AlcFier: Adaptive Self-Learning Classifier for Routing in Vehicular Ad-Hoc Network

Abstract

This paper presents an adaptive self-learning classifier-based clustering algorithm called AlcFier, to support scalability, enhance the stability of the network topology, and provide efficient routing. We incorporate mobility and channel characteristics (i.e., orientation, adjacency, link availability, queue occupancy, and signal-to-noise ratio) into the clustering approach as a channel-aware metric to provide a new direction to the taxonomy of the approaches employed to handle cluster head election, cluster affiliation, and cluster administration challenges. Experimental results show that AlcFier performs efficiently, improves cluster stability, reduces transmission delays, and improves throughput compared with the state-of-the-art routing protocols.