基于AOA-MSVM的控制集群故障检测方法

doi:10.3969/j.issn.1006-2475.2023.12.019

摘要/Abstract

摘要： 摘要：控制集群系统的复杂性和多样性导致集群系统易发生故障，从而降低集群系统的可用性。针对现有的故障检测方法存在的检测效率和准确度较低、故障类型难以有效自动识别等问题，本文提出一种基于改进的自适应算术优化的多类支持向量机（Arithmetic Optimization Algorithm-Multi-class SVM， AOA-MSVM）的控制集群故障检测方法来检测集群中的故障，以提高集群系统的可用性。首先，运用局部线性嵌入算法对集群系统中监测到的系统信息进行降维；然后，针对集群系统中故障种类多的特点，运用一对多支持向量机的方法构建故障检测模型，提升检测故障的能力；最后，使用改进的自适应算术优化算法对模型参数求最优解。搭建高可用控制集群系统进行对比实验，实验结果表明，本文提出的故障检测方法具有更高的检测效率和准确度并可有效识别故障类型。

关键词: 关键词：故障检测, 集群, 多类支持向量机, 算术优化算法

Abstract: Abstract： The complexity and diversity of the control cluster system lead to the easy failure of the cluster system，which reduces the availability of the cluster system. In view of the problems in the existing fault detection methods，such as low detection efficiency and accuracy，and difficulty in effective automatic identification of fault types，in this paper，a control cluster fault detection method based on an improved adaptive Arithmetic Optimization Algorithm-Multi-class SVM （AOA-MSVM） is proposed to detect cluster faults in order to improve the availability of the cluster system. Firstly，the local linear embedding algorithm is used to reduce the dimensionality of the system information detected in the cluster system. Then，according to the characteristics of multiple kinds of faults in the cluster system，the method of one-to-many support vector machine is used to build a fault detection model to improve the ability of fault detection. Finally，the improved adaptive arithmetic optimization algorithm is used to obtain the optimal solution of the model parameters. A high availability control cluster system is set up for comparative experiments. The experimental results show that the proposed fault detection method has higher detection efficiency and accuracy and can effectively identify the fault type.

Key words: Key words： fault detection, cluster, multi-class support vector machine, arithmetic optimization algorithm

中图分类号:

TP391

杨博, 庄毅. 基于AOA-MSVM的控制集群故障检测方法[J]. 计算机与现代化, 2023, 0(12): 112-116.

YANG Bo, ZHUANG Yi. Fault Detection Method of Control Cluster Based on AOA-MSVM[J]. Computer and Modernization, 2023, 0(12): 112-116.

参考文献［30］

［1］	COULOURIS G， DOLLIMORE J， KINDBERG T， et al. Distributed Systems： Concepts and Design［M］. Addison-Wesley，2011.
［2］	VERMA A，PEDROSA L，KORUPOLU M，et al. Large-scale cluster management at Google with Borg［C］// Proceedings of the 10th European Conference on Computer Systems. 2015. DOI： 10.1145/2741948.2741964.
［3］	THUSOO A， SHAO Z， ANTHONY S， et al. Data warehousing and analytics infrastructure at facebook［C］// Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data. 2010：1013-1020.
［4］	SOMASEKARAM P，CALINESCU R，BUYYA R. High-availability clusters： A taxonomy，survey，and future directions［J］. Journal of Systems and Software，2022,187. DOI： 10.1016/j.jss.2021.111208.
［5］	LIN Q W， HSIEH K， DANG Y N， et al. Predicting node failure in cloud service systems［C］// Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2018：480-490.
［6］	YAO D F，SHU X K，CHENG L，et al. Anomaly Detection as a Service： Challenges，Advances，and Opportunities［M］. Morgan & Claypool Publishers，2017.
［7］	IBIDUNMOYE O，HERNANDEZ-RODRIGUEZ F，ELMR
	OTH E. Performance anomaly detection and bottleneck identification［J］. ACM Computing Surveys （CSUR），2015,48（1）. DOI： 10.1145/2791120.
［8］	张夏豪. 面向云数据中心计算资源的可靠性保障技术研究［D］. 南京：南京航空航天大学， 2020.
［9］	GUAN Q，ZHANG Z M，FU S. Ensemble of Bayesian predictors and decision trees for proactive failure management in cloud computing systems［J］. Journal of Communications，2012,7（1）：52-61.
［10］	AREFIN A，SINGH V K，JIANG G F，et al. Diagnosing data center behavior flow by flow［C］// Proceedings of the 2013 IEEE 33rd International Conference on Distributed Computing Systems. 2013：11-20.
［11］	王开放. 云环境下基于LSTM和SVM的虚拟机故障预测模型［J］. 信息技术，2022,46（10）：108-112.
［12］	ADAMU H，MOHAMMED B，MAINA A B，et al. An approach to failure prediction in a cloud based environment［C］// Proceedings of the 2017 IEEE 5th International Conference on Future Internet of Things and Cloud （FiCloud）. 2017：191-197.
［13］	SHU X K，YAO D F，RAMAKRISHNAN N. Unearthing stealthy program attacks buried in extremely long execution paths［C］// Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security. 2015：401-413.
［14］	SHU X K，YAO D F，RYDER B G. A formal framework for program anomaly detection［C］// Proceedings of the 2015 International Symposium on Recent Advances in Intrusion Detection. 2015：270-292.
［15］	DU M，LI F F，ZHENG G N，et al. DeepLog： Anomaly detection and diagnosis from system logs through deep learning［C］// Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. 2017：1285-1298.
［16］	LU L，XU Z G，WANG W H，et al. A new fault detection method for computer networks［J］. Reliability Engineering & System Safety，2013,114：45-51.
［17］	张开延,潘杨,娄季朝. 基于ANP-SVM算法的智能变电站过程层网络故障分类［J］. 计算机与现代化， 2019（7）：72-77.
［18］	董海强. 基于贝叶斯网的IP网络故障定位算法的研究与实现［D］. 北京：北京邮电大学， 2009.
［19］	周畅. 计算机网络中的故障定位研究［J］. 软件工程，2016,19（12）：1-4.
［20］	YU L，LAN Z L. A scalable，non-parametric method for detecting performance anomaly in large scale computing［J］. IEEE Transactions on Parallel and Distributed Systems，2016,27（7）：1902-1914.
［21］	王焘，顾泽宇，张文博，等. 一种基于自适应监测的云计算系统故障检测方法［J］. 计算机学报， 2018,41（6）：1332-1345.
［22］	GUAN Q，FU S. Adaptive anomaly identification by exploring metric subspace in cloud computing infrastructures［C］// Proceedings of the 2013 IEEE 32nd International Symposium on Reliable Distributed Systems. 2013：205-214.
［23］	SHARMA B，JAYACHANDRAN P，VERMA A，et al. CloudPD： Problem determination and diagnosis in shared dynamic clouds［C］// Proceedings of the 2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks （DSN）. 2013. DOI： 10.1109/DSN.2013.
	6575298.
［24］	WANG J. Real local-linearity preserving embedding［J］. Neurocomputing， 2014,136：7-13.
［25］	李元,耿泽伟. 基于LLE与K均值聚类算法的工业过程故障诊断［J］. 系统仿真学报， 2021，33（9）：2066-2073.
［26］	HSU C W，LIN C J. A comparison of methods for multiclass support vector machines［J］. IEEE Transactions on Neural Networks， 2002，13（2）：415-425.
［27］	ABUALIGAH L，DIABAT A，MIRJALILI S，et al. The arithmetic optimization algorithm［J］. Computer Methods in Applied Mechanics and Engineering，2021,376. DOI： 10.1016/j.cma.2020.113609.
［28］	LIU Y M，ZHOU H F. MSVM recognition model for dynamic process abnormal pattern based on multi-kernel functions［J］. Journal of Systems Science and Information，2014,2（5）：473-480.
［29］	MEI Y Y，HAN W H，LI S D，et al. A hybrid intelligent approach to attribute advanced persistent threat organization using PSO-MSVM algorithm［J］. IEEE Transactions on Network and Service Management，2022,19（4）：4262-4272.
［30］	LU P，YE L，ZHONG W Z，et al. A novel spatio-temporal wind power forecasting framework based on multi-output support vector machine and optimization strategy［J］. Journal of Cleaner Production，2020,254. DOI： 10.1016/j.jclepro.2020.119993.

[1]	王重阳, 庄毅. 基于SDN和改进CSA算法的多作业集群的负载均衡算法[J]. 计算机与现代化, 2023, 0(11): 28-35.
[2]	陈晨, 庄毅, 高增. QoE驱动的SDN网络高可用传输框架[J]. 计算机与现代化, 2023, 0(11): 62-68.
[3]	倪雅婷, 杨文晖, 苗放, 黄安琪, 蒋媛. 基于Nginx的DRC集群动态负载均衡策略[J]. 计算机与现代化, 2022, 0(04): 58-64.
[4]	李娟. 基于物联网技术的异构集群动态负载均衡算法[J]. 计算机与现代化, 2021, 0(04): 104-108.
[5]	晋文明, 颜硕彦, 钱巨, . 大规模负载生成客户端影响因素研究[J]. 计算机与现代化, 2020, 0(08): 76-81.
[6]	苏林萍，安然，李为，崔文超，张晓良. 基于Hadoop的电力运维审计系统的设计[J]. 计算机与现代化, 2020, 0(01): 49-.
[7]	杨双浩1，2 . 利用网格计算加速基因大数据分析的方法实现[J]. 计算机与现代化, 2019, 0(08): 85-.
[8]	屠雪真1，杨海潮2. 基于Kubernetes的水平弹性扩缩容系统[J]. 计算机与现代化, 2019, 0(07): 25-.
[9]	杨炳钊，李泽平，刘江涛 . 基于HLS流媒体集群动态反馈负载均衡算法[J]. 计算机与现代化, 2019, 0(03): 51-.
[10]	赵博颖，肖鹏，张力. 基于Docker的MPI和OpenMP混合编程[J]. 计算机与现代化, 2018, 0(05): 60-.
[11]	原建伟. 企业云存储管理系统的设计与实现[J]. 计算机与现代化, 2016, 0(9): 49-53.
[12]	冉迅，袁建华，刘玉国，胡杨. 基于负载均衡的移动发票管理系统研究[J]. 计算机与现代化, 2016, 0(10): 121-.
[13]	李欧，陈燕，李桃迎. Linux环境下负载均衡集群的实现[J]. 计算机与现代化, 2014, 0(9): 29-32.
[14]	王尚超，汤小春. 异构集群中基于优先级的任务容错调度算法[J]. 计算机与现代化, 2014, 0(4): 69-72.
[15]	邹杰，许涛，林茂，李铁，雷宏声. 基于PBS的勘探数据处理作业管理[J]. 计算机与现代化, 2014, 0(2): 119-123.