异构资源分配问题的多智能体系统求解方法.pdfVIP

Vo l. 50 No.6 吉林大学学报(理学版) 第 50 卷第6 期 Journal of Jilin University (Science Edition) Nov 2012 2012 年 11 月 异构资源分配问题的多智能体系统求解方法关 孙婷婷l ，徐杨1 ，周瑛1.2 (1.电子科技大学计算机科学与工程学院，成都 610054; 2. 淄博职业学院电子电气工程学院，山东淄博 25531的 摘要:采用多智能体系统求解方法，将异构资源分配问题建模于分布式广义分配问题框架 下，利用智能体间的联合有哪些信誉好的足球投注网站实现复杂异构资源分配问题的高效求解.先利用前期有哪些信誉好的足球投注网站过程 中获得的知识，智能体预测谁更有能力求解当前子问题;再通过建立决策模型，智能体动态、 智能地改变有哪些信誉好的足球投注网站顺序，以加速全局可行解的求解.该非集中式框架能提高问题的求解效率， 增加动态可扩展性.实验结果表明了该方法的可行性. 关键词:异构资源分配问题;多智能体系统;分布式广义分配问题;启发式算法 中图分类号: TP30 1. 6 文献标志码:A 文章编号: 1671-5489(2012)O6-1163-06 Solving Heterogeneous Resource Allocation Problem by Multi-agent Systems 1 1 12 SUN Ting-ting , XU Yang , ZHOU PU . (1. School of Computer Science Eηgineering ， University of Electronic Science aηd Technology of China , Chengdu 610054 , China; 2. School 0f Electrical and Electronic Engineering , Zi加 νocational Institute , Zibo 255314 , Shandong Province , China) Abstract: The authors proposed a multi-agent cooperation method to solve heterogeneous resource allocation problem in a distributed way. When the problem is put into the architecture of distributed generalized assignment problem , the large problem is separated into many small ones and each agent is responsible for a part of the solution. By means of the knowledge from their previous communica- tion searches , agents are able to predict how to deploy their future similar searches more efficiently. Therefore , if an agent can solve some parts well , similar searches will be sent to it. Using this method , we may avoid the shortcomings mentioned a