首页> 外文会议>International conference on swarm intelligence >The Analysis of Strategy for the Boundary Restriction in Particle Swarm Optimization Algorithm
【24h】

The Analysis of Strategy for the Boundary Restriction in Particle Swarm Optimization Algorithm

机译:粒子群优化算法的边界约束策略分析

获取原文

摘要

Particle swarm optimization has been applied to solve many optimization problems because of its simplicity and fast convergence performance. In order to avoid precocious convergence and further improve the ability of exploration and exploitation, many researchers modify the parameters and the topological structure of the algorithm. However, the boundary restriction strategy to prevent the particles from flying beyond the search space is rarely discussed. In this paper, we investigate the problems of the strategy that putting the particles beyond the search space on the boundary. The strategy may cause PSO to get stuck in the local optimal solutions and even the results cannot reflect the real performance of PSO. In addition, we also compare the strategy with the random updating strategy. The experiment results prove that the strategy that putting the particles beyond the search space on the boundary is unreasonable, and the random updating strategy is more effective.
机译:粒子群算法由于其简单性和快速收敛性能而被应用于解决许多优化问题。为了避免早熟的收敛并进一步提高勘探和开发能力,许多研究人员修改了算法的参数和拓扑结构。但是,很少讨论防止粒子飞出搜索空间的边界限制策略。在本文中,我们研究了将粒子置于边界上的搜索空间之外的策略的问题。该策略可能会导致PSO陷入局部最优解中,甚至结果也无法反映PSO的实际性能。此外,我们还将策略与随机更新策略进行了比较。实验结果证明,将粒子置于搜索空间边界之外的策略是不合理的,随机更新策略更为有效。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号