發(fā)布時(shí)間：2018-06-24 01:51

  本文選題：流量矩陣估計(jì) + 高階神經(jīng)網(wǎng)絡(luò)　； 參考：《華中師范大學(xué)》2015年碩士論文

【摘要】：隨著互聯(lián)網(wǎng)技術(shù)的飛速發(fā)展,生活水平的不斷提高,越來(lái)越多的用戶加入到互聯(lián)網(wǎng)中,網(wǎng)絡(luò)規(guī)模日益擴(kuò)大；各種網(wǎng)絡(luò)應(yīng)用也是層出不窮,網(wǎng)絡(luò)中傳輸?shù)牧髁恳詭缀问皆鲩L(zhǎng)。對(duì)網(wǎng)絡(luò)運(yùn)營(yíng)商和網(wǎng)絡(luò)管理者而言,節(jié)約成本,優(yōu)化網(wǎng)絡(luò)規(guī)劃設(shè)計(jì),提高網(wǎng)絡(luò)服務(wù)質(zhì)量,全面掌握網(wǎng)絡(luò)運(yùn)行狀態(tài)等網(wǎng)絡(luò)工程問(wèn)題亟需得到進(jìn)一步解決。了解網(wǎng)絡(luò)內(nèi)部的種種特性有助于成功設(shè)計(jì)、控制和管理網(wǎng)絡(luò)。網(wǎng)絡(luò)流量矩陣作為重要的工具之一,全面地描述了網(wǎng)絡(luò)上所有節(jié)點(diǎn)間的流量分布,是網(wǎng)絡(luò)設(shè)計(jì)、管理和路由配置的重要依據(jù)。而龐大的網(wǎng)絡(luò)規(guī)模,海量的傳輸數(shù)據(jù),異構(gòu)分布的網(wǎng)絡(luò)模式使得直接通過(guò)網(wǎng)絡(luò)測(cè)量獲取流量矩陣非常困難,甚至不可能實(shí)現(xiàn)。因而廣大學(xué)者提出了各種利用有限測(cè)量信息進(jìn)行網(wǎng)絡(luò)流量矩陣估計(jì)的間接測(cè)量方法。本文圍繞流量矩陣估計(jì)這一課題所做的工作主要包括：1)首先介紹了流量矩陣的研究意義和目前國(guó)內(nèi)外的研究現(xiàn)狀,概要描述了本文的層次結(jié)構(gòu)；2)歸納了流量矩陣間接測(cè)量的三類方法,對(duì)每一類方法中應(yīng)用的技術(shù)作了基本的描述,分析了各類方法的優(yōu)缺點(diǎn)；3)在高階神經(jīng)網(wǎng)絡(luò)的基礎(chǔ)上,應(yīng)用最新的化學(xué)反應(yīng)優(yōu)化算法,提出了一種新型的CRO-PSNN算法來(lái)對(duì)流量矩陣進(jìn)行估計(jì)。對(duì)于該算法,本文從兩個(gè)方面論述了其優(yōu)越性：一是高階神經(jīng)網(wǎng)絡(luò)對(duì)于流量矩陣估計(jì)這類高維度病態(tài)問(wèn)題的優(yōu)勢(shì),包含乘法器使得高階神經(jīng)網(wǎng)絡(luò)能夠處理普通神經(jīng)網(wǎng)絡(luò)所不及的高階問(wèn)題和強(qiáng)非線性問(wèn)題。二是使用化學(xué)反應(yīng)優(yōu)化算法參與高階神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)過(guò)程,避免了以往誤差參與的權(quán)值調(diào)整,減小了計(jì)算量,加快網(wǎng)絡(luò)的收斂速度和計(jì)算速度。4)最后根據(jù)現(xiàn)有的理論和實(shí)驗(yàn)依據(jù),通過(guò)仿真實(shí)驗(yàn)與知名的流量矩陣估計(jì)方法進(jìn)行對(duì)比,證明該方法所具有的優(yōu)勢(shì)。最后總結(jié)全文,回顧了本文所做的研究工作,并根據(jù)目前的現(xiàn)狀對(duì)進(jìn)一步的研究方向作出了展望。
[Abstract]:With the rapid development of Internet technology and the improvement of living standard, more and more users join the Internet, and the scale of network is expanding day by day. For network operators and network managers, such network engineering problems as cost saving, optimization of network planning and design, improvement of network service quality and overall grasp of network operation state need to be solved further. Understanding the internal features of the network helps to successfully design, control, and manage the network. As one of the important tools, the network traffic matrix describes the traffic distribution among all nodes in the network. It is an important basis for network design, management and routing configuration. However, because of the huge network scale, the massive data transmission and the heterogeneous distributed network mode, it is very difficult or even impossible to obtain the traffic matrix directly through the network measurement. Therefore, a variety of indirect measurement methods using finite measurement information to estimate network traffic matrix have been proposed. The main work of this paper includes: 1) firstly, the research significance of traffic matrix and the current research situation at home and abroad are introduced, and the hierarchical structure of this paper is briefly described. 2) three kinds of methods for indirect measurement of flow matrix are summarized, the basic description of the techniques used in each method is given, and the advantages and disadvantages of each method are analyzed. 3) on the basis of high-order neural networks, the latest chemical reaction optimization algorithms are applied. A new CRO-PSNN algorithm is proposed to estimate the flow matrix. For this algorithm, this paper discusses its advantages from two aspects: one is the advantage of high-order neural networks for high-dimensional ill-conditioned problems such as traffic matrix estimation. The inclusion multiplier enables higher order neural networks to deal with higher order problems and strongly nonlinear problems that are beyond the reach of ordinary neural networks. The second is to use chemical reaction optimization algorithm to participate in the learning process of high-order neural network, avoid the weight adjustment of the previous error participation, and reduce the calculation amount. Finally, according to the existing theoretical and experimental basis, the simulation experiment is compared with the well-known flow matrix estimation method, and the advantages of the method are proved. Finally, the paper summarizes the full text, reviews the research work done in this paper, and forecasts the future research direction according to the present situation.
【學(xué)位授予單位】：華中師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP393.06;TP183

【參考文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 趙國(guó)鋒;基于IP/MPLS骨干網(wǎng)的動(dòng)態(tài)業(yè)務(wù)流量矩陣測(cè)量及應(yīng)用研究[D];重慶大學(xué);2003年

相關(guān)碩士學(xué)位論文 前2條

1 劉珂;基于附加鏈路信息的網(wǎng)絡(luò)流量矩陣測(cè)算方法[D];北京郵電大學(xué);2011年

2 王曉陽(yáng);基于IP骨干網(wǎng)絡(luò)的流量矩陣估計(jì)方法研究[D];湖南大學(xué);2011年

，

本文編號(hào)：2059438