摘要
研究模型决策机制问题,模型库是决策支持系统的核心部分,为了提高决策支持系统模型库的通用性和可扩展性,提出了一种基于Agent的DSS模型库通用架构方法和标准化模型策略。主要研究基于Agent的模型表示策略、模型库系统架构及各功能Agent模型,详细阐述模型库中各功能构件的工作原理、模型Agent的自适应演化行为,并在JADE平台上完成了系统原型。实验证明,DSS方法可以带来模型与模型库的标准化,模型的复合也被转换成一个多Agent之间的协作问题,为当前模型库系统的建设提供了一个新的设计策略。
Model Base is the core of decision support system. In order to improve the versatility and scalability of Model Base of DSS, the paper presents a structure of MB of DSS based on Agent. It studies the Agent - based model representation strategy, Model Base System general Architecture, a variety of Agent Models prototype. It elaborates the working principle of each functional component of MB, running mechanisms of Model Agent, and designs a Model Base prototype based on JADE platform. The method can bring not only a self - adaptive capacity and learning ability for MB, but also the standardization for Model and MB for the reason that there is international standards in the field of Agent. The problem about the compound of Model has been converted into a problem about the collaboration between multi - Agent. The paper points out a new way to construct MB.
出处
《计算机仿真》
CSCD
北大核心
2009年第12期141-143,181,共4页
Computer Simulation
基金
十一五国家科技支撑计划(科技奥运专项)(2006BAK12B03)
上海市自然科学基金(06ZR14153)