Intelligent GA-Based Vehicle Routing within Smart Urban Infrastructure

The perpetual growth in vehicle numbers, coupled with traffic congestion, environmental challenges, and the suboptimal utilization of transport networks, underscores the necessity for intelligent traffic management strategies. A pivotal component of such management involves the efficient identification of optimal routes, which contribute to shortened travel times, reduced fuel consumption, and diminished environmental pollution. This paper introduces a route planning method for smart city transport infrastructure utilizing a genetic algorithm. The proposed approach comprises two principal stages: identifying the primary route and generating a set of alternative routes amidst dynamic urban road congestion. The essential genetic algorithm operators, which are integral to the solution’s evolutionary process, are delineated. To assess the effectiveness of the proposed method, comparisons are drawn with a greedy algorithm and an ant colony optimization algorithm. Analysis of the results illustrates that the genetic algorithm–based method proposed herein reduces vehicle travel time by 18% compared to the ant colony algorithm, owing to its ability to ascertain the optimal route. The greedy algorithm, characterized by its locally focused decision-making processes, was unable to establish a complete route, terminating at intermediate nodes without reaching the intended destination.