基于数据挖掘技术的云计算服务器故障诊断

详细信息    查看全文 | 推荐本文 |

英文篇名：Fault Diagnosis of Cloud Computing Server Based on Data Mining Technology 作者：杨旭东 英文作者：Yang Xudong;Chongqing Vocational Institute of Safety & Technology; 关键词：云计算 ; 服务器故障 ; 诊断模型 ; 神经网络 ; 数据挖掘 英文关键词：cloud computing;;server failure;;diagnosis model;;neural network;;data mining 中文刊名：KJTB 英文刊名：Bulletin of Science and Technology 机构：重庆安全技术职业学院; 出版日期：2019-07-31 出版单位：科技通报 年：2019 期：v.35;No.251 语种：中文; 页：KJTB201907033 页数：5 CN：07 ISSN：33-1079/N 分类号：177-181

摘要

故障诊断是保证云计算服务器正常工作的关键技术,针对当前云计算服务器故障诊断模型存在的诊断正确率低,误判现象的缺陷,设计了基于数据挖掘技术的云计算服务器故障诊断模型。首先提取云计算服务器故障的信号,并对信号进行去噪处理,然后对云计算服务器故障诊断学习样本进行聚类分析,选择最优的样本子集,最后采用数据挖掘技术-极限学习机建立云计算服务器故障诊断分类器,并在Matlab 2014平台上进行了云计算服务器故障诊断仿真测试。结果表明,本文模型可以对云计算服务器故障特点进行准确挖掘,获得了正确率高的云计算服务器故障诊断结果,而且云计算服务器故障诊断误判率要远远低于当前其它模型,获得了理想的云计算服务器故障诊断结果。
        Fault diagnosis is the key technology to ensure the normal work of the cloud computing server.In view of the shortcomings of the current fault diagnosis model of the cloud computing server,the fault diagnosis model of cloud computing server based on data mining is designed. First,the signal is extracted from the fault of the cloud computing server,and the signal is de-noised. Then,the clustering analysis is carried out on the learning sample of the fault diagnosis of the cloud computing server,and the optimal subset is selected. Finally,the data mining technology-the limit learning machine is used to establish the fault diagnosis classifier for the cloud computing server,and the Matlab 2014 is flat. The cloud computing server fault diagnosis simulation test is carried out on the stage. The results show that the model can accurately excavate the fault characteristics of the cloud computing server,and obtain the fault diagnosis result of the cloud computing server with high correct rate,and the diagnosis rate of the fault diagnosis of the cloud computing server is far lower than the other models,and the ideal result of the cloud computing server's fault diagnosis is obtained.

引文

[1] Huebscher M C,Mcann J A. A survey of autonomic computing:Degrees, models, and applications[J].ACM Computing Surveys,2008,40(3):7-12.
    [2] Wang X, Wang Y. Coordinating power control and performance management for virtualized enterprise servers[J]. IEEE trans. on Parallel and Distributed Systems,2011,22(2):245-259.
    [3]白亚男,史永昌,史晓雨.基于自适应控制方法的云计算服务器性能管理[J].计算机与数字工程,2014,42(9):1668-1672.
    [4]董波,沈青,肖德宝.云计算集群服务器系统监控方法的研究[J].计算机工程与科学,2012,34(10):68-72.
    [5]郑洪源,周良,吴家祺.WEB服务器集群系统中负载平衡的设计与实现[J].南京航空航天大学学报,2006,38(2):347-351.
    [6]毛勇,金伟正.基于嵌入式Web服务器的远程故障诊断系统[J].电子技术应用,2003,3:23-24.
    [7]胡军,尹立群,李振,等.基于大数据挖掘技术的输变电设备故障诊断方法[J].高电压技术,2017,43(11):3690-3698.
    [8]马红光,韩崇昭,王国华,等.基于混沌和数据挖掘的电子系统故障诊断[J].数据采集与处理,2004,19(3):273-277.
    [9]黄蔓云,卫志农,孙国强,等.基于历史数据挖掘的配电网态势感知方法[J].电网技术,2017,41(4):1139-1144.
    [10]李宏升,顾才东.云计算大规模服务器故障诊断平台的设计[J].电网技术,2016,39(18):52-56.
    [11]刘念,张清鑫,李小芳.基于核函数极限学习机的分布式光伏短期功率预测[J].农业工程学报,2014,30(4):152-159.
    [12]黄纬,温志萍,程初.云计算中基于K-均值聚类的虚拟机调度算法研究[J].南京理工大学学报(自然科学版),2013,37(6):807-812.