复杂自适应多Agent系统的环境表示及感知  

Representing and Perceiving Environment of Complex Self-Adaptive Multi-Agent Systems

作　　者：董孟高[1,2] 毛新军[1] 郭毅[1] 齐治昌[1] 

机构地区：[1]国防科学技术大学计算机学院,长沙410073 [2]装备综合保障技术重点实验室,长沙410073

出　　处：《计算机研究与发展》2012年第2期402-412,共11页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(61070034);国家自然科学基金重点项目(90818028);教育部高等学校博士学科点专项科研基金项目(20094307110007);国家"九七三"重点基础研究发展计划基金项目(2011CB302601)

摘　　要：对自适应系统驻留环境的显式表示和有效感知是实现复杂自适应系统的前提,也是当前自适应系统研究面临的一项重要挑战.借助于组织学思想将自适应系统中的自主运行单元抽象为Agent,把复杂自适应系统视为多Agent组织,提出了基于动态绑定的自适应机制和构造框架;将环境作为一阶抽象,提供了对自适应多Agent组织的驻留环境进行抽象和描述的语言设施以及对环境进行有效感知的两种方法:基于事件发布-订阅和基于软传感器的方法;提出了支持软传感器与环境动态关联的思想和技术,使得复杂自适应系统的开发具有环境表示显式化、环境感知透明化的特征,所开发的软件系统易于维护和升级.介绍了实现上述机制、技术和语言设施的支撑平台SADE,并进行了案例分析以验证方法的可行性和有效性.Implementation of a self-adaptive system should be on the premise of explicitly representing and efficiently perceiving its environment, which is a challenge to the self-adaptive system research. In this paper, the autonomous entities in self-adaptive systems are abstracted as agents, and the complex self-adaptive systems are regarded as multi-agent organizations. Based on dynamic binding, we present an adaptive mechanism and its supporting framework to develop self-adaptive agents. In the framework, environment is regarded as the first-class abstraction, and a language is provided to abstract and describe the environment in which self-adaptive multi-agent organizations are situated. To perceive the environment efficiently, two approaches are presented based on event publish-subscrib and softsensor, and also the method of dynamic associating the relationship between softsensor and environment. Based on the approaches, the developed complex self-adaptive systems can represent their environment explicitly and perceive the environment transparently, and it is easy to maintain and upgrade those systems. This paper introduces the supporting platform SADE for the above mechanism, technology and language. In addition, a case study is presented to illustrate the feasibility and effectiveness of the proposed approaches.

关 键 词：自适应AGENT 环境 感知 动态绑定机制 多AGENT系统 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]