Optimizing 3D coverage in underwater wireless sensor networks via parallel particle swarm optimization

Underwater Wireless Sensor Networks (UWSNs) are pivotal for sustainable ocean monitoring, yet achieving reliable 3D coverage remains challenging due to dynamic environments and resource constraints. This paper presents a parallel Particle Swarm Optimization (PSO) framework that maximizes coverage while minimizing energy consumption. By integrating grid-based spatial modeling and MATLAB’s Parallel Computing Toolbox, our method dynamically adjusts inertia weights and velocity constraints to avoid local optima. Experimental results demonstrate an 86.7% coverage rate within 310 iterations—surpassing conventional PSO by 12.5% and genetic algorithms by 8.2%—with a 35% reduction in convergence time. The proposed approach not only addresses scalability issues in large-scale deployments but also provides a computationally efficient solution adaptable to real-time environmental changes. This work advances marine monitoring technologies by enabling energy-efficient, high-coverage sensor networks, with potential applications in tsunami early warning systems and underwater infrastructure protection.