MetoidS: Hybrid K-Medoids-Meta Heuristic Clustering-Based Routing Optimization in Vehicular Ad-Hoc Networks

Clustering plays a vital role in establishing a more stable global network topology in Vehicular Ad Hoc NETworks (VANETs) and supports Intelligent Transportation Systems (ITS) applications and message routing. However, due to the unstable infrastructure of VANETs, cluster size and geographical span have a significant impact on maintaining cluster stability and network efficiency. Thus, this paper presents a hybrid machine learning (ML) and meta-heuristics (MH) based routing scheme called MetoidS to support scalability, enhance the stability of the network topology, and provide efficient routing. We incorporate vehicle orientation-based unsupervised clustering and population based MH to provide a new direction to the taxonomy of the approaches to handling efficient route discovery and cluster maintenance challenges. To represent a real-world simulation of our approach, we have conducted the experiments using a combination of four frameworks (i.e., OMNeT++, SUMO, VEINS, and INET) that demonstrate better performance in terms of high cluster stability, enhanced throughput, high packet delivery ratio, and minimizes average transmission delay compared to the existing routing protocols used in this research.