Optimizing Environment-aware VANET Clustering using Machine Learning

Clustering is important to improve the quality of service in many VANET protocols and applications, such as data dissemination, media access control, Internet of vehicles and intrusion detection systems. Since the performance of a clustering algorithm is highly influenced by the surrounding environment, an environment-aware clustering algorithm that can adapt itself to follow the changes in the environment features is required. In this paper, we propose a machine learning-based framework to include this awareness to an arbitrary clustering algorithm. This is done by optimizing the clustering algorithm’s parameters taking into consideration the road structure and the traffic features that affect the clustering performance. Our framework aims to model how the optimum values of different configuration parameters change with the considered features. Then, these models are used to allow the clustering algorithm to adjust its configurations in real-time according to the measured environment features. After applying this framework on a state-of-the-art clustering algorithm, the performance of the resulting algorithm is compared to other clustering schemes as well as the original algorithm. The obtained results prove the efficiency of the proposed approach reflected by the significant improvements in the different quality metrics and maintaining these metrics in the highest possible levels despite the changes in the considered environment features.