Energy-efficient UAV routing optimization using genetic algorithms in dynamic logistics systems

Abstract

The pandemic’s impacts aside, the growth of e-commerce and the development of drone technology have increased demand for freight transportation on a worldwide scale. In order to address this demand, unmanned aerial vehicles, or UAVs, have emerged as a practical logistics solution. Optimizing cargo UAV routes is the aim of this study, as it is expected to play a significant role in today’s logistics systems. Using randomized sites, the proposed methodology takes into account the unique requirements and constraints of cargo UAVs while aiming to minimize energy usage during routing. An optimized Genetic Algorithm (GA) with a focus on vehicle routing problems (VRPs) is used to find the optimal route that meets the requirements.

Unlike conventional routing methods, which often assume fixed points for service requests, this methodology permits the assumption of random sites to better mimic real-world scenarios. Scalable solutions for various operational circumstances are provided by the algorithm due to its capacity to manage varying quantities of service-requesting points. The results of the experiments conducted with varying numbers of service-requesting points demonstrate the effectiveness of the proposed methodology. A respectable level of accuracy is revealed when comparing the exact solutions with the GA, particularly in situations with few points. Furthermore, the energy efficiency performance of the algorithm remains constant despite variations in the number of sites requesting services. All things considered, by concentrating on a particular objective, this work developed a revolutionary strategy for UAV routing optimization strategies to determine the best routes in dynamic, constantly changing logistical scenarios.