Multi-objective Optimization Algorithm of Cross-border E-commerce Social Traffic Network based on Improved Particle Swarm Optimization

Abstract

The optimization algorithm known as Particle Swarm Optimization (PSO) is based on swarm intelligence and was created by modeling the foraging behavior of bird flocks. This study using the generalized regression neural network to improve particle swarm optimization (PSO) algorithm, proposed a target for cross-border electricity social network optimization algorithm PSO-PNNG, the simulation experiment in multiple real social network data environment and algorithm comparison, and the basic operation of genetic algorithm into the particle swarm algorithm, enhance the particle swarm optimization algorithm’s performance, speed up the convergence speed. In this study, three social network datasets obtained by real reptiles were used to solve the proposed PSO-PNNG algorithm in a real social network data environment. The findings of the experiment indicate that the suggested multi-objective optimization algorithm for cross-border e-commerce social traffic network based on improved PSO has higher efficiency and accuracy than the traditional method.