面向战场信息共享的Agent动态聚类算法研究  

Research and Implementation of battle Field Information Sharing System Based on Multi Agent

作　　者：于晓浩[1] 常国岑[1] 胡丹[1] 刘鹏[1] 

机构地区：[1]空军工程大学电讯工程学院

出　　处：《微计算机信息》2007年第24期271-273,共3页Control & Automation

基　　金：空军信息化建设关键技术研究(KGD04355A)

摘　　要：针对联合作战中分布、动态的战场环境和海量的战场信息,满足不同作战实体对战场信息资源共享的需求。构建了一个基于多智能体的、面向作战任务的信息资源共享模型,并在考虑战场信息时效性的前提下提出了一种新颖的基于相似度的用户动态聚类方法,从用户的资源请求中发现用户兴趣和用户之间的相似度,通过交互机制有效的将相同兴趣的用户及资源智能体关联起来,提高作战主体获取战场信息的能力。实验证明该算法具有较高的效率和良好的可扩展性。To content the requirement of different unit in warfare information sharing, several design issues need to be addressed such as the distributed and the dynamic nature of the environment, and the large size of the information. To this end, The paper propose a multi-agent architecture based on battle tasks. To advance the unit＇s ability in gathering the warfare information, it presents an effective algorithms based on similarity degree, which can not only find the user＇s interest and similarity degree from the dynamic resource requests but also cluster learners and resource agent with similar interest. Experiments show that this algorithm has steadily improved efficiency and scalability.

关 键 词：信息共享 多智能体 协作 动态聚类 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] V271.47[自动化与计算机技术—控制科学与工程]