小时间尺度网络数据传输故障识别数学建模  

Mathematical Modeling for Fault Identification in Small Time Scale Network Data Transmission

作　　者：肖金桐 田亮[2,3,4] 王艳君 XIAO Jin-tong;TIAN Liang;WANG Yan-jun(Hebei University of Water Resources and Electric Engineering,Cangzhou Hebei 061000,China;College of Computer and Cyber Security,Hebei Normal University,Shijiazhuang Hebei 050024,China;Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security,Hebei Shijiazhuang 050024,China;Hebei Digital Education Collaborative Innovation Center,Hebei Shijiazhuang 050024,China)

机构地区：[1]河北水利电力学院,河北沧州061000 [2]河北师范大学计算机与网络空间安全学院,河北石家庄050024 [3]供应链大数据分析与数据安全河北省工程研究中心,河北石家庄050024 [4]河北省数字教育协同创新中心,河北石家庄050024

出　　处：《计算机仿真》2024年第6期507-511,共5页Computer Simulation

基　　金：2020年河北省教育厅教改项目(2020GJXGK012);2021年河北师范大学科技类科研基金项目(L2021B39)。

摘　　要：在网络传输过程中,数据容量较大,受外界因素影响极易导致传输中断,从而出现信息缺失与传输误码。为解决中断故障造成的数据传输误差和缺失问题,提高网络利用率,保证网络的正常通信。因此,提出一种小时间尺度网络数据传输故障识别数学建模。建立传输的容错控制条件,分析小时间尺度网络的混沌状态和流量序列,描述网络中多层前向特征,调整各个尺度下权重和阈值。设定容错策略,对小时间尺度网络多项训练,得到网络的中断故障诊断。针对性预测缺失数据,通过函数计算预测误差及序列权重等参数,获得故障隶属度层和规则集合层间调节权值,完成中断故障容错识别。实验证明,所提方法提高了网络传输召回率,增加网络资源利用率,减少网络在中断故障下的传输误码率。In the process of network transmission,the data capacity is large,which is easily interrupted by external factors,resulting in information loss and transmission errors.To solve the problem of data transmission errors and missing caused by interruption faults,improve network utilization,and ensure normal communication of the network.Therefore,a mathematical model for identifying faults in small-scale network data transmission is proposed.Establish fault-tolerant control conditions for transmission,analyze the chaotic state and traffic sequence of small time scale net⁃works,describe multi-layer forward features in the network,and adjust weights and thresholds at each scale.Set a fault-tolerant strategy,train multiple small time scale networks,and obtain network interruption fault diagnosis.Targe⁃ted prediction of missing data is achieved by calculating parameters such as prediction error and sequence weights through functions,and adjusting weights between the fault membership level and rule set level to complete fault toler⁃ance identification for interruptions.Experiments have shown that the proposed method improves the network transmis⁃sion recall rate,increases network resource utilization,and reduces the transmission error rate of the network under in⁃terruption faults.

关 键 词：小时间尺度网络 网络流量 混沌理论 中断故障 容错识别 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]