基于多Agent的分布式IP网故障诊断系统设计与实现  

Design and Implementation of Distributed IP Network Fault Diagnosis System Based on Multi-agent System

作　　者：史春光[1] 刘波[1] 彭进霖 常丽萍[1] 

机构地区：[1]太原卫星发射中心技术部,山西太原030027 [2]北京跟踪与通信技术研究所,北京100094

出　　处：《装备学院学报》2016年第6期95-99,共5页Journal of Equipment Academy

摘　　要：为便于及时定位并排除典型网络故障,以数据包分析为基础,基于多Agent系统,设计实现了一种便于扩展的分布式IP网故障诊断系统。该系统采用网络端口镜像的方式进行数据采集,采用伯克利数据包过滤器(BPF)包过滤机制进行数据包过滤,基于专家系统进行典型网络故障诊断。此外,系统采用三元组〈实体,属性,规则集〉进行知识表示,用支持度表示规则出现的频率。实际应用表明,该系统可有效地帮助网络维护人员及时了解网络状态,快速、准确地诊断典型网络故障。To locate and eliminate typical network faults in time,the paper designs an expandable distributed IP network fault diagnosis system based on data packet analysis and multi-agent system.The system adopts the method of network port mirroring to collect data,conducts data filtering with Berkeley Packet Filtering（BPF）mechanism,and performs network fault diagnosis based on expert system.In addition,the system uses triple〈entity,attribute and rule set〉to realize knowledge representation,and represent the frequency of the rule appearance by support degree.The practical application shows that the system can effectively help network maintenance personnel to know the network status in time and quickly and accurately diagnose typical network faults.

关 键 词：故障诊断 多AGENT系统 专家系统 

分 类 号：TP393.1[自动化与计算机技术—计算机应用技术]