PSO-Based Multi-UAV Swarm Coordination for Flying Edge Machines in Precision Agriculture 4.0

Large-scale agricultural monitoring in Precision Agriculture 4.0 faces challenges related to limited UAV energy resources, inefficient field coverage, communication overhead, and the lack of intelligent coordination among multiple aerial platforms. These limitations reduce monitoring efficiency and hinder real-time agricultural decision-making. To address these challenges, this paper proposes a PSO-based multi-UAV swarm coordination framework for Flying Edge Machines in Precision Agriculture 4.0. The proposed AeroAgriNet framework integrates Particle Swarm Optimization (PSO), swarm intelligence, and edge computing to enable autonomous monitoring, distributed decision-making, and efficient resource utilization. Each UAV operates as a Flying Edge Machine capable of sensing, local processing, communication, and cooperative navigation. The framework was evaluated through MATLAB-based simulations in a 1000 × 1000 m agricultural environment consisting of 400 monitoring regions. Experimental results demonstrate that the proposed approach significantly outperforms random UAV movement, achieving 92% coverage compared to 61%, reducing energy consumption by 32%, decreasing mission completion time by 41%, and substantially lowering monitoring overlap and collision-risk events. The proposed framework can support real-time crop monitoring, agricultural surveillance, disease detection, precision farming operations, and next-generation smart agriculture systems requiring scalable, autonomous, and energy-efficient UAV swarm deployments.