5G Vehicular Network Resource Management for Improving Radio Access Through Machine Learning

The current cellular technology and vehicular networks cannot satisfy the mighty strides of vehicular network demands. Resource management has become a complex and challenging objective to gain expected outcomes in a vehicular environment. The 5G cellular network promises to provide ultra-high-speed, reduced delay, and reliable communications. The development of new technologies such as the network function virtualization (NFV) and software defined networking (SDN) are critical enabling technologies leveraging 5G. The SDN-based 5G network can provide an excellent platform for autonomous vehicles because SDN offers open programmability and flexibility for new services incorporation. This separation of control and data planes enables centralized and efficient management of resources in a very optimized and secure manner by having a global overview of the whole network. The SDN also provides flexibility in communication administration and resource management, which are of critical importance when considering the ad-hoc nature of vehicular network infrastructures, in terms of safety, privacy, and security, in vehicular network environments. In addition, it promises the overall improved performance. In this paper, we propose a flow-based policy framework on the basis of two tiers virtualization for vehicular networks using SDNs. The vehicle to vehicle (V2V) communication is quite possible with wireless virtualization where different radio resources are allocated to V2V communications based on the flow classification, i.e., safety-related flow or non-safety flows, and the controller is responsible for managing the overall vehicular environment and V2X communications. The motivation behind this study is to implement a machine learning-enabled architecture to cater the sophisticated demands of modern vehicular Internet infrastructures. The inclination towards robust communications in 5G-enabled networks has made it somewhat tricky to manage network slicing efficiently. This paper also presents a proof of concept for leveraging machine learning-enabled resource classification and management through experimental evaluation of special-purpose testbed established in custom mininet setup. Furthermore, the results have been evaluated using Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Deep Neural Network (DNN). While concluding the paper, it is shown that the LSTM has outperformed the rest of classification techniques with promising results.