本文關(guān)鍵詞： 認(rèn)知網(wǎng)絡(luò) QoS 流量預(yù)測(cè) 負(fù)載均衡　出處：《北京郵電大學(xué)》2014年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著未來(lái)互聯(lián)網(wǎng)的架構(gòu)及使用行為模式所發(fā)生的翻天覆地的變化,網(wǎng)絡(luò)中的數(shù)據(jù)流量也將隨用戶(hù)數(shù)量、服務(wù)應(yīng)用類(lèi)型的增多而快速增長(zhǎng)。對(duì)于日趨復(fù)雜的網(wǎng)絡(luò)接入環(huán)境,如何根據(jù)網(wǎng)絡(luò)環(huán)境狀態(tài)進(jìn)行有效地網(wǎng)絡(luò)流量預(yù)測(cè)與負(fù)載均衡決策,更好地協(xié)調(diào)各種網(wǎng)絡(luò)資源,解決網(wǎng)絡(luò)擁塞和服務(wù)質(zhì)量下降等一系列問(wèn)題,對(duì)于未來(lái)異構(gòu)網(wǎng)絡(luò)流量控制與性能測(cè)量具有重要的意義。認(rèn)知網(wǎng)絡(luò)不僅具有頻譜動(dòng)態(tài)感知切換功能,還具有對(duì)節(jié)點(diǎn)地理信息、鏈路質(zhì)量、網(wǎng)絡(luò)流量、用戶(hù)偏好、業(yè)務(wù)類(lèi)型以及服務(wù)質(zhì)量等方面的認(rèn)知學(xué)習(xí)決策能力,因此可以更好的進(jìn)行網(wǎng)絡(luò)流量預(yù)測(cè),進(jìn)一步改善網(wǎng)間互通,優(yōu)化網(wǎng)絡(luò)流量,實(shí)現(xiàn)負(fù)載均衡,提升網(wǎng)絡(luò)性能。 本文通過(guò)對(duì)傳統(tǒng)互聯(lián)網(wǎng)流量預(yù)測(cè)技術(shù)的研究和認(rèn)知網(wǎng)絡(luò)智能感知特性的分析,并重點(diǎn)結(jié)合認(rèn)知網(wǎng)絡(luò)中的流量預(yù)測(cè)與負(fù)載均衡技術(shù),開(kāi)展本課題工作,主要工作如下： 首先研究了當(dāng)前網(wǎng)絡(luò)中的一些流量預(yù)測(cè)方法,對(duì)其中的ARIMA模型及馬爾科夫鏈模型原理進(jìn)行了詳細(xì)的分析,并利用仿真實(shí)驗(yàn)對(duì)這些預(yù)測(cè)模型進(jìn)行了實(shí)驗(yàn)。本文在此基礎(chǔ)上提出了一種基于部分可觀(guān)馬爾科夫過(guò)程的認(rèn)知網(wǎng)絡(luò)流量預(yù)測(cè)模型。該方法充分考慮到了認(rèn)知網(wǎng)絡(luò)中多種參數(shù)的不可測(cè)性,不完整性,可以根據(jù)認(rèn)知網(wǎng)絡(luò)中前一時(shí)刻的狀態(tài),采用部分可觀(guān)測(cè)的參數(shù)進(jìn)行流量預(yù)測(cè),解決流量預(yù)測(cè)中的不可觀(guān)參數(shù)選擇問(wèn)題,提高流量預(yù)測(cè)精度。 然后本文根據(jù)上述的流量預(yù)測(cè)模型提出了一種認(rèn)知網(wǎng)絡(luò)負(fù)載均衡算法,可根據(jù)所設(shè)計(jì)的分類(lèi)方法及預(yù)測(cè)算法對(duì)傳輸業(yè)務(wù)分類(lèi)和預(yù)測(cè)結(jié)果對(duì)網(wǎng)絡(luò)流量進(jìn)行合理調(diào)度和均衡,提高網(wǎng)絡(luò)吞吐量,改進(jìn)網(wǎng)絡(luò)資源利用率與數(shù)據(jù)傳輸性能。 最后,本文在認(rèn)知網(wǎng)絡(luò)系統(tǒng)中進(jìn)行該課題的實(shí)現(xiàn),對(duì)傳統(tǒng)模式下的網(wǎng)絡(luò)狀態(tài)與采用本方案下的網(wǎng)絡(luò)狀態(tài)進(jìn)行比較,選取網(wǎng)絡(luò)吞吐量,丟包率,時(shí)延,抖動(dòng)等參數(shù)進(jìn)行了具體分析,體現(xiàn)出了本方案的優(yōu)勢(shì)。
[Abstract]:With the great changes in the architecture of the Internet and the mode of using the Internet in the future, the data flow in the network will also grow rapidly with the increase of the number of users and the types of service applications. How to make effective network traffic prediction and load balancing decision according to the network environment condition, better coordinate all kinds of network resources, solve a series of problems such as network congestion and quality of service decline, etc. Cognitive network not only has the function of spectrum dynamic sensing switching, but also has the function of node geographic information, link quality, network traffic and user preference. Because of the cognitive learning decision ability of service type and quality of service, it can better predict network traffic, further improve interworking, optimize network traffic, realize load balance, and improve network performance. Through the research of traditional Internet traffic prediction technology and the analysis of cognitive network intelligent perception characteristic, and combining the traffic prediction and load balancing technology in cognitive network, this paper carries out the work of this subject, the main work is as follows:. Firstly, some current network traffic forecasting methods are studied, and the principle of ARIMA model and Markov chain model are analyzed in detail. On the basis of these experiments, a traffic prediction model of cognitive network based on partially observable Markov process is proposed. This method takes full account of the cognitive network. The untestability of multiple parameters, According to the state of the previous moment in the cognitive network, the incomplete state can be used to predict the flow with some observable parameters, which can solve the problem of the unobservable parameter selection in the traffic prediction and improve the accuracy of the traffic prediction. Then, according to the above traffic prediction model, this paper proposes a cognitive network load balancing algorithm, which can reasonably schedule and balance the network traffic according to the designed classification method and prediction algorithm. Improve network throughput, network resource utilization and data transmission performance. Finally, this paper carries on the realization in the cognitive network system, compares the network state under the traditional mode with the network state under this scheme, selects the network throughput, the packet loss rate, the delay, The jitter and other parameters are analyzed in detail, which shows the advantages of this scheme.
【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(lèi)號(hào)】：TP393.06

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 王靖岱,陳紀(jì)忠,陽(yáng)永榮,程志強(qiáng),戴連奎;迭代動(dòng)態(tài)規(guī)劃在樹(shù)脂牌號(hào)切換最優(yōu)化模型中的應(yīng)用[J];高�；瘜W(xué)工程學(xué)報(bào);2000年03期

2 郭萌;王玨;;數(shù)據(jù)挖掘與數(shù)據(jù)庫(kù)知識(shí)發(fā)現(xiàn):綜述[J];模式識(shí)別與人工智能;1998年03期

，

本文編號(hào)：1499077