Publication Details
Abstract
Route optimization is one of the significant roles in ITS, as it enables dynamic changes in routes in real-time, based on traffic information. This would reduce travel time, decrease congestion, and minimize the environmental impact due to vehicle emissions. Many algorithms, particularly those inspired by nature, like the Ant Colony Optimization, Particle Swarm Optimization, Elephant Herding Optimization, Whale Optimization Algorithm, Grey Wolf Optimization, Shark Smell Optimization algorithms, have had success in enhancing efficiency in route optimization. These are all evaluated in hybrid forms here along with their independent forms to promote optimum traffic flow selection. The algorithms about the solution time, utilization of memory, iterations at which the solution was found as optimum, and iteration time of the best-iteration are implemented by using an artificial highway network that includes 15 nodes and 33 segments. This experimentation clearly illustrates how EHO is tending towards swiftness in finding an optimum at approximately 0.1042 seconds while still consuming minimal memory. The GWO_PSO hybrid algorithm had balanced performance in route optimization, efficiently lowering computation time and memory consumption. The present study shall contribute to further insights into selecting an appropriate algorithm for each optimization goal with regard to ITS by considering system efficiency and the reduction of environmental impacts.