Energy-Efficient Task Allocation for Rotary-Wing Swarm UAV in IoT Networks Using Improved Particle Swarm Optimization

Unmanned Aerial Vehicles (UAVs) are becoming more frequently used in Internet of Things (IoT) settings to gather data, perform surveillance, and conduct monitoring. Nevertheless, the maximum battery capacity onboard is still a significant limitation to rotary-wing swarm UAV operations. Effective task assignment programs are thus needed to increase energy saving and improve mission life. The paper suggests an Improved Particle Swarm Optimization (IPSO) algorithm to use in allocating energy-efficient tasks to swarm UAV networks in rotary-wing swarm networks. The proposed approach also has an adaptive inertia weight mechanism that enhances convergence behavior and helps avoid untimely stagnation. Python is used to create a simulation environment with multiple UAVs and distributed, IoT sensor nodes. The overall energy consumption and convergence rate are used to measure the performance of the proposed IPSO approach. The simulation findings show that the IPSO algorithm has reduced energy consumption and convergence velocity than the traditional PSO, and thus it can be used in energy-conscious UAV swarm tasks in IoT-based applications.