动态环境下几个改进微粒群算法的性能比较

微粒群算法是一种模拟动物群体行为的随机优化算法,而且已经提出了许多改进策略,然而,受各种不确定因素的干扰,现实世界中很少有系统是静态的,因此动态优化问题的研究更具有实际的工程意义。为此,在动态环境下,用最近提出的两个改进微粒群算法同标准微粒群算法以及其他两个高性能的改进微粒群算法进行性能比较和分析。通过比较,本文得出在不同的动态环境下,不同的算法表现出了相异的特点。

Performance Comparison of Several Improved Particle Swarm Optimizers in Dynamic Environment

Particle Swarm Optimization（PSO） is a new selfadaptive random search methodology inspired by social behaviour of animal.Many strategys have been introduced to improve the performance of PSO,but few system is static in the real world because of the various uncertain factors.So the researches on Dynamic Optimization Problems have more practical significance of the project.This paper compares and analyzes the performances of the two latest improved PSO and the other two improved algorithms.It is concluded that the different algorithms put up different characteristics in dynamic environment.