本文關(guān)鍵詞： 測(cè)量 網(wǎng)絡(luò)視頻服務(wù) 用戶(hù)體驗(yàn)質(zhì)量 機(jī)器學(xué)習(xí)　出處：《北京交通大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著互聯(lián)網(wǎng)技術(shù)以及視頻多媒體技術(shù)的不斷發(fā)展,網(wǎng)絡(luò)視頻作為一種重要的休閑娛樂(lè)方式,受到了人們的一致追捧。思科公布的互聯(lián)網(wǎng)預(yù)測(cè)報(bào)告顯示:2015年網(wǎng)絡(luò)視頻流量占全部互聯(lián)網(wǎng)流量的70%,預(yù)計(jì)到2020年所有消費(fèi)的網(wǎng)絡(luò)流量中的視頻流量將占到82%,其中移動(dòng)視頻數(shù)據(jù)流量將占總網(wǎng)絡(luò)流量的50%。如此龐大的視頻數(shù)據(jù)流量對(duì)當(dāng)前的視頻服務(wù),特別是移動(dòng)端視頻服務(wù),帶來(lái)了極大的挑戰(zhàn)。與此同時(shí),視頻用戶(hù)對(duì)視頻觀看質(zhì)量也提出了更高層次的要求:高視頻分辨率、低啟動(dòng)時(shí)延、低緩沖率,追求更高的用戶(hù)體驗(yàn)質(zhì)量(Quality of Experience,QoE)。因此,研究如何精準(zhǔn)預(yù)測(cè)網(wǎng)絡(luò)視頻服務(wù)中的用戶(hù)體驗(yàn)質(zhì)量,近而提升視頻用戶(hù)體驗(yàn)質(zhì)量,具有很大的理論價(jià)值和商業(yè)應(yīng)用價(jià)值�，F(xiàn)有的關(guān)于用戶(hù)體驗(yàn)質(zhì)量的研究工作中,大多是研究視頻用戶(hù)觀看行為以及視頻質(zhì)量影響因素,或者提出一些復(fù)雜的控制平臺(tái)系統(tǒng)來(lái)優(yōu)化網(wǎng)絡(luò)視頻資源傳輸效率,或者研究復(fù)雜的視頻編碼,來(lái)提升用戶(hù)體驗(yàn)質(zhì)量。本文擬運(yùn)用機(jī)器學(xué)習(xí)算法,構(gòu)建簡(jiǎn)單、易部署的基于用戶(hù)終端的QoE模型,提升用戶(hù)體驗(yàn)質(zhì)量。本文的具體貢獻(xiàn)主要有如下四個(gè)方面。(1)詳細(xì)分析了 PPTV視頻用戶(hù)接入日志數(shù)據(jù)集,發(fā)現(xiàn):1)起始緩沖時(shí)長(zhǎng)比緩沖總時(shí)長(zhǎng)更需要針對(duì)性的優(yōu)化;2)緩沖次數(shù)與用戶(hù)有效觀看時(shí)間比的相關(guān)性最大。在此基礎(chǔ)上設(shè)計(jì)了一種高性能的基于隨機(jī)森林算法的QoE映射模型,在預(yù)測(cè)用戶(hù)體驗(yàn)質(zhì)量不好時(shí)的F1值達(dá)到0.77,并且起始緩沖時(shí)長(zhǎng)和緩沖次數(shù)對(duì)模型預(yù)測(cè)效果的影響較大。(2)開(kāi)發(fā)了一整套適用于LTE網(wǎng)絡(luò)環(huán)境下DASH視頻質(zhì)量研究的實(shí)驗(yàn)平臺(tái)。具體說(shuō)來(lái),在阿里云服務(wù)器上搭建了 DASH視頻服務(wù)器,并部署了 MongoDB數(shù)據(jù)庫(kù)用于測(cè)量數(shù)據(jù)的持久化存儲(chǔ);開(kāi)發(fā)了 Androidapp應(yīng)用用于采集LTE網(wǎng)絡(luò)質(zhì)量參數(shù),修改dashjs客戶(hù)端源碼來(lái)采集DASH視頻客戶(hù)端播放信息。(3)通過(guò)對(duì)實(shí)驗(yàn)測(cè)量數(shù)據(jù)的研究分析發(fā)現(xiàn):1)當(dāng)緩沖區(qū)長(zhǎng)度低于0.5秒鐘時(shí),視頻將會(huì)出現(xiàn)卡頓;2)當(dāng)前LTE網(wǎng)絡(luò)下的DASH視頻用戶(hù)體驗(yàn)質(zhì)量的主要問(wèn)題在于往返時(shí)間(RTT)。(4)提出了一種基于"時(shí)間窗口"的預(yù)測(cè)方法,設(shè)計(jì)了兩種基于隨機(jī)森林算法的QoE模型,在預(yù)測(cè)用戶(hù)體驗(yàn)質(zhì)量不好時(shí)的F1值達(dá)到0.87。并且,最佳的間隔時(shí)間窗口值:28秒,最佳的歷史時(shí)間窗口值為10秒到18秒。
[Abstract]:With the continuous development of Internet technology and video multimedia technology, network video as an important way of leisure and entertainment, In 2015, network video traffic accounted for 70 percent of all Internet traffic, and it is expected that by 2020, video traffic will account for 82 percent of all network traffic consumed. Moving video data traffic will account for 50 percent of the total network traffic. In particular, the mobile video service brings great challenges. At the same time, video users also put forward higher quality requirements for video viewing: high video resolution, low startup delay, low buffering rate. Therefore, research on how to accurately predict the quality of user experience in online video services, and improve the quality of video user experience, It has great theoretical value and commercial application value. Most of the existing research work on the quality of user experience is to study the viewing behavior of video users and the influencing factors of video quality. Or some complex control platform systems are proposed to optimize the transmission efficiency of network video resources, or to study complex video coding to improve the quality of user experience. The QoE model based on user terminal is easy to deploy to improve the quality of user experience. The specific contributions of this paper are as follows: (1) the PPTV video user access log data set is analyzed in detail. It is found that the initial buffer time is more important than the total buffer time to optimize the buffer times. The correlation between the buffer times and the effective viewing time ratio is the greatest. Based on this, a high performance QoE mapping model based on stochastic forest algorithm is designed. The F1 value is 0.77 when the user experience quality is not good, and the effect of the initial buffer time and buffer times on the model prediction effect is great.) A set of experimental platforms suitable for the research of DASH video quality in LTE network environment are developed. DASH video server was built on Ali cloud server, and MongoDB database was deployed for persistent storage of measurement data. Androidapp application was developed to collect LTE network quality parameters. Modify the dashjs client source code to collect the DASH video client playback information.) by analyzing the experimental data, we find that: 1) when the buffer length is less than 0.5 seconds, The main problem of the DASH video user experience quality under the current LTE network is that the round trip time is RTT. 4) A prediction method based on "time window" is proposed, and two QoE models based on stochastic forest algorithm are designed. The F1 value is 0.87 when the user experience quality is not good. Moreover, the optimal interval window value is: 28 seconds, and the best historical time window value is from 10 seconds to 18 seconds.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP393.09;TN919.8

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 林闖;胡杰;孔祥震;;用戶(hù)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 孫知信;陳亞當(dāng);任志廣;;基于P2P流媒體直播系統(tǒng)的數(shù)據(jù)傳輸策略[J];通信學(xué)報(bào);2011年06期

，

本文編號(hào)：1499376