Development of an Efficient Path Planning Algorithm for Unmanned Aerial Vehicles - Wireless Sensor Networks in Agricultural Data Collection

Abstract

The increasing demand for precision agriculture has intensified the need for efficient data collection methods across expansive farmlands. This research focuses on the development of an efficient path planning algorithm for Unmanned Aerial Vehicles (UAVs) deployed in Wireless Sensor Networks (WSNs) to facilitate timely and energy-efficient agricultural data collection. The study proposes and evaluates a Particle Swarm Optimization (PSO)-based algorithm to optimize UAV trajectories concerning multiple conflicting objectives, including minimizing mission completion time, reducing energy consumption, and maximizing coverage efficiency through minimizing UAVs’ flight paths. A simulation model was implemented in Matrix Laboratory (MATLAB), considering realistic constraints such as UAV energy limits, communication range, sensor clustering, and agricultural field geometry. The performance of the developed algorithm was compared against the spherical particle swarm optimization algorithm (SPSO), Genetic algorithm (GA), and Random computation method (RCM). Results demonstrate that the developed PSO-based algorithm significantly outperforms others in terms of path length reduction, energy utilization, and mission completion time while maintaining high data collection accuracy. The findings validate the effectiveness of evolutionary optimization techniques in improving UAV-based WSN operations for precision agriculture, outperforming the benchmarking algorithms, with an average optimization efficiency over all the metrics of 23% compared to the random computation method (RCM) as the baseline algorithm. This work contributes a scalable and adaptable algorithmic approach suitable for real-world deployment in resourceconstrained agricultural environments.