跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 賴昱瑋
Yu-wei Lai
論文名稱： 資料傳輸網路之貝氏診斷
Bayesian Tomography for Data Routing Networks
指導教授： 洪英超
Ying-chao Hung
口試委員:
學位類別： 碩士
Master
系所名稱： 理學院 - 統計研究所
Graduate Institute of Statistics
畢業學年度： 97
語文別： 中文
論文頁數： 41
中文關鍵詞： 服務品質 、工作遺失率 、資料傳輸網路 、流量控制策略
外文關鍵詞： quality of service, job loss rate, tree-type of data routing network model, flow control policy
相關次數： 點閱：8  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著現代化網路的快速擴張及普及化，網路使用者對於網路服務品質(quality of service；QoS)的要求也越來越高，而網路服務品質通常可藉由工作延遲(job delay)、工作遺失率(job loss rate)等系統表現值來衡量。本文探討一樹狀架構的資料傳輸網路(tree-type of data routing network)，並利用點對點(end-to-end)的部份資訊來偵測(或估計)網路連結的工作遺失率(通過率)。本文使用的方法是建立一個統計模型並藉由貝氏方法來解決此問題。最後，我們介紹如何藉由所得到之工作通過率估計值建構一最佳動態的流量控制策略(flow control policy)。

    Assessing and monitoring the performance of computer and communications networks is an important problem for network engineers. We consider a tree-type of data routing network model, and it has a broad application in real life (public telephone switches, call centers, etc.). Our focus here is on estimating and monitoring network Quality-of-Service (QoS) parameters. The QoS of a network can usually be measured by some system performance such as job delay or job loss rate. In this article , We propose a Bayesian method for detect(or,say,estimate) the job loss rate of edge level parameters from end-to-end path-level measurements, an important engineering problem that raises interesting statistical modeling issues. Further, we introduce how we can use the estimated job loss rate to choose an optimal dynamic flow control policy.

    摘要 ............................................... i Abstract............................................ ii 誌謝................... ............................ iii 目錄................................................ v 圖目次.............................................. vii 表目次.............................................. viii 第一章 緒論........................................ 1 第二章 網路模型介紹及統計反向問題................ 3 2.1 樹狀網路模型................................. 3 2.2 統計反向問題(Statistical Inverse Problem).... 5 2.3 奇異值分解解統計反向問題..................... 6 第三章 貝氏方法之探討............................ 11 3.1 先驗分佈之選取............................... 11 3.2 Gibbs Sampler ............................... 12 3.3 計算問題..................................... 15 第四章 電腦模擬研究.............................. 17 第五章 建構動態最佳流量控制策略.................. 23 5.1 逐次檢定(Sequential Test)................... 24 5.2 多變量指數加權移動平均(MEWMA)管制圖......... 25 第六章 結論及未來研究方向........................ 26 參考文獻 ........................................... 27 附錄 ............................................... 30

    [1] C''aceres, R., Duffield, N. G., Horowitz, J. and Towsley, D. (1999).“Multicast Based Inference of Network Internal Loss Characteristics.”IEEE Transactions on Information Theory,45,2462–2480.
    [2] Casella, G. and George, E. I. (1992).“Explaining the Gibbs Sampler.”The American Statistician,46,167–174.
    [3] Castro, R., Coates, M., Liang, G., Nowak, R. and Yu,B. (2004).“Network Tomography: Recent Developments.” Statistical Science,19,499–517.
    [4] Choudhury, A. and Borthakur, A. C. (2008).“Bayesian Inference and Prediction in the Single Server Markovian Queue.”Metrika, 67, 371–383.
    [5] Damien, P. and Walker, S. G. (2001).“Sampling Truncated Normal,Beta and Gamma Densities.”Journal of Computational and Graphical Statistics,10,206–215.
    [6] Denby, L., Landwehr, J. M., Mallows, C. L., Meloche, J.,Tuck, J., Xi, B., Michailidis, G. and Nair, V. N. (2007).“Statistical Aspects of the Analysis of Data Networks.”Technometrics,49,318–334.
    [7] Gelfand, A. and Smith, F. (1990).“Sampling-Based Approaches to Calculating Marginal Densities.”Journal of the American Statistical Association,85,398–409.
    [8] Geman, S. and Geman, D. (1984).“Stochastic Relaxation, Gibbs Distributions and the Bayesian Restoration of Images.”IEEE Trans. On Pattern Analysis and Machine Intelligence,6,721–741.
    [9] Geo5204“Minimum Norm Solution”Inverse Theory Lecture 6.http://www.geo.umn.edu/courses/5204/Lectures/lecture 06.pdf.
    [10] Lawrence, E., Michailidis, G. and Nair, V. N. (2003). “Maximum Likelihood Estimation of Internal Network Link Delay Distributions Using Multicast Measurements.”In Proceedings of the Conference on Information Sciences and Systems.
    [11] Lawrence, E., Michailidis, G. and Nair, V. N.(2007). “Statistical Inverse Problems in Active Network Tomography.”in Statistical Inverse Problems, Liu, R., Straderman, W. and Zhang, C. H.(editors), IMS Lecture Note Series.
    [12] Lo, P. F., Paxson, V. and Towsley, D. F. (2001). “Inferring Link Loss Using Striped Unicast Probes.” Duffield, N. G. Proc. IEEE Infocom Anchorage, Alaska, pp. 22–26.
    [13] Lowry, C. A. and Woodall, W. H. (1992).“A Multivariate Exponentially Weighted Moving Average Control Chart.”Technometrics,34,46–53.
    [14] Nadarajah, S. and Kote, S. (2006).“R Programs for Computing Truncated Distribution.”Journal of Statistical Software,16.
    [15] Rrabhu, S. S. and Runger, G. C. (1997). “Designing a Multivariate EWMA Control Chart.” Journal of Quality Technology,29,8–15.
    [16] Qiu, W., Skafidas, E. and Hao, P. (2009).“Enhanced Tree Routing for Wireless Sensor Network.”Ad Hoc Network,7,638–650.
    [17] Vardi,Y. (1996).“Network Tomography : Estimating Source Destination Traffic Intensities from Link Data.” Journal of the American Statistical Association,91,365–377.
    [18] Xi, B., Michailidis, G. and Nair, V. N. (2006). “Estimating Network Loss Rates Using Active Tomography.” Journal of the American Statistical Association, 101, 1430–1448.
    [19] Zeger, S. L. and Karim, M. R. (1991).“Generalized Linear Models with Random Effects : A Gibbs Sampling Approach.”Journal of the American Statistical Association,86,79–86.
    [20]詹政霖(2008),『 The Control and Statistical Inverse Problem for Tree Types of Queueing Networks』,國立中央大學,碩士論文。

    QR CODE
    :::