Evolutionary Multi-objective Optimization Non-dominant Individual Selection Strategy Based on Internet of Things

As one of the important components of the Internet of Things (IoT), wireless sensor networks (WSN) are widely deployed to monitor, perceive and collect object information in real time, and then collect the information to the control center of IoT for various analysis and decision-making. In order to improve the positioning accuracy of node positioning technology and obtain a more balanced unloading decision, this paper studies the constrained multi-objective evolution problem based on evolutionary algorithm, and puts forward the non-dominant individual selection strategy of evolutionary multi-objective optimization to solve the contradiction between delay and energy consumption in IoT computing unloading technology. By adopting different optimization strategies for each archive set, each archive set can achieve the optimal search efficiency and reduce unnecessary crossover and mutation of the algorithm. The simulation results show that compared with the original algorithm, the algorithm with adaptive partition strategy has improved the uniformity and breadth of the optimal solution. The algorithm makes up for the deficiency of the diversity of traditional non-dominated individual selection methods, makes full use of the structural information of antibodies, and greatly improves the diversity of Pareto solutions.