Adaptive Hybrid Routing for Vehicular Ad-Hoc Networks Using Swarm Intelligence and Neural Network-Based Traffic Prediction

Abstract

Vehicular Ad-Hoc Networks (VANETs) play a crucial role in the development of intelligent transportation systems, enhancing road safety and optimizing traffic flow. However, efficient routing in VANETs is challenging due to high mobility, frequent topology changes, and dynamic traffic conditions. This paper proposes an Adaptive Hybrid Routing (AHR) protocol that integrates swarm intelligence and neural network-based traffic prediction to improve routing efficiency in VANETs. The swarm intelligence component leverages the collective behavior of vehicular nodes for adaptive route discovery and maintenance, ensuring reliable and scalable communication. Simultaneously, the neural network model predicts traffic conditions based on real-time vehicular data, enabling proactive route selection that minimizes delays and packet loss. The AHR protocol dynamically adapts to changing traffic patterns by combining the advantages of reactive and proactive routing strategies. Swarm-based optimization ensures robust pathfinding in dense and highly mobile networks, while the neural network prediction model mitigates congestion and route failures by providing early traffic forecasts. Simulation results demonstrate that AHR outperforms traditional routing protocols in terms of throughput, end-to-end delay, and packet delivery ratio, particularly under high traffic volumes and rapidly changing network conditions. The integration of swarm intelligence and neural network-based traffic prediction offers a novel approach to enhancing routing performance in VANETs, paving the way for more reliable and efficient vehicular communications in smart cities.