發(fā)布時(shí)間：2018-02-06 05:42

  本文關(guān)鍵詞： 網(wǎng)絡(luò)流量 特征分析 AP-SVM 流量分類　出處：《南京郵電大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著各種新興應(yīng)用和網(wǎng)絡(luò)技術(shù)的大量使用，網(wǎng)絡(luò)環(huán)境變得越來越復(fù)雜，，對(duì)網(wǎng)絡(luò)管理提出了巨大的挑戰(zhàn)。如何才能更好地監(jiān)管網(wǎng)絡(luò)流量和保障網(wǎng)絡(luò)服務(wù)的QoS，準(zhǔn)確高效對(duì)網(wǎng)絡(luò)業(yè)務(wù)的識(shí)別和分類是前提。在基于業(yè)務(wù)流統(tǒng)計(jì)特征的網(wǎng)絡(luò)業(yè)務(wù)流識(shí)別分類方法中，特征的選取是關(guān)鍵。 本文通過對(duì)tudou視頻、Skype、DOTA、QQ視頻、迅雷等5種常用Internet業(yè)務(wù)進(jìn)行分析，分析的主要特征有包大小分布及其統(tǒng)計(jì)特征、Hellinger距離、包大小平均概率及包大小轉(zhuǎn)移概率、上下行包數(shù)目和字節(jié)數(shù)比例等。經(jīng)過分析發(fā)現(xiàn)：各類業(yè)務(wù)的包大小分布較為穩(wěn)定，包大小分布的均值、方差、信息熵、四分位數(shù)、峰度參數(shù)和偏度參數(shù)等統(tǒng)計(jì)特征均能一定程度上反映業(yè)務(wù)流包大小的特征。計(jì)算比較業(yè)務(wù)流之間包大小分布的Hellinger距離發(fā)現(xiàn)，tudou視頻和迅雷業(yè)務(wù)包大小分布具有一定的重合，DOTA和Skype兩類業(yè)務(wù)的包大小分布很相似。而這些業(yè)務(wù)在上下行包數(shù)目和字節(jié)數(shù)之比上也有著明顯的區(qū)別。因而可以使用包大小、上下行包數(shù)目和字節(jié)數(shù)之比這些特征進(jìn)行業(yè)務(wù)流的識(shí)別分類。最后，對(duì)現(xiàn)有的AP-SVM算法進(jìn)行改進(jìn)，提出了一種改變偏向參數(shù)（perferences）來實(shí)現(xiàn)更好地聚類效果的方法，以期得到更高質(zhì)量、更具代表性的訓(xùn)練樣本集，從而得到更好地分類效果。通過對(duì)網(wǎng)絡(luò)業(yè)務(wù)流的分類實(shí)驗(yàn)比較，改進(jìn)的算法取得了更好的分類效果。
[Abstract]:With the extensive use of a variety of emerging applications and network technology, the network environment becomes more and more complicated, a great challenge to the network management. How to better regulate the network traffic and network security services QoS, accurate and efficient of network traffic identification and classification is provided. In the flow classification statistical characteristics of traffic flow based on the network business, the selection of features is the key.
Based on the Tudou video, Skype, DOTA, QQ, video analysis, thunder and other 5 kinds of Internet business, the main feature of the analysis is packet size distribution and its statistical characteristics, Hellinger distance, average packet size and packet size probability transfer probability on the downlink packet number and node number word proportion. After analysis found: the size distribution of all kinds of business is relatively stable, the mean packet size distribution, variance, information entropy, four quantile, statistical feature parameters and skewness kurtosis feature parameters are able to reflect the degree of traffic packet size are calculated. Comparison between traffic packet size distribution Hellinger distance found, Tudou video and thunder packet size the distribution of a certain overlap, packet size distribution of DOTA and Skype two kinds of business are very similar. The packet number and the number of bytes in the uplink and downlink ratio also have obvious differences. So it can make With packet size on the downlink packet number and the ratio of the number of bytes of these features to classify the traffic flow. Finally, this paper improved the AP-SVM algorithm, the paper proposes a change bias parameter (perferences) method to achieve better clustering effect, in order to get higher quality, more representative the training sample set, to obtain better classification results. Through the experiment of network traffic classification and comparison, the improved algorithm achieved better classification results.

【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP393.06

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 王開軍;張軍英;李丹;張新娜;郭濤;;自適應(yīng)仿射傳播聚類[J];自動(dòng)化學(xué)報(bào);2007年12期

2 徐鵬;林森;;基于C4.5決策樹的流量分類方法[J];軟件學(xué)報(bào);2009年10期

相關(guān)博士學(xué)位論文 前1條

1 李為民;互聯(lián)網(wǎng)典型業(yè)務(wù)流量特征研究[D];北京郵電大學(xué);2012年

本文編號(hào)：1493720