本文選題：流媒體系統(tǒng) + 覆蓋網(wǎng)絡(luò)��； 參考：《中國(guó)科學(xué)技術(shù)大學(xué)》2014年博士論文

【摘要】：隨著通信技術(shù)和互聯(lián)網(wǎng)的發(fā)展,視頻點(diǎn)播服務(wù)(Video on Demand, VoD)以其訪問(wèn)便捷、內(nèi)容豐富等特征越來(lái)越受到人們的關(guān)注并得到了飛速發(fā)展,成為互聯(lián)網(wǎng)上的主流應(yīng)用。為應(yīng)對(duì)龐大的用戶規(guī)模、海量的數(shù)據(jù)存儲(chǔ)和動(dòng)態(tài)的用戶交互請(qǐng)求,內(nèi)容分發(fā)網(wǎng)絡(luò)和對(duì)等網(wǎng)絡(luò)等構(gòu)建于物理網(wǎng)絡(luò)之上的邏輯覆蓋網(wǎng)絡(luò)被用于流媒體系統(tǒng)的開(kāi)發(fā),以提高系統(tǒng)的吞吐量和可擴(kuò)展性。用戶在視頻訪問(wèn)過(guò)程中的交互式操作和分布式系統(tǒng)中節(jié)點(diǎn)及資源的動(dòng)態(tài)變化都制約了流媒體服務(wù)的服務(wù)質(zhì)量,研究流媒體中的用戶行為模型和資源管理策略,對(duì)提供高質(zhì)量的流媒體服務(wù)具有重要的現(xiàn)實(shí)意義。 本文以國(guó)家863項(xiàng)目“融合網(wǎng)絡(luò)業(yè)務(wù)體系的開(kāi)發(fā)”課題和國(guó)家科技支撐計(jì)劃“支持跨區(qū)域、多運(yùn)營(yíng)商的新一代廣播電視服務(wù)系統(tǒng)”課題為研究背景,以提高系統(tǒng)資源利用效率、保障流媒體服務(wù)的服務(wù)質(zhì)量為目的,在多媒體覆蓋網(wǎng)絡(luò)中研究系統(tǒng)的資源管理和服務(wù)組合策略,通過(guò)對(duì)用戶在流媒體播放過(guò)程中的交互式操作行為的統(tǒng)計(jì)建模,實(shí)現(xiàn)高性能的流媒體數(shù)據(jù)緩存預(yù)取策略。本文主要研究?jī)?nèi)容包括以下三個(gè)方面： (1)提出一種保障QoS分布式流媒體系統(tǒng)資源管理策略 針對(duì)動(dòng)態(tài)分布式環(huán)境下服務(wù)節(jié)點(diǎn)資源分配和流媒體服務(wù)的QoS保障等問(wèn)題,在傳統(tǒng)的內(nèi)容分發(fā)網(wǎng)絡(luò)的基礎(chǔ)上提出采用多媒體覆蓋網(wǎng)整合和管理分布式系統(tǒng)中的資源,并采用具有QoS保證的服務(wù)組合算法向用戶提供具有QoS偏好的流媒體服務(wù)。通過(guò)對(duì)系統(tǒng)中各種資源的分析及服務(wù)質(zhì)量各個(gè)屬性的定義,提出了元服務(wù)QoS模型以及組合服務(wù)的QoS計(jì)算方法,在給出具有服務(wù)質(zhì)量保證的服務(wù)組合問(wèn)題的數(shù)學(xué)模型的基礎(chǔ)上,提出基于學(xué)習(xí)自動(dòng)機(jī)理論的服務(wù)組合算法。該算法通過(guò)對(duì)服務(wù)覆蓋網(wǎng)中資源與服務(wù)狀況的感知與學(xué)習(xí),尋找滿足資源約束條件與用戶給定服務(wù)質(zhì)量的服務(wù)組合策略,在實(shí)驗(yàn)設(shè)定由5-90個(gè)元服務(wù)構(gòu)成的組合服務(wù)時(shí),使用該學(xué)習(xí)算法可以在多項(xiàng)式時(shí)間內(nèi)選擇出最優(yōu)或次優(yōu)的服務(wù)組合策略,并具有良好的可擴(kuò)展性。 (2)建立基于隱馬爾可夫模型的用戶交互式行為模型 建立和分析用戶的交互行為模型可以對(duì)系統(tǒng)的性能進(jìn)行有針對(duì)性的優(yōu)化,以提高服務(wù)效率。本文在統(tǒng)計(jì)和分析用戶觀看視頻過(guò)程中的交互行為的基礎(chǔ)上,將用戶觀看行為建模為隱馬爾可夫模型,并在所建立模型的基礎(chǔ)上對(duì)用戶瀏覽狀態(tài)進(jìn)行預(yù)測(cè),該策略使用Baum-Welch法對(duì)隱狀態(tài)的轉(zhuǎn)移概率參數(shù)進(jìn)行極大似然估計(jì),并利用系統(tǒng)參數(shù)的部分先驗(yàn)信息,避免所估計(jì)參數(shù)的似然函數(shù)陷入局部極大值,然后根據(jù)系統(tǒng)參數(shù)和單個(gè)用戶的在線操作行為更新用戶瀏覽狀態(tài)的后驗(yàn)概率,使用最大后驗(yàn)概率準(zhǔn)則對(duì)用戶行為進(jìn)行判決。通過(guò)貝葉斯推理,跟蹤用戶瀏覽狀態(tài)的變化,充分利用了HMM模型的先驗(yàn)知識(shí)和當(dāng)前用戶記錄在流媒體服務(wù)器上的操作信息,尤其是對(duì)于熱門(mén)視頻的觀看行為,得益于用戶在觀看熱門(mén)視頻過(guò)程中豐富的VCR操作,對(duì)用戶的交互操作預(yù)測(cè)準(zhǔn)確率能達(dá)到77.5%以上,該策略具有較為明顯的建模能力。 (3)提出一種基于模型預(yù)測(cè)的流媒體預(yù)取策略 本文綜合計(jì)算了用戶在視頻訪問(wèn)過(guò)程中的初始訪問(wèn)延遲以及視頻對(duì)象在播放過(guò)程中因無(wú)法及時(shí)獲得所需數(shù)據(jù)而導(dǎo)致的網(wǎng)絡(luò)抖動(dòng)延遲,結(jié)合媒體對(duì)象各數(shù)據(jù)段的初始訪問(wèn)概率和條件訪問(wèn)概率提出了降低延遲的優(yōu)化公式。根據(jù)模型參數(shù)和用戶當(dāng)前所處狀態(tài)對(duì)用戶下一時(shí)刻可能訪問(wèn)的數(shù)據(jù)段進(jìn)行判決,由判決結(jié)果計(jì)算影片數(shù)據(jù)段的預(yù)取價(jià)值和緩存價(jià)值并實(shí)施預(yù)取策略以降低用戶訪問(wèn)視頻過(guò)程中的延遲和抖動(dòng)。實(shí)驗(yàn)表明,本算法針對(duì)交互操作頻繁的熱門(mén)視頻,采用預(yù)取技術(shù)能充分利用系統(tǒng)的帶寬并及時(shí)獲得用戶將要訪問(wèn)的數(shù)據(jù)從而降低訪問(wèn)延遲發(fā)生的概率,提高流媒體系統(tǒng)的服務(wù)質(zhì)量,其延時(shí)降低量比采用簡(jiǎn)單統(tǒng)計(jì)的預(yù)取算法高出6%左右,比單純采用LRU策略的緩存算法高出20%。
[Abstract]:With the development of communication technology and Internet , Video on Demand ( VOD ) has been paid more attention to and developed rapidly and becomes the mainstream application on the Internet . In order to deal with the huge user scale , massive data storage and dynamic user interaction , content distribution network and peer - to - peer network are used in the development of streaming media system .

In this paper , based on the research background of the research background of the national 863 project " Development of converged network service system " and the " new generation broadcast television service system supporting cross - region and multi - operator " , this paper aims to improve the utilization efficiency of system resources and guarantee the service quality of streaming media service . In this paper , the resource management and service combination strategy of the system is studied in the multimedia overlay network .

( 1 ) To propose a QoS distributed streaming media system resource management strategy

On the basis of the traditional content distribution network , a service combination algorithm based on the theory of learning automata is put forward based on the analysis of resources and service conditions in the system , and the service combination algorithm based on the theory of learning automata is proposed .

( 2 ) Establishing User Interactive Behavior Model Based on Hidden Markov Model

Based on the statistics and analysis of the interactive behavior of the user in watching video , the user ' s viewing behavior is modeled as hidden Markov model , and the user ' s browsing state is predicted based on the established model . This strategy makes full use of the knowledge of the HMM model and the operation information recorded on the streaming server by the current user .

( 3 ) A kind of streaming media pre - fetching strategy based on model prediction is proposed .

Experiments show that the algorithm can fully utilize the bandwidth of the system and obtain the data to be accessed by the user in time according to the model parameters and the current state of the user , so as to reduce the delay and jitter in the user ' s access to the video . Experiments show that the algorithm can fully utilize the bandwidth of the system and obtain the data to be accessed by the user in a timely manner , thereby reducing the probability of the access delay and improving the service quality of the streaming media system .

【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN948.64

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 林闖;胡杰;孔祥震;;用戶體驗(yàn)質(zhì)量(QoE)的模型與評(píng)價(jià)方法綜述[J];計(jì)算機(jī)學(xué)報(bào);2012年01期

2 邱菡;李玉峰;鄔江興;;保障連續(xù)媒體流用戶層QoS的緩存控制[J];軟件學(xué)報(bào);2009年07期

3 王必堯;王勁林;吳剛;劉學(xué);;一種應(yīng)用于分布式緩存系統(tǒng)中的緩存部署算法[J];小型微型計(jì)算機(jī)系統(tǒng);2012年08期

，

本文編號(hào)：1765106