Benchmarking Study of Machine Learning Algorithms Case Study: VANET Network

Abstract

In the last few years, the expansion of mobile equipment and the deployment of wireless technologies has experienced rapid growth. Today's ongoing advancements in communication systems are opening up new areas of research, such as Intelligent Transport Systems (ITS). The vehicle ad hoc network (VANET) is a promising technological breakthrough in the transport field. Due to its features, namely, the high mobility, the dynamic topology, frequent disconnection, etc., the network became highly susceptible to threats. In accordance with these an amount of research in machine learning has been carried out to secure the VANET network and improve other aspects in VANET such as routing. They have obtained satisfying results. In this article, we will carry out a benchmarking study of the most commonly used machine learning algorithms in the context of the VANET network focusing on five criteria with the objective of selecting the most relevant one to be used for further work. We will also provide an overview of the attacks against VANET Network that may be useful to the average reader to get an idea of the security issues in VANET.