Modeling and Analysis of New Hybrid Clustering Technique for Vehicular Ad Hoc Network

Hazem Noori Abdulrazzak, Goh Chin Hock (), Nurul Asyikin Mohamed Radzi, Nadia M. L. Tan () and Chiew Foong Kwong
Additional contact information
Hazem Noori Abdulrazzak: Institute of Power Engineering (IPE), Universiti Tenaga Nasional (UNITEN), Kajang 43000, Malaysia
Goh Chin Hock: Institute of Power Engineering (IPE), Universiti Tenaga Nasional (UNITEN), Kajang 43000, Malaysia
Nurul Asyikin Mohamed Radzi: Institute of Power Engineering (IPE), Universiti Tenaga Nasional (UNITEN), Kajang 43000, Malaysia
Nadia M. L. Tan: Institute of Power Engineering (IPE), Universiti Tenaga Nasional (UNITEN), Kajang 43000, Malaysia
Chiew Foong Kwong: Department of Electrical and Electronic Engineering, University of Nottingham Ningbo China, Ningbo 315100, China

Mathematics, 2022, vol. 10, issue 24, 1-27

Abstract: Many researchers have proposed algorithms to improve the network performance of vehicular ad hoc network (VANET) clustering techniques for different applications. The effectiveness of the clustering model is the most important challenge. The K-Means clustering algorithm is an effective algorithm for multi-clusters that can be used in VANETs. The problems with the K-Means algorithm concern the selection of a suitable number of clusters, the creation of a highly reliable cluster, and achieving high similarity within a cluster. To address these problems, a novel method combining a covering rough set and a K-Means clustering algorithm (RK-Means) was proposed in this paper. Firstly, RK-Means creates multi-groups of vehicles using a covering rough set based on effective parameters. Secondly, the K-value-calculating algorithm computes the optimal number of clusters. Finally, the classical K-Means algorithm is applied to create the vehicle clusters for each covering rough set group. The datasets used in this work were imported from Simulation of Urban Mobility (SUMO), representing two highway scenarios, high-density and low-density. Four evaluation indexes, namely, the root mean square error (RMSE), silhouette coefficient (SC), Davies–Bouldin (DB) index, and Dunn index (DI), were used directly to test and evaluate the results of the clustering. The evaluation process was implemented on RK-Means, K-Means++, and OK-Means models. The result of the compression showed that RK-Means had high cluster similarity, greater reliability, and error reductions of 32.5% and 24.2% compared with OK-Means and K-Means++, respectively.

Keywords: energy; K-Means clustering; rough set; clustering; VANET; cluster evaluation; unsupervised machine learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/24/4720/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/24/4720/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:24:p:4720-:d:1001203

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().