本文選題：網(wǎng)絡(luò)流量預(yù)測(cè)　切入點(diǎn)：小波變換　出處：《西安電子科技大學(xué)》2014年碩士論文

【摘要】：隨著互聯(lián)網(wǎng)規(guī)模的不斷擴(kuò)大和多樣化網(wǎng)絡(luò)業(yè)務(wù)的不斷出現(xiàn)，網(wǎng)絡(luò)流量數(shù)據(jù)呈現(xiàn)出越來越錯(cuò)綜復(fù)雜的行為特征，如何對(duì)網(wǎng)絡(luò)進(jìn)行有效管理并使得網(wǎng)絡(luò)提供更好的服務(wù)質(zhì)量成為人們?cè)絹碓疥P(guān)心的問題。其中，如何建立一個(gè)有效而準(zhǔn)確的預(yù)測(cè)模型對(duì)網(wǎng)絡(luò)流量進(jìn)行預(yù)測(cè)，成為一個(gè)具有一定挑戰(zhàn)性的研究熱點(diǎn)，它對(duì)網(wǎng)絡(luò)多樣化的性能評(píng)價(jià)、擁塞控制、大規(guī)模網(wǎng)絡(luò)規(guī)劃設(shè)計(jì)以及業(yè)務(wù)的服務(wù)保障等重要問題的研究，都具有十分重要的意義。 論文對(duì)網(wǎng)絡(luò)流量預(yù)測(cè)模型進(jìn)行了研究。論文首先對(duì)網(wǎng)絡(luò)流量的特征以及網(wǎng)絡(luò)流量預(yù)測(cè)模型的研究現(xiàn)狀進(jìn)行了總結(jié)。然后，介紹了由小波變換和神經(jīng)網(wǎng)絡(luò)構(gòu)成的小波神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型(WNN模型)，并重點(diǎn)介紹了我們以前工作中提出過的一種使用遺傳算法優(yōu)化小波神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)模型(WGANN模型)。接著，論文提出了一種基于粒子群小波神經(jīng)網(wǎng)絡(luò)的網(wǎng)絡(luò)流量預(yù)測(cè)模型(WPSONN模型)，為了提高預(yù)測(cè)精度并優(yōu)化網(wǎng)絡(luò)收斂速度，我們將比遺傳算法收斂更快并具有更高預(yù)測(cè)精度的全局搜索優(yōu)化的粒子群算法引入預(yù)測(cè)模型，對(duì)BP神經(jīng)網(wǎng)絡(luò)的權(quán)值及閾值進(jìn)行優(yōu)化。該模型使用具有多分辨率和單支重構(gòu)特點(diǎn)的小波變換，將網(wǎng)絡(luò)流量訓(xùn)練樣本和預(yù)測(cè)樣本分別分解為低頻流量和高頻流量，分別用于訓(xùn)練和預(yù)測(cè)。在使用訓(xùn)練樣本對(duì)神經(jīng)網(wǎng)絡(luò)訓(xùn)練（即網(wǎng)絡(luò)學(xué)習(xí)）的過程中，使用粒子群算法，通過重復(fù)迭代優(yōu)化BP神經(jīng)網(wǎng)絡(luò)各層之間所有的連接權(quán)值及閾值，得到性能較優(yōu)的神經(jīng)網(wǎng)絡(luò)。在預(yù)測(cè)網(wǎng)絡(luò)流量時(shí)，將預(yù)測(cè)樣本的低頻和高頻流量數(shù)據(jù)輸入訓(xùn)練好的神經(jīng)網(wǎng)絡(luò)，分別得到各預(yù)測(cè)結(jié)果，，然后將各分量進(jìn)行疊加，得到預(yù)測(cè)模型的預(yù)測(cè)結(jié)果。最后，論文對(duì)提出的預(yù)測(cè)模型，與WGANN預(yù)測(cè)模型和WNN預(yù)測(cè)模型進(jìn)行了對(duì)比分析。 針對(duì)本文所提出的預(yù)測(cè)模型，論文進(jìn)行預(yù)測(cè)實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明，與WGANN預(yù)測(cè)模型和WNN預(yù)測(cè)模型相比較，提出的WPSONN預(yù)測(cè)模型具有更高的預(yù)測(cè)精度，并具有更快的網(wǎng)絡(luò)收斂速度，是一種有效的網(wǎng)絡(luò)流量預(yù)測(cè)模型。
[Abstract]:With the continuous expansion of the scale of the Internet and the emergence of diversified network services, network traffic data show more and more complex behavior characteristics.How to effectively manage the network and make the network to provide better quality of service has become a growing concern.Among them, how to establish an effective and accurate prediction model to predict network traffic has become a challenging research hotspot.The research of large-scale network planning and service security is of great significance.The network traffic prediction model is studied in this paper.Firstly, the characteristics of network traffic and the research status of network traffic prediction model are summarized.Then, the prediction model of wavelet neural network, which is composed of wavelet transform and neural network, is introduced, and a prediction model using genetic algorithm to optimize wavelet neural network is introduced in detail.Then, a network traffic prediction model based on particle swarm optimization wavelet neural network (PSO) is proposed. In order to improve the prediction accuracy and optimize the convergence speed of the network, a WPSONN model is proposed.The particle swarm optimization algorithm, which converges faster than genetic algorithm and has higher prediction precision, is introduced into the prediction model to optimize the weights and thresholds of BP neural network.The model uses wavelet transform with multi-resolution and single-branch reconstruction to decompose network traffic training samples and prediction samples into low-frequency and high-frequency traffic respectively for training and prediction.In the process of using training samples to train neural networks (that is, network learning), particle swarm optimization (PSO) algorithm is used to optimize all the connection weights and thresholds between layers of BP neural networks through repeated iterations, and a neural network with better performance is obtained.When forecasting network traffic, the low-frequency and high-frequency flow data of the predicted samples are input into the trained neural network, and the prediction results are obtained respectively, and then each component is superposed to obtain the prediction results of the prediction model.Finally, the proposed prediction model is compared with the WGANN prediction model and the WNN prediction model.According to the prediction model proposed in this paper, the prediction experiment is carried out in this paper.The experimental results show that compared with the WGANN and WNN prediction models, the proposed WPSONN prediction model has higher prediction accuracy and faster network convergence speed, so it is an effective network traffic prediction model.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP393.06;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃建國;羅航;王厚軍;龍兵;;運(yùn)用GA-BP神經(jīng)網(wǎng)絡(luò)研究時(shí)間序列的預(yù)測(cè)[J];電子科技大學(xué)學(xué)報(bào);2009年05期

2 徐曉霞,陳濤,王曉升;基于正交最小二乘算法的小波神經(jīng)網(wǎng)絡(luò)[J];電子學(xué)報(bào);1998年10期

3 呂振肅,侯志榮;自適應(yīng)變異的粒子群優(yōu)化算法[J];電子學(xué)報(bào);2004年03期

4 高海兵,高亮,周馳,喻道遠(yuǎn);基于粒子群優(yōu)化的神經(jīng)網(wǎng)絡(luò)訓(xùn)練算法研究[J];電子學(xué)報(bào);2004年09期

5 蔣建國;蘇兆品;李援;梁立偉;;RTP/RTCP自適應(yīng)流量控制算法[J];電子學(xué)報(bào);2006年09期

6 姜明;吳春明;張e

本文編號(hào)：1717514