網(wǎng)絡(luò)流量預(yù)測技術(shù)的研究
發(fā)布時間：2018-11-19 10:29
【摘要】：在計(jì)算機(jī)網(wǎng)絡(luò)技術(shù)不斷發(fā)展的今天,網(wǎng)絡(luò)所覆蓋的范圍越來越廣,所承載的業(yè)務(wù)需求和使用的規(guī)模也日趨普遍。近年來,特別是P2P等新技術(shù)的大量涌起,更是嚴(yán)重地劣化了計(jì)算機(jī)網(wǎng)絡(luò)的性能。為了加速網(wǎng)絡(luò)運(yùn)行的速率和增強(qiáng)網(wǎng)絡(luò)的利用率,最重要的環(huán)節(jié)就是通過一些方法有效地預(yù)測出網(wǎng)絡(luò)流量的趨勢。假如我們能夠?qū)崟r監(jiān)控網(wǎng)絡(luò)的運(yùn)行情況,在出現(xiàn)網(wǎng)絡(luò)擁塞問題之前對流量數(shù)據(jù)進(jìn)行分析,便能顯著地提高網(wǎng)絡(luò)的服務(wù)質(zhì)量、有效性和安全性。作為網(wǎng)絡(luò)行為研究的一個重要領(lǐng)域,流量預(yù)測在擁塞控制、準(zhǔn)入控制以及無線和有線網(wǎng)絡(luò)管理上發(fā)揮著重要作用,具有現(xiàn)實(shí)的研究意義。 國內(nèi)外學(xué)者將一些模型理論引入到了網(wǎng)絡(luò)流量的預(yù)測中,如ARMA線性預(yù)測模型、神經(jīng)網(wǎng)絡(luò)等。本文比較了一些傳統(tǒng)的預(yù)測模型和新技術(shù)的優(yōu)勢及不足,重點(diǎn)分析了最小二乘支持向量機(jī)(LSSVM)的方法,該方法是機(jī)器學(xué)習(xí)方法的典型代表,可以較好地應(yīng)用于非線性預(yù)測的環(huán)境中,它克服了傳統(tǒng)機(jī)器學(xué)習(xí)需要大量數(shù)據(jù)的特點(diǎn),即使樣本數(shù)據(jù)量較小,預(yù)測也能達(dá)到較好的效果。然而,隨著網(wǎng)絡(luò)流量的混沌性、非平穩(wěn)性、復(fù)雜性等特性的出現(xiàn),現(xiàn)存的單的方法已經(jīng)不能對其進(jìn)行高精度的預(yù)測。 針對網(wǎng)絡(luò)流量的混沌性,本文提出了一種基于相空間重構(gòu)(PSR)和LSSVM的網(wǎng)絡(luò)流量預(yù)測模型。首先計(jì)算最大Lyapunov指數(shù)來判斷網(wǎng)絡(luò)流量的混沌特性后,使用粒子群算法優(yōu)化的LSSVM對相空間重構(gòu)后的多維序列進(jìn)行訓(xùn)練并預(yù)測出未來網(wǎng)絡(luò)流量的走勢。實(shí)驗(yàn)效果優(yōu)于單一的LSSVM模型。 針對網(wǎng)絡(luò)流量的非平穩(wěn)性和復(fù)雜性,本文提出了一種組合小波變換和PSR-LSSVM的網(wǎng)絡(luò)流量預(yù)測模型。首先利用小波變換在非線性系統(tǒng)中發(fā)揮出來的多尺度分析的特性,將網(wǎng)絡(luò)流量分解并單支重構(gòu)為高頻分量和低頻分量,相當(dāng)于對原始網(wǎng)絡(luò)流量序列進(jìn)行了平滑處理。然后判斷各分量的混沌性,將具有混沌特性的分量通過PSR-LSSVM模型進(jìn)行預(yù)測,其余分量通過粒子群算法優(yōu)化的LSSVM進(jìn)行預(yù)測,最后將各分量的預(yù)測結(jié)果綜合計(jì)算輸出,獲得最終的預(yù)測流量。在Matlab中使用本文提出的新的模型對真實(shí)的網(wǎng)絡(luò)流量進(jìn)行實(shí)驗(yàn)并預(yù)測,預(yù)測精度高達(dá)90%以上,預(yù)測效果明顯優(yōu)于單一的LSSVM模型以及神經(jīng)網(wǎng)絡(luò)模型。
[Abstract]:With the development of computer network technology, the scope of network is more and more extensive, and the demand and scale of service are becoming more and more common. In recent years, especially with the emergence of P2P and other new technologies, the performance of computer network has been seriously degraded. In order to speed up the operation of the network and enhance the utilization of the network, the most important link is to effectively predict the trend of network traffic through some methods. If we can monitor the operation of the network in real time and analyze the traffic data before the network congestion problem we can significantly improve the quality of service effectiveness and security of the network. As an important field of network behavior research, traffic prediction plays an important role in congestion control, access control, wireless and wired network management, and has practical significance. Scholars at home and abroad have introduced some model theories into network traffic prediction, such as ARMA linear prediction model, neural network and so on. In this paper, the advantages and disadvantages of some traditional prediction models and new techniques are compared, and the method of least square support vector machine (LSSVM) is emphatically analyzed, which is a typical representative of machine learning methods. It can be well applied to the environment of nonlinear prediction. It overcomes the characteristics that traditional machine learning requires a lot of data. Even if the sample data is small, the prediction can achieve better results. However, with the appearance of chaos, nonstationarity and complexity of network traffic, the existing single method can not predict it with high accuracy. Aiming at the chaos of network traffic, this paper presents a network traffic prediction model based on phase space reconstruction (PSR) and LSSVM. First, the maximum Lyapunov exponent is calculated to judge the chaotic characteristics of network traffic, then the LSSVM optimized by particle swarm optimization is used to train the multi-dimensional sequence after phase space reconstruction and to predict the trend of network traffic in the future. The experimental results are better than the single LSSVM model. Aiming at the nonstationarity and complexity of network traffic, a network traffic prediction model combining wavelet transform and PSR-LSSVM is proposed in this paper. Firstly, the network traffic is decomposed and reconstructed into high-frequency and low-frequency components by using the multi-scale analysis of wavelet transform in nonlinear systems, which is equivalent to smoothing the original network traffic sequence. Then the chaos of each component is judged, the components with chaotic characteristics are predicted by PSR-LSSVM model, the other components are forecasted by LSSVM optimized by particle swarm optimization. Finally, the prediction results of each component are synthetically calculated and outputted. Get the final predicted flow. The new model proposed in this paper is used to test and predict the real network traffic in Matlab. The prediction accuracy is more than 90%, and the prediction effect is obviously better than that of the single LSSVM model and neural network model.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP393.06
本文編號：2342030
[Abstract]:With the development of computer network technology, the scope of network is more and more extensive, and the demand and scale of service are becoming more and more common. In recent years, especially with the emergence of P2P and other new technologies, the performance of computer network has been seriously degraded. In order to speed up the operation of the network and enhance the utilization of the network, the most important link is to effectively predict the trend of network traffic through some methods. If we can monitor the operation of the network in real time and analyze the traffic data before the network congestion problem we can significantly improve the quality of service effectiveness and security of the network. As an important field of network behavior research, traffic prediction plays an important role in congestion control, access control, wireless and wired network management, and has practical significance. Scholars at home and abroad have introduced some model theories into network traffic prediction, such as ARMA linear prediction model, neural network and so on. In this paper, the advantages and disadvantages of some traditional prediction models and new techniques are compared, and the method of least square support vector machine (LSSVM) is emphatically analyzed, which is a typical representative of machine learning methods. It can be well applied to the environment of nonlinear prediction. It overcomes the characteristics that traditional machine learning requires a lot of data. Even if the sample data is small, the prediction can achieve better results. However, with the appearance of chaos, nonstationarity and complexity of network traffic, the existing single method can not predict it with high accuracy. Aiming at the chaos of network traffic, this paper presents a network traffic prediction model based on phase space reconstruction (PSR) and LSSVM. First, the maximum Lyapunov exponent is calculated to judge the chaotic characteristics of network traffic, then the LSSVM optimized by particle swarm optimization is used to train the multi-dimensional sequence after phase space reconstruction and to predict the trend of network traffic in the future. The experimental results are better than the single LSSVM model. Aiming at the nonstationarity and complexity of network traffic, a network traffic prediction model combining wavelet transform and PSR-LSSVM is proposed in this paper. Firstly, the network traffic is decomposed and reconstructed into high-frequency and low-frequency components by using the multi-scale analysis of wavelet transform in nonlinear systems, which is equivalent to smoothing the original network traffic sequence. Then the chaos of each component is judged, the components with chaotic characteristics are predicted by PSR-LSSVM model, the other components are forecasted by LSSVM optimized by particle swarm optimization. Finally, the prediction results of each component are synthetically calculated and outputted. Get the final predicted flow. The new model proposed in this paper is used to test and predict the real network traffic in Matlab. The prediction accuracy is more than 90%, and the prediction effect is obviously better than that of the single LSSVM model and neural network model.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP393.06
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 楊延西,劉丁;基于小波變換和最小二乘支持向量機(jī)的短期電力負(fù)荷預(yù)測[J];電網(wǎng)技術(shù);2005年13期
2 杜穎;盧繼平;李青;鄧穎玲;;基于最小二乘支持向量機(jī)的風(fēng)電場短期風(fēng)速預(yù)測[J];電網(wǎng)技術(shù);2008年15期
3 王海濤;;網(wǎng)絡(luò)流量測量及測量軟件的設(shè)計(jì)和實(shí)現(xiàn)[J];電信快報(bào);2011年10期
4 李捷;候秀紅;韓志杰;;基于卡爾曼濾波和小波的網(wǎng)絡(luò)流量預(yù)測算法研究[J];電子與信息學(xué)報(bào);2007年03期
5 曹彥;王倩;周馳;;基于最小二乘支持向量機(jī)的短期電力負(fù)荷預(yù)測[J];電腦開發(fā)與應(yīng)用;2013年03期
6 李士寧;閆焱;覃征;;基于FARIMA模型的網(wǎng)絡(luò)流量預(yù)測[J];計(jì)算機(jī)工程與應(yīng)用;2006年29期
7 馬華林;李翠鳳;張立燕;;基于灰色模型和自適應(yīng)過濾的網(wǎng)絡(luò)流量預(yù)測[J];計(jì)算機(jī)工程;2009年01期
8 邱婧;夏靖波;吳吉祥;;網(wǎng)絡(luò)流量預(yù)測模型研究進(jìn)展[J];計(jì)算機(jī)工程與設(shè)計(jì);2012年03期
9 楊光;張國梅;劉星宇;;基于小波核LS-SVM的網(wǎng)絡(luò)流量預(yù)測[J];微機(jī)發(fā)展;2005年12期
10 龍文;焦建軍;龍祖強(qiáng);;基于PSO優(yōu)化LSSVM的未知模型混沌系統(tǒng)控制[J];物理學(xué)報(bào);2011年11期
，本文編號：2342030
本文鏈接：http://www.sikaile.net/guanlilunwen/ydhl/2342030.html
最近更新
教材專著
