Traffic offloading model in a multilevel edge computing system for autonomous vehicles

Abstract

Research subject is autonomous control networks for unmanned vehicles. Research method – study of the main functional elements and their locations for MEC, Fog technologies; studying the types of interaction between devices in vehicle networks; identification of the main problems arising in vehicle networks. Main results – MEC, V2X technologies are described in detail; considered a system that will be implemented using edge computing, and will also support ultra-low latency and high density for unmanned vehicles; a model was created for the VANET environment, demonstrating signal processing at two levels of edge computing. Practical significance – The presented architecture will reduce the load on the core network and ensure the provision of ultra-low transmission delays, which can also contribute to the introduction of unmanned vehicle networks into
 mass use in the future. The proposed architecture can be used as part of the «Smart City» concept. It is also worth noting that a multi-level system, due to its closer location to the user, will be more effective in forming a Fog cluster than with a standard network architecture, when a remote server will be used to form a cluster.