發(fā)布時間：2018-05-07 09:05

  本文選題：網(wǎng)絡(luò)流量協(xié)議識別 + 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待網(wǎng)絡(luò)數(shù)據(jù)流和網(wǎng)絡(luò)流量梯度化收費等手段在盡量不增加成本升級硬件的前提下賺取更多的網(wǎng)絡(luò)資源使用費用，這些需求就要求網(wǎng)絡(luò)提供商能夠識別種類繁雜的數(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，上述問題導(dǎo)致了網(wǎng)絡(luò)流量協(xié)議自動識別的困難。 通過對各種應(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)會話的流量數(shù)據(jù)包頭信息作為統(tǒng)計值的基本元素，并獲得了基于網(wǎng)絡(luò)流量統(tǒng)計值的特征集合。通過基于BP神經(jīng)網(wǎng)絡(luò)算法的平均影響度值評價特征對結(jié)果的影響，最終確定了最優(yōu)的網(wǎng)絡(luò)流量統(tǒng)計值的特征集合。然后根據(jù)目前研究的一些網(wǎng)絡(luò)流量協(xié)議識別技術(shù)，采用基于馬爾科夫隨機場的隱馬爾科夫模型(HMM)對網(wǎng)絡(luò)流量進行協(xié)議識別。 在設(shè)計的實驗中，利用華中科技大學(xué)軟件學(xué)院Intel多核實驗室收集的網(wǎng)絡(luò)通信數(shù)據(jù)集，對最優(yōu)消息統(tǒng)計值的特征集合訓(xùn)練馬爾科夫模型并用這些數(shù)據(jù)對訓(xùn)練所得模型進行測試，模型的總體準確度達到90%以上。并將得到的實驗結(jié)果與其他的分類方法比較，進一步驗證了論文提出的基于馬爾科夫隨機場的網(wǎng)絡(luò)流量協(xié)議識別方法的優(yōu)越性——準確、簡單、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)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP393.06

【相似文獻】

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];兵工自動化;2010年03期

3 馬世榮;;馬爾科夫性是相互獨立性的推廣[J];撫順石油學(xué)院學(xué)報;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)視頻圖像目標檢測跟蹤方法研究[J];測繪科學(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];長沙大學(xué)學(xué)報;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];小型微型計算機系統(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：1856312