多Agent系统分布式问题求解的代数模型方法(Ⅱ):群体智能和社会动力学  

A New Algebraic Modeling for Distributed Problem-Solving of Multi-Agent Systems(PartⅡ): Colony Intelligence and Social Dynamics

作　　者：帅典勋[1] 顾静 

机构地区：[1]华东理工大学计算机科学与工程系 [2]朗讯科技(中国)有限公司,上海200230

出　　处：《计算机学报》2002年第2期138-147,共10页Chinese Journal of Computers

基　　金：国家自然科学基金重点项目 (60 13 5 0 10 );国家"九七三"重点基础研究发展规划项目(G19990 3 2 70 7);国家自然科学基金项目 (60 0 73 0 0 8);清华大学智能技术和系统国家重点实验室开放课题基金;高校重点实验室访问学者基金的资助和支持

摘　　要：该文是组合论文中第二篇 ,讨论多 Agent系统分布式问题求解的代数模型中的特性层和动力学层 ,即不同粒度 Agent群体的宏观群体智能的形式化代数模型以及宏观社会智能与 Agent个体间微观社会行为之间的社会动力学模型 .提出了基于这种新的代数模型方法的超分布超并行社会智能问题求解算法 .关于分布式多任务自组织规划和资源自组织分配的仿真实验以及与其它方法的比较分析 。This paper, as the second of companion papers, discusses the property level and the dynamics level of the algebraic modeling for distributed problem solving in multi agent systems. An algebraic formalization of macro intelligent properties defined over agent colonies with different granularities is presented, which tries to explore the essential features of social intelligence and to describe the relation between macroscopic social intelligence and microscopic social interactions among agent individuals. The social dynamics associated with social intelligence is also addressed. As a result, a new hyper distributed hyper parallel algorithm for problem solving in multi agent systems is obtained. The simulation on distributed self organizing multi task allocations and resource assignments, and the comparisons with other conventional methods show many advantages of the proposed algebraic approach.

关 键 词：多AGENT系统 分布式人工智能 分布式问题求解 代数模型 群体智能 社会动力学 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]