Serverless Vehicular Edge Computing for the Internet of Vehicles

Abstract

Rapid growth in the popularity of smart vehicles and increasing demand for vehicle autonomy brings new opportunities for vehicular edge computing (VEC). VEC aims at offloading the time-sensitive computational load of connected vehicles to edge devices, e.g., roadside units. However, VEC offloading raises complex resource management challenges and thus remains largely inaccessible to automotive companies. Recently, serverless computing emerged as a convenient approach to the execution of functions without the hassle of infrastructure management. In this work, we propose the idea of serverless VEC as the execution paradigm for the Internet of vehicles applications. Further, we analyze its benefits and drawbacks, and identify technology gaps. We also propose emulation as a design, evaluation, and experimentation methodology for serverless VEC solutions. Using our emulation toolkit, we validate the feasibility of serverless VEC for real-world traffic scenarios.