基于粗集理论的MIB变量开采

基于粗集理论的MIB变量开采 A Method of MIB Data Mining Based on Rough Set 郭成城 GUO Cheng cheng 1 first-author 左敏 ZUO Min 1 晏蒲柳 YAN Pu liu 1 武汉大学电子信息科学学院,湖北,武汉,430072 武汉大学电子信息科学学院,湖北,武汉,430072 School of Electronic Information Science, Wuhan University School of Electronic Information Science, Wuhan University 利用粗集理论对大量的 MIB（Manager inform ation base）变量进行数据挖掘 ,找出反映网络故障现象的 MIB变量组及其逻辑组合关系 .通过对网络故障采集的 MIB变量离散化 ,运用粗集方法去处错误和不必要的数据 ,提取表现故障现象的规则 ,并将规则用于设计计算机网络故障诊断程序 .给出了具体的分析过程和算法的实现步骤 . Illustrates an algorithm by which the relationship between MIB and network faults can be obtained. First a Decision Table is constructed by collecting original MIB data from networks, and then a reduction strategy based on Rough Set, including attribute reduction and rule generation, is implemented to remove inconsistent or erronrous MIB data, and accordingly concise information of network faults and relative MIB data is reserved. In this way the diagnostic rules for network faults can be obtained. These diagnostic rules are then used to design Computer Network Fault Diagnosis System, and are proved correct in this fault diagnosing system. Detailed data analysis procedure and algorithm developing steps are both specified in this paper. The expermental result verify the efficiency, high speed and high accuracy of this algorithm. 粗集理论 MIB变量 网络故障诊断 rough set MIB（Manager information base） computer network fault diagnosis TP393 国家自然科学基金 （ 69892 40 ）;国家 863计划资助项目 （ 863 -3 0 6-ZT0 5 -2 ） 2001-03-01 2021-04-01 3