An improved multi-objective optimization-based method for UAV-assisted industrial IoT data collection

An efficient Industrial Internet of Things (IIoT) data collection system is crucial for data-driven decision-making in smart factory construction. However, traditional fixed ground station collection methods face challenges such as inflexible deployment, high infrastructure costs, and poor environmental adaptability. To address these issues, this paper proposes a UAV-assisted data collection system based on multi-objective optimization. First, a mathematical model for UAV-assisted data collection is constructed by comprehensively considering factors including UAV hovering position selection, device access sequence planning, flight speed control, and terminal device transmission power adjustment. The model aims to simultaneously maximize the minimum data transmission rate of all devices while minimizing both device total energy consumption and UAV total energy consumption. Second, an improved multi-objective particle swarm optimization algorithm incorporating dynamic inertia weight and Levy flight mechanism is designed to solve this model. Through simulation experiments under different industrial plant topologies, the performance of random deployment and uniform deployment strategies are comparatively analyzed. Results demonstrate that the proposed algorithm outperforms existing baseline algorithms in key indicators such as data transmission efficiency and energy consumption, providing effective technical support for data-driven intelligent manufacturing.