發(fā)布時(shí)間：2018-06-03 06:21

  本文選題：神經(jīng)網(wǎng)絡(luò) + 復(fù)雜網(wǎng)絡(luò)��； 參考：《北京郵電大學(xué)》2014年碩士論文

【摘要】：近幾年,對(duì)下一代網(wǎng)絡(luò)的研究已如火如荼,因?yàn)橄乱淮W(wǎng)絡(luò)所提出的架構(gòu)理念能很好的解決現(xiàn)在互聯(lián)網(wǎng)所存在的很多問題。與此同時(shí),隨著科技不斷進(jìn)步,用戶對(duì)于所使用的網(wǎng)絡(luò)及業(yè)務(wù)的服務(wù)質(zhì)量要求不斷提高。所以,立足于用戶需求,再結(jié)合下一代網(wǎng)絡(luò)的發(fā)展趨勢(shì),我們需要清楚而全面地把握網(wǎng)絡(luò)用戶的行為,預(yù)測(cè)網(wǎng)絡(luò)用戶行為的變化規(guī)律,從而為優(yōu)化網(wǎng)絡(luò)的性能和提高業(yè)務(wù)的服務(wù)質(zhì)量提供一條路徑。 首先,本文介紹了下一代網(wǎng)絡(luò)架構(gòu)；總結(jié)了網(wǎng)絡(luò)用戶行為的研究現(xiàn)狀；總結(jié)了神經(jīng)網(wǎng)絡(luò)用于用戶行為分析及預(yù)測(cè)的研究現(xiàn)狀。 其次,為了進(jìn)一步提高網(wǎng)絡(luò)流量的預(yù)測(cè)精度,使模型能自適應(yīng)不同的業(yè)務(wù)流量預(yù)測(cè),我們研究了寬參數(shù)域下的回聲狀態(tài)神經(jīng)網(wǎng)絡(luò)算法(ESNs, Echo State Networks)。我們引入復(fù)雜網(wǎng)絡(luò)理論以及基于生物側(cè)抑制機(jī)制(LIM,Lateral Inhibition Mechanism)的思想提出了兩種新型的回聲狀態(tài)網(wǎng)絡(luò)算法： ·帶有動(dòng)態(tài)池預(yù)測(cè)的去耦合回聲狀態(tài)神經(jīng)網(wǎng)絡(luò)(DMESN+RP, Decoupled Mixed Echo State Network with Reservoir Prediction); ·帶有最大信息量的DMESN(DMESN+Maxlnfo,Decoupled Mixed Echo State Network with Maximum Information)。 與此同時(shí),我們與傳統(tǒng)的回聲網(wǎng)絡(luò)狀態(tài)算法在預(yù)測(cè)精度,譜半徑,參數(shù)魯棒性等方面進(jìn)行了仿真分析及對(duì)比。仿真發(fā)現(xiàn)我們所提出的DMESN+RP和DMESN+Maxlnfo在預(yù)測(cè)精度,譜半徑參數(shù)變化范圍及參數(shù)魯棒性上要優(yōu)于傳統(tǒng)的回聲狀態(tài)神經(jīng)網(wǎng)絡(luò)。 再次,我們將所提出的DMESN+RP和DMESN+Maxlnfo用于移動(dòng)互聯(lián)網(wǎng)的真實(shí)網(wǎng)絡(luò)流量預(yù)測(cè)之中,從預(yù)測(cè)精度方面驗(yàn)證這種方案的實(shí)用性。 最后,本文結(jié)合未來網(wǎng)絡(luò)新型分層架構(gòu)提出了一種基于DMESN+Maxlnfo的網(wǎng)絡(luò)節(jié)點(diǎn)流量預(yù)測(cè)的新型網(wǎng)絡(luò)鏈路分配策略。
[Abstract]:In recent years, the research on NGN has been in full swing, because the architecture of NGN can solve many problems existing in the Internet. At the same time, with the development of science and technology, the quality of service of the network and service is improved. Therefore, based on user needs and combined with the development trend of next generation network, we need to clearly and comprehensively grasp the behavior of network users and predict the changing law of network users' behavior. It provides a path for optimizing network performance and improving service quality. Firstly, this paper introduces the next generation network architecture, summarizes the research status of network user behavior, and summarizes the research status of neural network for user behavior analysis and prediction. Secondly, in order to further improve the accuracy of network traffic prediction and enable the model to adapt to different traffic prediction, we study the echo state neural network algorithm ESNs, Echo State networks in wide parameter domain. In this paper, we introduce the theory of complex network and the idea of LIMLlateral Inhibition Mechanism based on the biological side inhibition mechanism. We propose two new echo state network algorithms: De-coupled echo state neural network with dynamic cell prediction (DMESN RP, Decoupled Mixed Echo State Network with Reservoir prediction); DMESN(DMESN Maxlnfol decouped Mixed Echo State Network with Maximum Information with maximum amount of information. At the same time, the simulation analysis and comparison with the traditional echo network state algorithm in prediction accuracy, spectral radius and parameter robustness are carried out. Simulation results show that the proposed DMESN RP and DMESN Maxlnfo are superior to the conventional echo state neural networks in prediction accuracy, spectral radius parameter variation range and parameter robustness. Thirdly, we apply the proposed DMESN RP and DMESN Maxlnfo to the real network traffic prediction of mobile Internet, and verify the practicability of the proposed scheme in terms of prediction accuracy. Finally, this paper proposes a new network link allocation strategy based on DMESN Maxlnfo network node traffic prediction combined with the future network new hierarchical architecture.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP393.09

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李擎,鄭德玲,趙星浩,劉東方;一種新的混沌識(shí)別方法(Ⅰ)[J];北京科技大學(xué)學(xué)報(bào);1999年02期

2 張宗震;馬爾可夫預(yù)測(cè)法基本原理解析與應(yīng)用[J];成都電子機(jī)械高等�？茖W(xué)校學(xué)報(bào);2001年02期

3 肖盛;張建華;;基于小世界拓?fù)淠Ｐ偷碾娋W(wǎng)脆弱性評(píng)估[J];電網(wǎng)技術(shù);2010年08期

4 王麗君;劉永強(qiáng);張健;;基于OpenFlow的未來互聯(lián)網(wǎng)試驗(yàn)技術(shù)研究[J];電信網(wǎng)技術(shù);2011年06期

5 陳敏;葉曉舟;;混沌時(shí)間序列的判定方法研究[J];信息技術(shù);2008年06期

6 余少波;嚴(yán)雋永;;神經(jīng)網(wǎng)絡(luò)應(yīng)用[J];海軍工程學(xué)院學(xué)報(bào);1990年02期

7 范玉妹;玄婧;;ARMA算法在GDP預(yù)測(cè)中的應(yīng)用[J];江南大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年06期

8 鄒恩,李祥飛,張?zhí)┥?混沌與混沌應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2002年11期

9 裴承丹;;回聲狀態(tài)網(wǎng)絡(luò)及其在圖像邊緣檢測(cè)中的應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2008年19期

10 李果;吉小恒;;基于小世界拓?fù)淠Ｐ偷木W(wǎng)絡(luò)系統(tǒng)安全分析[J];計(jì)算機(jī)工程;2010年14期

，

本文編號(hào)：1971792