and downlink connectionsthat can significantly degrade the performance of vehicular connectedapplications. An end-to-end automotive edge networking system, FAIR, isproposed to provide fast, scalable, and impartial connected services forintelligent vehicles with edge computing, which can be applied to any trafficscenes and road topology. The core of FAIR is our proposed symmetrical networkresource allocation algorithm deployed at edge servers and service adaptationalgorithm equipped on intelligent vehicles. Extensive simulations are conductedto validate our proposed FAIR by leveraging real-world traffic dataset.Simulation results demonstrate that FAIR outperforms existing solutions in avariety of traffic scenes and road topology.