基于范例推理的合同网模型  

Contract Net Model Based on Case Based Reasoning

作　　者：万武南[1] 王晓京[1] 宋春雨[1] 刘旸[1] 

机构地区：[1]中国科学院成都计算机应用研究所自动推理实验室,四川成都610041

出　　处：《小型微型计算机系统》2005年第9期1578-1581,共4页Journal of Chinese Computer Systems

基　　金：国家"九七三"计划项目(2004CB318003)资助.

摘　　要：合同网是一类重要的基于竞争机制的协同问题求解模型,它一般不对竞争者范围进行限制,采用广播方式发布任务,消费了大量通讯负载,因此不能保证高的工作效率.为了减少Agent之间的通讯负载和协商时间,提高工作效率,本文在合同网模型中引入范例推理,使用范例推理来确定合适的投标竞争者,缩小问题竞争者范围;同时本文在范例中加入了时间因子和遗忘系数等参数,以及一类特殊的范例,有助于改善合同网协作过程,使得系统具有较好的灵活性和适应性.The contract net is an important model for problem solving based on the competitive mechanism and it does not place any limits on competitors in general, but the broadcast of the Task Announcement on Contract Net Protocol tends to consume much communication load ,therefore it does not ensure the high efficiency. In order to achieve high performance and reduce cost of resource and communication,contract net protocol based on case based reasoning is presented, it can decrease the scope of competitors, make a distinct improvement to the efficiency. Several parameters such as forget coefficient,time coefficient and a special case are introduced into case based reasoning to ensure a better cooperation between agents and higher flexibility of sys- tem.

关 键 词：合同网 任务分配 范例推理 多AGENT 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]