Open Access

ARTICLE

Enhancing ITS Reliability and Efficiency through Optimal VANET Clustering Using Grasshopper Optimization Algorithm

Seongsoo Cho¹, Yeonwoo Lee^2,*, Cheolhee Yoon^3,*

1 Department of Convergence Science, Kongju National University, Gongju, 32588, Republic of Korea
2 Department of Artificial Intelligence Engineering, Mokpo National University, Chonnam, 58554, Republic of Korea
3 Laboratory of Autonomous Vehicle and Block-chain, Korean National Police University, Hungnamm, 31539, Republic of Korea

* Corresponding Authors: Yeonwoo Lee. Email: ; Cheolhee Yoon. Email:

(This article belongs to the Special Issue: Computer Modeling for Future Communications and Networks)

Computer Modeling in Engineering & Sciences 2025, 143(3), 3769-3793. https://doi.org/10.32604/cmes.2025.066298

Received 04 April 2025; Accepted 16 June 2025; Issue published 30 June 2025

Abstract

As vehicular networks grow increasingly complex due to high node mobility and dynamic traffic conditions, efficient clustering mechanisms are vital to ensure stable and scalable communication. Recent studies have emphasized the need for adaptive clustering strategies to improve performance in Intelligent Transportation Systems (ITS). This paper presents the Grasshopper Optimization Algorithm for Vehicular Network Clustering (GOA-VNET) algorithm, an innovative approach to optimal vehicular clustering in Vehicular Ad-Hoc Networks (VANETs), leveraging the Grasshopper Optimization Algorithm (GOA) to address the critical challenges of traffic congestion and communication inefficiencies in Intelligent Transportation Systems (ITS). The proposed GOA-VNET employs an iterative and interactive optimization mechanism to dynamically adjust node positions and cluster configurations, ensuring robust adaptability to varying vehicular densities and transmission ranges. Key features of GOA-VNET include the utilization of attraction zone, repulsion zone, and comfort zone parameters, which collectively enhance clustering efficiency and minimize congestion within Regions of Interest (ROI). By managing cluster configurations and node densities effectively, GOA-VNET ensures balanced load distribution and seamless data transmission, even in scenarios with high vehicular densities and varying transmission ranges. Comparative evaluations against the Whale Optimization Algorithm (WOA) and Grey Wolf Optimization (GWO) demonstrate that GOA-VNET consistently outperforms these methods by achieving superior clustering efficiency, reducing the number of clusters by up to 10% in high-density scenarios, and improving data transmission reliability. Simulation results reveal that under a 100–600 m transmission range, GOA-VNET achieves an average reduction of 8%–15% in the number of clusters and maintains a 5%–10% improvement in packet delivery ratio (PDR) compared to baseline algorithms. Additionally, the algorithm incorporates a heat transfer-inspired load-balancing mechanism, ensuring equitable distribution of nodes among cluster leaders (CLs) and maintaining a stable network environment. These results validate GOA-VNET as a reliable and scalable solution for VANETs, with significant potential to support next-generation ITS. Future research could further enhance the algorithm by integrating multi-objective optimization techniques and exploring broader applications in complex traffic scenarios.

---

Keywords

---