Self-Driving Car Meets Multi-Access Edge Computing for Deep Learning-Based Caching

Abstract

In the future, self-driving cars are expected to be involved in public transportation. Once passengers are comfortable with them, the self-driving cars will be new spaces for entertainment. However, getting infotainment contents from Data Centers (DCs) can be perturbed by the high end-to-end delay. To address this issue, we propose caching for infotainment contents in close proximity to the self-driving cars and in self-driving cars. In our proposal, Multi-access Edge Computing (MEC) helps self-driving cars by deploying MEC servers to the edge of the network at macro base stations (BSs), WiFi access points (WAPs), and roadside units (RSUs) for caching infotainment contents in close proximity to the self-driving cars. Based on the passenger's features learned via self-driving car deep learning approach proposed in this paper, the self-driving car can download infotainment contents that are appropriate to its passengers from MEC servers and cache them. The simulation results show that our prediction for the infotainment contents need to be cached in close proximity to the self-driving cars can achieve 99.28% accuracy.