Multiobjective Optimization of VANET Networks for Intelligent Parking with Hybrid PSO-NSGA II Algorithm

Managing parking efficiently has become a critical challenge in today's densely populated urban areas, such as Tirana, Albania, where increasing vehicle congestion exacerbates traffic and environmental concerns. Vehicle Ad-Hoc Networks (VANETs) offer a promising platform for intelligent parking systems by enabling real-time communication between vehicles and infrastructure. This study tackles the complex challenges involved in improving parking systems, focusing on reducing the time spent searching for parking spots, lowering fuel consumption, and improving the utilization of parking spaces, through a novel hybrid approach combining the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and Particle Swarm Optimization (PSO). The hybridization of these algorithms uses the multi-objective optimization capabilities of NSGA-II and the rapid convergence of PSO to explore and exploit the search space effectively. Experimental results demonstrate significant improvements in the performance of the parking system, achieving a balanced tradeoff between competing objectives. These findings highlight the potential of hybrid optimization strategies to advance intelligent transportation systems and contribute to sustainable urban mobility solutions.