基于模糊盟友关系的多主体系统长期联盟

Long-Term MAS Coalition Based on Fuzzy Relation

多Agent系统形成长期联盟有利于降低计算复杂度、改善盟友关系·Breban和Griffiths等人研究了Agent之间的信任关系,但计算复杂度高、可行性差·长期联盟形成的模糊盟友关系的提出,可以合理地描述长期联盟Agent之间的盟友关系·通过监控Agent之间的交互更新盟友关系,降低盟友关系的计算复杂度,提高盟友关系计算的实时性,深化了Breban和Griffiths的工作,仿真结果验证了该方法的可靠性和实用性·该方法是长期联盟和组织的形成、演化研究基础·

Long-term coalition of MAS has several advantages such as decreasing cost, maintaining coalition stability and improving relation. Breban and Griffiths researched trust relation among agents. But there is no feasible relation algorithm. A fuzzy relation of long-term coalition is proposed which can compute the relation value of members easily and effectively. This method reasonably describes fuzzy relation of longterm coalition. Through monitoring agent interaction, it can update the fuzzy relation. Its advantages are the decrease of computing complexity and the effectiveness improvement. It improves the work of Breban and Griffiths. The simulation result demonstrates the reliability and practicality of this method. The method is the basis of forming and evolvement research of long-term coalition and organization.