發(fā)布時(shí)間：2018-05-07 09:05

  本文選題：網(wǎng)絡(luò)流量協(xié)議識(shí)別 + 神經(jīng)網(wǎng)絡(luò)��； 參考：《華中科技大學(xué)》2014年碩士論文

【摘要】：傳統(tǒng)的網(wǎng)絡(luò)設(shè)備對(duì)各種協(xié)議一視同仁，，均分資源的服務(wù)形式己經(jīng)不能滿足用戶的多樣化需求。在這種情況下，網(wǎng)絡(luò)服務(wù)供應(yīng)商希望藉由路由器智能對(duì)待網(wǎng)絡(luò)數(shù)據(jù)流和網(wǎng)絡(luò)流量梯度化收費(fèi)等手段在盡量不增加成本升級(jí)硬件的前提下賺取更多的網(wǎng)絡(luò)資源使用費(fèi)用，這些需求就要求網(wǎng)絡(luò)提供商能夠識(shí)別種類繁雜的數(shù)據(jù)流量。但是，由于網(wǎng)絡(luò)服務(wù)的快速發(fā)展，網(wǎng)絡(luò)應(yīng)用協(xié)議的種類不斷增加，網(wǎng)絡(luò)協(xié)議的復(fù)雜程度也不斷增長(zhǎng)，上述問題導(dǎo)致了網(wǎng)絡(luò)流量協(xié)議自動(dòng)識(shí)別的困難。 通過對(duì)各種應(yīng)用業(yè)務(wù)的網(wǎng)絡(luò)流量協(xié)議的分析，提出將網(wǎng)絡(luò)會(huì)話的流量數(shù)據(jù)包頭信息作為統(tǒng)計(jì)值的基本元素，并獲得了基于網(wǎng)絡(luò)流量統(tǒng)計(jì)值的特征集合。通過基于BP神經(jīng)網(wǎng)絡(luò)算法的平均影響度值評(píng)價(jià)特征對(duì)結(jié)果的影響，最終確定了最優(yōu)的網(wǎng)絡(luò)流量統(tǒng)計(jì)值的特征集合。然后根據(jù)目前研究的一些網(wǎng)絡(luò)流量協(xié)議識(shí)別技術(shù)，采用基于馬爾科夫隨機(jī)場(chǎng)的隱馬爾科夫模型(HMM)對(duì)網(wǎng)絡(luò)流量進(jìn)行協(xié)議識(shí)別。 在設(shè)計(jì)的實(shí)驗(yàn)中，利用華中科技大學(xué)軟件學(xué)院Intel多核實(shí)驗(yàn)室收集的網(wǎng)絡(luò)通信數(shù)據(jù)集，對(duì)最優(yōu)消息統(tǒng)計(jì)值的特征集合訓(xùn)練馬爾科夫模型并用這些數(shù)據(jù)對(duì)訓(xùn)練所得模型進(jìn)行測(cè)試，模型的總體準(zhǔn)確度達(dá)到90%以上。并將得到的實(shí)驗(yàn)結(jié)果與其他的分類方法比較，進(jìn)一步驗(yàn)證了論文提出的基于馬爾科夫隨機(jī)場(chǎng)的網(wǎng)絡(luò)流量協(xié)議識(shí)別方法的優(yōu)越性——準(zhǔn)確、簡(jiǎn)單、高效。
[Abstract]:Traditional network equipments treat all kinds of protocols equally, and the service form of equally distributing resources can not meet the diverse needs of users. In this case, the network service provider hopes to earn more network resource cost without increasing the cost of upgrading the hardware by means of router intelligent treatment of network data flow and network traffic gradient charges. These requirements require network providers to identify a variety of complex data flows. However, due to the rapid development of network services, the types of network application protocols are increasing, and the complexity of network protocols is also increasing. These problems lead to the difficulties of automatic identification of network traffic protocols. Based on the analysis of network traffic protocols for various application services, the packet header information of network session traffic data is proposed as the basic element of statistical value, and the feature set based on network traffic statistics is obtained. Based on the BP neural network algorithm, the characteristic set of the optimal network traffic statistics is determined by evaluating the effect of the average influence degree value on the result. Then, according to some network traffic protocol identification techniques, the Hidden Markov Model (HMMM) based on Markov Random Field is used to identify the network traffic. In the designed experiment, using the network communication data set collected by the Intel multi-core laboratory of software school of Huazhong University of Science and Technology, the Markov model is trained by the characteristic set of the optimal message statistics, and the training model is tested with these data. The overall accuracy of the model is over 90%. By comparing the experimental results with other classification methods, the superiority of the proposed network traffic protocol recognition method based on Markov random field is further verified-accurate, simple and efficient.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP393.06

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王雙成;冷翠平;劉鳳霞;;無向馬爾科夫毯分類器與集成[J];系統(tǒng)工程與電子技術(shù);2008年07期

2 沈吉鋒;張永志;宋朝河;陳芬;;基于馬爾科夫更新過程的偵察系統(tǒng)可靠性分析[J];兵工自動(dòng)化;2010年03期

3 馬世榮;;馬爾科夫性是相互獨(dú)立性的推廣[J];撫順石油學(xué)院學(xué)報(bào);1987年02期

4 肖剛;非馬爾科夫可修表決系統(tǒng)可靠性數(shù)字仿真[J];系統(tǒng)工程與電子技術(shù);1998年04期

5 曹建農(nóng),李德仁,關(guān)澤群;基于馬爾科夫網(wǎng)視頻圖像目標(biāo)檢測(cè)跟蹤方法研究[J];測(cè)繪科學(xué);2004年06期

6 金圣華;周瑋;;馬爾科夫蒙特卡洛在視網(wǎng)膜血管分割中的應(yīng)用[J];長(zhǎng)沙大學(xué)學(xué)報(bào);2011年05期

7 王輝,王雙成,張劍飛;馬爾科夫網(wǎng)絡(luò)中的隱藏變量學(xué)習(xí)[J];小型微型計(jì)算機(jī)系統(tǒng);2005年03期

8 曹容菲;張美霞;王醒策;武仲科;周明全;田l

本文編號(hào)：1856312