云计算光纤网络中大数据异常负载检测模型
|
摘要
云计算光纤网络中大数据出现异常负载时容易导致网络中断,为了确保光纤网络的连通性,提出一种基于高阶统计量特征提取的云计算光纤网络中大数据异常负载检测模型。采用非线性时间序列分析方法进行云计算光纤网络中大数据异常负载信息流建模,对异常负载信息流采用高阶统计量分析方法进行特征重构;采用时频分析方法提取异常负载的统计特征量,结合极限学习方法进行异常负载检测的自适应修正,在滑动平均窗口中进行云计算光纤网络大数据异常负载的谱密度分析和特征检测;根据高阶统计量的异常谱分布实现大数据异常负载检测。仿真结果表明,采用所提方法进行云计算光纤网络中大数据异常负载检测的准确性较高,抗干扰能力较强,整体更具优势。
In the cloud computing fiber network,the abnormal load of big data is easy to cause network interruption. In order to ensure the connectivity of the fiber network,a big data abnormal load detection model in cloud computing fiber network based on high-order statistic feature extraction is proposed. The nonlinear time series analysis method is used to model the big data abnormal load information flow in the cloud computing fiber network,and the high-order statistic analyzing method is used to reconstruct the feature of the abnormal load information flow. The time-frequency analyzing method is used to extract the statistical characteristics of the abnormal load,and then adaptively correct the abnormal load detection combined with limit learning method. Realizing the big data abnormal load detection based on abnormal spectrum distribution of high-order statistics. The simulation results show that the proposed method is more accurate in the detection of big data abnormal load in cloud computing fiber network,the anti-interference ability is stronger,and the overall is better.
In the cloud computing fiber network,the abnormal load of big data is easy to cause network interruption. In order to ensure the connectivity of the fiber network,a big data abnormal load detection model in cloud computing fiber network based on high-order statistic feature extraction is proposed. The nonlinear time series analysis method is used to model the big data abnormal load information flow in the cloud computing fiber network,and the high-order statistic analyzing method is used to reconstruct the feature of the abnormal load information flow. The time-frequency analyzing method is used to extract the statistical characteristics of the abnormal load,and then adaptively correct the abnormal load detection combined with limit learning method. Realizing the big data abnormal load detection based on abnormal spectrum distribution of high-order statistics. The simulation results show that the proposed method is more accurate in the detection of big data abnormal load in cloud computing fiber network,the anti-interference ability is stronger,and the overall is better.
引文
[1]王宝进,吴淑跃,薛娟.SDD-1改进算法在Hive中应用[J].湘潭大学自然科学学报,2014,36(4):77-82.
[2]李艳婷,张红伟,师星辰,等.离散多音调制可见光信道非线性失真及参数优化[J].光电子.激光,2014,25(1):82-88.
[3] GUO H,LIU H,WU C,et al.Logistic discrimination based on G-mean and F-measure for imbalanced problem[J].Journal of Intelligent and Fuzzy Systems,2016,31(3):1155-1166.
[4] XV Y,TONG S,LI Y.Prescribed performance fuzzy adaptive fault-tolerant control of non-linear systems with actuator faults[J].IET Control Theory and Applications,2014,8(6):420-431.
[5] HUANG X,WANG Z,LI Y,et al. Design of fuzzy state feedback controller for robust stabilization of uncertain fractional-order chaotic systems[J].Journal of the Franklin Institute,2015,351(12):5480-5493.
[6]孙媛凯,谢涛,李英娜,等.变压器漏磁热损特征与光纤光栅监测研究[J].激光与红外,2017,47(1):92-97.
[7]唐小川,罗亮.基于析因设计的大数据相关关系挖掘算法[J].计算机应用,2018,38(9):2507-2510.
[8]梁吉业,冯晨娇,宋鹏.大数据相关分析综述[J].计算机学报,2016,39(1):1-18.
[9]李晨,申德荣,朱命冬,等.一种对时空信息的k NN查询处理方法[J].软件学报,2016,27(9):2278-228
[10] JU C H,ZOU J B.An incremental classification algorithm for data stream based on information entropy diversity measure[J]. Telecommunications Science,2015,31(2):86-96.
[11] LYU Y X,WANG C Y,WANG C,et al.Online classification algorithm for uncertain data stream in big data[J].Journal of Northeastern University(Natural Science Edition),2016,37(9):1245-1249
[12] CHEN Y,LI L J.Very fast decision tree classification algorithm based on red-black tree for data stream with continuous attributes[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2017,37(2):86-90.
[13]王清,龚晓峰,雒瑞森.基于圆阵虚拟阵列平移的相干信源数目估计[J].计算机工程,2018,44(9):78-82.
[14]赵太飞,王文科,刘龙.WDM光网络中一种优先共享通路保护算法[J].激光技术,2012,36(3)408-412.
[15]秦宁宁,余颖华,吴德恩.移动混合传感网中节点自主部署算法[J].电子与信息学报,2016,38(7):1838-1842.
[16]杨景明,侯宇浩,孙浩,赵志伟.采用数量级阈值与二维信息排序策略的NSGA-II-DE算法[J].控制与决策,2016,31(09):1577-1584.
[17]曹玉林,王小明,何早波.移动无线传感网中恶意软件传播的最优安全策略[J].电子学报,2016,44(8):1851-1857.
[2]李艳婷,张红伟,师星辰,等.离散多音调制可见光信道非线性失真及参数优化[J].光电子.激光,2014,25(1):82-88.
[3] GUO H,LIU H,WU C,et al.Logistic discrimination based on G-mean and F-measure for imbalanced problem[J].Journal of Intelligent and Fuzzy Systems,2016,31(3):1155-1166.
[4] XV Y,TONG S,LI Y.Prescribed performance fuzzy adaptive fault-tolerant control of non-linear systems with actuator faults[J].IET Control Theory and Applications,2014,8(6):420-431.
[5] HUANG X,WANG Z,LI Y,et al. Design of fuzzy state feedback controller for robust stabilization of uncertain fractional-order chaotic systems[J].Journal of the Franklin Institute,2015,351(12):5480-5493.
[6]孙媛凯,谢涛,李英娜,等.变压器漏磁热损特征与光纤光栅监测研究[J].激光与红外,2017,47(1):92-97.
[7]唐小川,罗亮.基于析因设计的大数据相关关系挖掘算法[J].计算机应用,2018,38(9):2507-2510.
[8]梁吉业,冯晨娇,宋鹏.大数据相关分析综述[J].计算机学报,2016,39(1):1-18.
[9]李晨,申德荣,朱命冬,等.一种对时空信息的k NN查询处理方法[J].软件学报,2016,27(9):2278-228
[10] JU C H,ZOU J B.An incremental classification algorithm for data stream based on information entropy diversity measure[J]. Telecommunications Science,2015,31(2):86-96.
[11] LYU Y X,WANG C Y,WANG C,et al.Online classification algorithm for uncertain data stream in big data[J].Journal of Northeastern University(Natural Science Edition),2016,37(9):1245-1249
[12] CHEN Y,LI L J.Very fast decision tree classification algorithm based on red-black tree for data stream with continuous attributes[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2017,37(2):86-90.
[13]王清,龚晓峰,雒瑞森.基于圆阵虚拟阵列平移的相干信源数目估计[J].计算机工程,2018,44(9):78-82.
[14]赵太飞,王文科,刘龙.WDM光网络中一种优先共享通路保护算法[J].激光技术,2012,36(3)408-412.
[15]秦宁宁,余颖华,吴德恩.移动混合传感网中节点自主部署算法[J].电子与信息学报,2016,38(7):1838-1842.
[16]杨景明,侯宇浩,孙浩,赵志伟.采用数量级阈值与二维信息排序策略的NSGA-II-DE算法[J].控制与决策,2016,31(09):1577-1584.
[17]曹玉林,王小明,何早波.移动无线传感网中恶意软件传播的最优安全策略[J].电子学报,2016,44(8):1851-1857.