Improved energy efficient localization of UAVs in farmlands using hybrid metaheuristic optimization algorithms

Vast farmlands and areas that require pesticide application are often irregular and fragmented, necessitating the use of unmanned aerial vehicles (UAVs) for pesticide spraying where onboard processing takes place. This work outlines a new optimization approach specific for accurate UAV positioning and application of pesticides on vast farming landscapes. The proposed frameworks the hybrid Grasshopper Optimization Algorithm (GOA) with the Genetic Algorithm(GA) called hybrid GOA-GA , hybridization of Particle Swarm Optimisation with Ant Colony Optimisation Algorithm is called hybrid PSO-ACO and hybridization of Particle Swarm Optimisation with Grey Wolf Optimisation Algorithm is called hybrid PSO-ACO for designing UAV flight patterns that offer the broadest coverage of the crops in the least time possible while expending the least quantity of pesticide. The low latency and high bandwidth benefits of 5G (5th generation mobile communication) coordinates from ground-based anchor nodes are used to estimate the UAV position while using path planning in real-time during operations. The involvement of comprehensive simulation studies confirms the efficiency of the proposed approach to increase the effectiveness of pesticide application by up to 40% and reduce resource usage compared to traditional methods