作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2010, Vol. 36 ›› Issue (19): 168-170. doi: 10.3969/j.issn.1000-3428.2010.19.058

• 人工智能及识别技术 • 上一篇    下一篇

基于QPSO的单任务Agent联盟形成

许 波1,余建平2   

  1. (1. 广东石油化工学院计算机科学与技术系,广东 茂名 525000;2. 湖南师范大学数学与计算机科学学院,长沙 410081)
  • 出版日期:2010-10-05 发布日期:2010-09-27
  • 作者简介:许 波(1982-),男,助教、硕士,主研方向:智能计算,云计算,信息安全;余建平,讲师、博士
  • 基金资助:
    国家自然科学基金资助项目(60903168);广东石油化工学院青年创新人才培育基金资助项目(2010YC09)

Agent Coalition Formation for Single Task Based on Quantum-behaved Particle Swarm Optimization

XU Bo1, YU Jian-ping2   

  1. (1. Department of Computer Science and Technology, Guangdong University of Petrochemical Technology, Maoming 525000, China; 2. College of Mathematics and Computer Science, Hunan Normal University, Changsha 410081, China)
  • Online:2010-10-05 Published:2010-09-27

摘要: 智能群体搜索算法在求解单任务Agent联盟时稳定性较差、收敛速度慢、全局寻优能力不强,因此采用优化的量子粒子群优化算法解决上述问题。利用群体历史优质解,在最优粒子变异的基础上,采用多种群并行搜索,防止陷入局部极值,并对粒子群进行筛选以加快粒子群的收敛速度。对比实验结果表明,该算法可以快速、高效地找出合适的Agent联盟,在运行时间和解的质量方面优于同类算法。

关键词: Agent联盟, 量子粒子群优化算法, 组合优化, 多Agent系统

Abstract: There are some problems such as slow convergence, low stability and poor global optimization ability when intelligent search algorithms solve single task Agent coalition. This paper uses an improved Quantum-behaved Particle Swarm Optimization(QPSO) to solve the problems. By using the better recording locations of all particles and the mutation of the best behaved particle, and based on public history researching Parallel, the particle swarm is filtrated and the convergence speed is accelerated. Multiple particle swarms are used to research parallel, avoiding running into local optima. Comparative experimental results show that the algorithm can identify the Agent alliance quickly and efficiently. Its run-time performance is better than other algorithms.

Key words: Agent coalition, Quantum-behaved Particle Swarm Optimization(QPSO) algorithm, combinatorial optimization, Multi-Agent system

中图分类号: