Margin Boost Clustering based Multivariate Dolphin Swarm Optimization for Routing and Reliable Data Dissemination in VANET

Abstract

VANET is the Vehicular Ad hoc NETworks where the vehicle nodes communicate to others without any fixed infrastructure. Due to frequent topology changes, VANET suffers from challenges like routing and data dissemination between the vehicles. This research work develops an efficient technique called Mean shift Margin Boost Clustering Based Multivariate Dolphin Swarm Optimized Routing (MMBC-MDSOR) technique for improving the routing and reliable data dissemination in VANET. A mean-shift margin boost clustering is an ensemble clustering technique to divide the total network into a number of groups. Each group comprises the number of vehicle nodes by the ensemble method uses the iterative Gaussian kernelized mean shifted clustering technique to assign each vehicle towards the closest cluster centroid based on the different stability parameters such as vehicles density, direction, distance and velocity to form a cluster head. By using cluster head, the data communication is controlled between vehicle nodes as well as the end to end delay is reduced. Multivariate Dolphin Swarm Optimized Routing (MDSOR) is the cluster based optimization to select the optimal cluster head based on fitness function in terms of distance, signal strength and bandwidth. Then the optimal route path between source to destination is identified to disseminate the messages. The designed MDSOR in MMBC-MDSOR increases the reliability, throughput and minimizes packet drop ratio. The above technique can be applied wherever there is high congestion on the road due to the failure of optimal link discovery and data distribution between the vehicles in emergency condition. The simulation result shows that the MMBC-MDSOR Technique can enhance the reliability, throughput and also minimizes the end to end delay and packet drop ratio in VANET as compared to state-of-the-art works