【摘要】：隨著云計(jì)算的快速發(fā)展,云平臺(tái)的集群規(guī)模急劇擴(kuò)大,由于資源競(jìng)爭(zhēng)和軟件衰退等原因,虛擬機(jī)在運(yùn)行過(guò)程中可能會(huì)發(fā)生異常行為。虛擬機(jī)一旦出現(xiàn)異常會(huì)影響云平臺(tái)的服務(wù)質(zhì)量,進(jìn)而會(huì)造成用戶流失等嚴(yán)重后果。因此,虛擬計(jì)算環(huán)境下的節(jié)點(diǎn)異常檢測(cè)方法研究對(duì)于提高云平臺(tái)的穩(wěn)定性有重要的應(yīng)用價(jià)值。本文針對(duì)虛擬計(jì)算環(huán)境下集群節(jié)點(diǎn)的異常行為檢測(cè)展開(kāi)研究,分析和總結(jié)了現(xiàn)有的節(jié)點(diǎn)異常檢測(cè)方法的優(yōu)缺點(diǎn)。在此基礎(chǔ)上,根據(jù)虛擬計(jì)算環(huán)境的特點(diǎn),著重研究了單個(gè)節(jié)點(diǎn)的異常檢測(cè)方法、多個(gè)同構(gòu)節(jié)點(diǎn)的異常檢測(cè)方法,解決了虛擬機(jī)實(shí)時(shí)異常檢測(cè)、多節(jié)點(diǎn)異常檢測(cè)準(zhǔn)確率低和誤報(bào)率高等關(guān)鍵問(wèn)題。論文的工作主要包括以下幾個(gè)方面:1.針對(duì)基于單聚類的節(jié)點(diǎn)異常檢測(cè)方法準(zhǔn)確率低、誤報(bào)率高等問(wèn)題,提出一種基于組合聚類的單節(jié)點(diǎn)異常檢測(cè)框架,該框架通過(guò)改進(jìn)子空間聚類算法和密度聚類算法,以滿足數(shù)據(jù)流聚類的要求,并以改進(jìn)的兩種算法作為基聚類算法產(chǎn)生聚類成員,采用基于聚類差異度的選擇策略選擇聚類成員,最后設(shè)計(jì)基于共聯(lián)矩陣的共識(shí)函數(shù)實(shí)現(xiàn)聚類成員的融合。該模型基于聚類融合技術(shù),相比于單聚類,具備更好的適用性、穩(wěn)定性等特點(diǎn)。實(shí)驗(yàn)結(jié)果表明,改進(jìn)的聚類算法在保證聚類精度的同時(shí),在處理效率上有明顯提升,并且提出的組合模型相比于單一聚類方法,在準(zhǔn)確率、誤報(bào)率上都有明顯的改進(jìn)。2.針對(duì)多節(jié)點(diǎn)異常檢測(cè)問(wèn)題,提出一種基于上下文的多節(jié)點(diǎn)異常檢測(cè)方法。該方法是針對(duì)同構(gòu)分布式計(jì)算系統(tǒng)的多節(jié)點(diǎn)異常檢測(cè)方法,結(jié)合同構(gòu)節(jié)點(diǎn)間的上下文信息和單節(jié)點(diǎn)的歷史信息進(jìn)行異常檢測(cè)。實(shí)驗(yàn)結(jié)果表明,該方法在準(zhǔn)確率、召回率等方面均優(yōu)于現(xiàn)有的方法。
[Abstract]:With the rapid development of cloud computing, the cluster scale of cloud platform expands dramatically. Due to the competition of resources and the decline of software, the abnormal behavior of virtual machine may occur in the process of running. Once there is an anomaly in virtual machine, it will affect the quality of service of cloud platform, which will lead to serious consequences such as loss of users and so on. Therefore, the research on node anomaly detection in virtual computing environment has important application value for improving the stability of cloud platform. In this paper, the anomaly behavior detection of cluster nodes in virtual computing environment is studied, and the advantages and disadvantages of existing node anomaly detection methods are analyzed and summarized. On this basis, according to the characteristics of virtual computing environment, the anomaly detection method of single node and the anomaly detection method of multiple isomorphic nodes are studied emphatically, and the real-time anomaly detection of virtual machine is solved. The key problems such as low accuracy and high false positive rate of multi-node anomaly detection. The work of this paper mainly includes the following aspects: 1. In order to solve the problems such as low accuracy and high false alarm rate of node anomaly detection based on mono-clustering, a single-node anomaly detection framework based on combinatorial clustering is proposed, which improves subspace clustering algorithm and density clustering algorithm. In order to meet the requirements of data flow clustering, two improved clustering algorithms are used as the base clustering algorithm to generate clustering members, and cluster members are selected by the selection strategy based on clustering difference degree. Finally, the consensus function based on the co-join matrix is designed to realize the fusion of cluster members. The model is based on clustering and fusion technology, and has better applicability and stability than single clustering. The experimental results show that the improved clustering algorithm not only guarantees the clustering accuracy, but also improves the processing efficiency obviously. Compared with the single clustering method, the proposed combination model has obvious improvement on the accuracy and false alarm rate. 2. To solve the problem of multi-node anomaly detection, a context-based multi-node anomaly detection method is proposed. This method is a multi-node anomaly detection method for isomorphic distributed computing systems, which combines the context information between the isomorphic nodes and the historical information of the single node to detect the anomalies. The experimental results show that the proposed method is superior to the existing methods in accuracy and recall.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP393.09;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 朱林;雷景生;畢忠勤;楊杰;;一種基于數(shù)據(jù)流的軟子空間聚類算法[J];軟件學(xué)報(bào);2013年11期

2 饒翔;王懷民;陳振邦;周揚(yáng)帆;蔡華;周琦;孫廷韜;;云計(jì)算系統(tǒng)中基于伴隨狀態(tài)追蹤的故障檢測(cè)機(jī)制[J];計(jì)算機(jī)學(xué)報(bào);2012年05期

3 陽(yáng)琳，

本文編號(hào)：2446229