An End-to-end Intelligent Network Resource Allocation in IoV: A Machine Learning Approach

Abstract

The enormous increase in the number of communicating vehicles every year imposes many challenges for efficient resource allocation in IoV (Internet of Vehicles). Additionally, with advancements, many new communication services have been added to the vehicles, each requiring a unique set of resources. The vehicle communication services include simple video streaming, multimedia, and navigation to mission-critical services in self-driving cars. In addition to that, the vehicular technology is rapidly shifting towards the electric vehicle to help the green energy revolution and reduction of carbon footprints. Similarly, communication services are also consuming high-energy so IoE (Internet of Energy) has also become vital to optimize resource utilization for reduction of energy consumption. Due to the complexity of the service requirements in IoV, an energy-efficient and intelligent resource allocation system is essential. To this end, this paper proposes a solution that provides an efficient and proactive resource orchestration for IoV services while considering edge-cloud infrastructure. Machine Learning (ML) approach has been used to manage the resources by predicting network traffic at the edge, and VNF resource utilization at the core.