基于數(shù)據(jù)挖掘的IPTV故障診斷研究與實現(xiàn)
發(fā)布時間：2018-09-12 09:48
【摘要】：隨著多媒體通信技術(shù)的迅猛發(fā)展,越來越多的用戶能夠在家中享受IPTV(Internet Protocol Television)服務(wù)。為了保證極佳的用戶體驗,IPTV運營商們盡力支撐高質(zhì)量視頻節(jié)目并確保視頻傳輸通暢。與此同時,運維部門的壓力也越來越大,通常每日都要解決不同程度、不同層面的困難與故障。因此,如何客觀準確地評估IPTV服務(wù)質(zhì)量并及時維護IPTV網(wǎng)絡(luò)正常運行已成為當下的研究熱點。本論文提出了全新的IPTV運維質(zhì)量評估方案,該方案是一套能高效精準定位并診斷IPTV網(wǎng)絡(luò)故障的綜合系統(tǒng)。該IPTV業(yè)務(wù)服務(wù)質(zhì)量評估系統(tǒng)在構(gòu)建過程中,特別融合潛在用戶報障與潛在設(shè)備預(yù)警這兩方面。在采用故障設(shè)備預(yù)測模型來解決潛在設(shè)備預(yù)警過程中,不僅使用傳統(tǒng)服務(wù)質(zhì)量QoS(Quality of Service)指標,也充分考慮并采用能反映用戶觀看行為的客觀用戶體驗質(zhì)量QoE(Quality of Experience)指標。此外,本文針對IPTV故障定位診斷還進行以下工作:一方面,本文提出了一個綜合故障設(shè)備預(yù)測模型,該模型首先挖掘機頂盒指標參數(shù)與網(wǎng)絡(luò)狀況之間的關(guān)聯(lián),使IPTV網(wǎng)絡(luò)故障診斷更加高效準確,特別是針對卡頓花屏故障現(xiàn)象。該故障設(shè)備預(yù)測模型包括質(zhì)差指標、記錄、用戶三方面。首先,質(zhì)差指標模型作為替代傳統(tǒng)決策樹生成中的特征提取部分,負責(zé)從候選機頂盒指標中篩選出有效有限指標。其次,質(zhì)差記錄模型是基于改進的決策樹算法,通過不斷調(diào)整閾值以達到高準確率以及低誤判率。最后的質(zhì)差用戶模型將反映用戶觀看體驗質(zhì)量的觀看時長考慮在內(nèi)。實驗結(jié)果表明,質(zhì)差用戶模型的預(yù)測準確率能高達83.25%。另一方面,針對傳統(tǒng)算法在非均衡IPTV數(shù)據(jù)集下用戶報障預(yù)測效果不理想的問題,本文將影響網(wǎng)絡(luò)服務(wù)質(zhì)量的傳統(tǒng)網(wǎng)絡(luò)參數(shù)QoS和主觀反映用戶體驗質(zhì)量QoE的MOS(Mean Opinion Score)評分結(jié)合來預(yù)測用戶是否報障。本文在已有的ODR-BSMOTE-SVM算法基礎(chǔ)上,針對過采樣算法產(chǎn)生噪聲以及核參數(shù)沒有進行優(yōu)化的缺陷,提出了一種改進型算法。該改進算法首先采用欠采樣和過采樣算法及數(shù)據(jù)清洗算法對原始非均衡數(shù)據(jù)進行處理,然后通過自適應(yīng)變核參數(shù)尋找近似最優(yōu)值,最終實現(xiàn)提升分類效果。實驗結(jié)果表明,較傳統(tǒng)標準支持向量機(SVM)算法和ODR-BSMOTE-SVM算法,本文所提出的算法能獲得更佳的預(yù)測效果。
[Abstract]:With the rapid development of multimedia communication technology, more and more users can enjoy IPTV (Internet Protocol Television) services at home. IPTV operators try to support high-quality video programs and ensure that video is transmitted smoothly in order to ensure an excellent user experience. At the same time, the pressure of operations and maintenance departments is increasing, usually to solve different levels of difficulties and failures on a daily basis. Therefore, how to evaluate IPTV QoS objectively and accurately and maintain the normal operation of IPTV network in time has become a hot research topic. In this paper, a new IPTV operation and maintenance quality evaluation scheme is proposed, which is a comprehensive system which can locate and diagnose IPTV network faults efficiently and accurately. In the process of constructing the IPTV service quality assessment system, the potential user reporting barrier and potential equipment warning are especially integrated. In the process of using fault equipment prediction model to solve the potential equipment warning process, not only the traditional quality of service (QoS (Quality of Service) index is used, but also the objective user experience quality (QoE (Quality of Experience) index, which can reflect the user's viewing behavior, is fully considered and adopted. In addition, this paper also does the following work for IPTV fault location diagnosis: on the one hand, this paper proposes a comprehensive fault equipment prediction model, which first mining the relationship between set-top box index parameters and network condition. Make the IPTV network fault diagnosis more efficient and accurate, especially for the phenomenon of Carton flower screen fault. The fault equipment prediction model includes three aspects: quality index, record and user. First, the quality difference index model, as the feature extraction part of the traditional decision tree generation, is responsible for screening out the effective limited index from the candidate set-top box index. Secondly, the quality difference record model is based on the improved decision tree algorithm, by constantly adjusting the threshold to achieve high accuracy and low error rate. The final quality difference user model takes into account the length of viewing time that reflects the quality of the user's viewing experience. The experimental results show that the prediction accuracy of the quality difference user model can reach 83.25%. On the other hand, aiming at the problem that the performance of the traditional algorithm is not satisfactory under the unbalanced IPTV data set, In this paper, the traditional network parameter QoS which affects the quality of service of the network is combined with the MOS (Mean Opinion Score) score, which reflects the quality of user experience. In this paper, based on the existing ODR-BSMOTE-SVM algorithm, an improved algorithm is proposed to overcome the defects of over-sampling algorithm which produces noise and the kernel parameters are not optimized. The improved algorithm firstly processes the original unbalanced data by using the under-sampling and over-sampling algorithm and the data cleaning algorithm, and then finds the approximate optimal value through adaptive variable kernel parameters, and finally realizes the improvement of classification effect. The experimental results show that the proposed algorithm can obtain better prediction results than the traditional standard support vector machine (SVM) algorithm and the ODR-BSMOTE-SVM algorithm.
【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TN949.292
[Abstract]:With the rapid development of multimedia communication technology, more and more users can enjoy IPTV (Internet Protocol Television) services at home. IPTV operators try to support high-quality video programs and ensure that video is transmitted smoothly in order to ensure an excellent user experience. At the same time, the pressure of operations and maintenance departments is increasing, usually to solve different levels of difficulties and failures on a daily basis. Therefore, how to evaluate IPTV QoS objectively and accurately and maintain the normal operation of IPTV network in time has become a hot research topic. In this paper, a new IPTV operation and maintenance quality evaluation scheme is proposed, which is a comprehensive system which can locate and diagnose IPTV network faults efficiently and accurately. In the process of constructing the IPTV service quality assessment system, the potential user reporting barrier and potential equipment warning are especially integrated. In the process of using fault equipment prediction model to solve the potential equipment warning process, not only the traditional quality of service (QoS (Quality of Service) index is used, but also the objective user experience quality (QoE (Quality of Experience) index, which can reflect the user's viewing behavior, is fully considered and adopted. In addition, this paper also does the following work for IPTV fault location diagnosis: on the one hand, this paper proposes a comprehensive fault equipment prediction model, which first mining the relationship between set-top box index parameters and network condition. Make the IPTV network fault diagnosis more efficient and accurate, especially for the phenomenon of Carton flower screen fault. The fault equipment prediction model includes three aspects: quality index, record and user. First, the quality difference index model, as the feature extraction part of the traditional decision tree generation, is responsible for screening out the effective limited index from the candidate set-top box index. Secondly, the quality difference record model is based on the improved decision tree algorithm, by constantly adjusting the threshold to achieve high accuracy and low error rate. The final quality difference user model takes into account the length of viewing time that reflects the quality of the user's viewing experience. The experimental results show that the prediction accuracy of the quality difference user model can reach 83.25%. On the other hand, aiming at the problem that the performance of the traditional algorithm is not satisfactory under the unbalanced IPTV data set, In this paper, the traditional network parameter QoS which affects the quality of service of the network is combined with the MOS (Mean Opinion Score) score, which reflects the quality of user experience. In this paper, based on the existing ODR-BSMOTE-SVM algorithm, an improved algorithm is proposed to overcome the defects of over-sampling algorithm which produces noise and the kernel parameters are not optimized. The improved algorithm firstly processes the original unbalanced data by using the under-sampling and over-sampling algorithm and the data cleaning algorithm, and then finds the approximate optimal value through adaptive variable kernel parameters, and finally realizes the improvement of classification effect. The experimental results show that the proposed algorithm can obtain better prediction results than the traditional standard support vector machine (SVM) algorithm and the ODR-BSMOTE-SVM algorithm.
【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TN949.292
【參考文獻】
相關(guān)期刊論文 前10條
1 干陽琳;歐鷗;黃媛媛;;中國IPTV增值業(yè)務(wù)發(fā)展現(xiàn)狀與分析[J];科技創(chuàng)新導(dǎo)報;2016年08期
2 黃海峰;;用戶日放號峰值破萬 廣東4K IPTV業(yè)務(wù)緣何領(lǐng)跑?[J];通信世界;2016年13期
3 青格日勒;云鵬增;;三網(wǎng)融合背景下IPTV的發(fā)展趨勢[J];數(shù)字傳媒研究;2016年03期
4 董智純;楊林;詹念武;廖振松;;一種基于大數(shù)據(jù)技術(shù)的投訴分析與預(yù)測系統(tǒng)[J];信息通信;2015年09期
5 廖振松;葉楊;劉德好;劉余罡;;一種基于大數(shù)據(jù)的投訴精細化分析系統(tǒng)[J];信息通信;2014年09期
6 何清;李寧;羅文娟;史忠植;;大數(shù)據(jù)下的機器學(xué)習(xí)算法綜述[J];模式識別與人工智能;2014年04期
7 李忠國;侯杰;王凱;劉慶華;;模糊支持向量機在路面識別中的應(yīng)用[J];數(shù)據(jù)采集與處理;2014年01期
8 汪友生;胡百樂;張麗杰;吳煥煥;王志東;李亦林;陳建新;;基于支持向量機的動脈硬化斑塊識別[J];數(shù)據(jù)采集與處理;2012年03期
9 林闖;胡杰;孔祥震;;用戶體驗質(zhì)量(QoE)的模型與評價方法綜述[J];計算機學(xué)報;2012年01期
10 陶新民;童智靖;劉玉;付丹丹;;基于ODR和BSMOTE結(jié)合的不均衡數(shù)據(jù)SVM分類算法[J];控制與決策;2011年10期
相關(guān)博士學(xué)位論文 前2條
1 史志明;網(wǎng)絡(luò)視頻質(zhì)量評估方法與測試技術(shù)研究[D];北京郵電大學(xué);2013年
2 古強;直播型IPTV QoS若干關(guān)鍵技術(shù)的研究[D];北京郵電大學(xué);2010年
相關(guān)碩士學(xué)位論文 前1條
1 胡s，
本文編號：2238637
本文鏈接：http://sikaile.net/kejilunwen/xinxigongchenglunwen/2238637.html
最近更新
教材專著
