基于均匀设计的多智能体遗传算法研究  

Research on multi-agent genetic algorithm based on uniform design

作　　者：梁昌勇[1] 陆青[1] 张恩桥[1] 魏兆旺[1] 

机构地区：[1]合肥工业大学计算机网络系统研究所,安徽合肥230009

出　　处：《系统工程学报》2009年第1期109-113,共5页Journal of Systems Engineering

基　　金：国家自然科学基金重点资助项目(70631003);国家自然科学基金资助项目(70771037);高校博士点基金资助项目(20050359006)

摘　　要：将均匀设计方法、多智能体系统与遗传算法相结合,提出了一种多智能体遗传算法.设计了基于均匀设计表的均匀种群初始化方法和均匀交叉算子,并将其引入算法中.算法通过智能体与智能体环境间的相互作用,以及智能体自学习提高自身能量,实现了复杂问题的全局优化目标.实验表明,该算法对于高维函数优化问题,尤其是高维多峰函数,具有很好的全局搜索能力和较快的收敛速度,能够避免陷入局部最优.A uniform design multi-agent genetic algorithm is proposed, which combines uniform design, multi-agent system with genetic algorithm. Methods of uniform population initialization and uniform crossover operator based on uniform design tables are introduced into the algorithm. Through the interaction between agents and agents＇ environment and the agents＇ self-learning to increase their energies, the algorithm can optimize complex problems globally. Experiments show that the algorithm can solve high-dimensional function optimization problems, especially the high-dimensional multimodal functions, with a good global search ability and a fast convergence rate, and can avoid falling into local optimum.

关 键 词：均匀设计 多智能体 遗传算法 多峰函数优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]