Cargando…
Internet teletraffic modeling and estimation /
This book presents a new statespace model for Internet traffic, which is based on a finite-dimensional representation of the Autoregressive Fractionally Integrated Moving Average (ARFIMA) random process. The modeling via Autoregressive (AR) processes is also investigated.
| Clasificación: | Libro Electrónico |
|---|---|
| Autores principales: | , |
| Otros Autores: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Aalborg, Denmark :
River Publishers,
2013.
|
| Colección: | River Publishers Series in Information Science and Technology
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Cover; Contents; List of Tables; List of Figures; Preface; List of acronyms and symbols; 1 Introduction; 1.1 Objectives of telecommunications carriers; 1.2 Traffic characteristics; 1.3 Questions and contributions; 1.4 Time series basic concepts; 1.4.1 Time series examples; 1.4.2 Operators notation; 1.4.3 Stochastic processes; 1.4.4 Time seriesmodeling; 2 The fractal nature of network traffic; 2.1 Fractals and self-similarity examples; 2.1.1 The Hurst exponent; 2.1.2 Samplemean variance; 2.2 Long range dependence; 2.2.1 Aggregate process; 2.3 Self-similarity.
- 2.3.1 Exact second order self-similarity2.3.2 Impulsiveness; 2.4 Final remarks: why is the data networks traffic fractal?; 3 Modeling of long-range dependent teletraffic; 3.1 Classes of modeling; 3.1.1 Non-parametric modeling; 3.2 Wavelet transform; 3.2.1 Multiresolution analysis and the discrete wavelet transform; 3.3 ModelMWM; 3.4 Parametric modeling; 3.4.1 ARFIMAmodel; 3.4.2 ARFIMA models prediction
- optimum estimation; 3.4.3 Formsof prediction; 3.4.4 Confidence interval; 3.4.5 ARFIMAprediction; 3.5 Longmemorystatistical tests; 3.5.1 R/Sstatistics; 3.5.2 GPHtest.
- 3.6 Some H and d estimation methods3.6.1 R/Sstatistics; 3.6.2 Variance plot; 3.6.3 Periodogram method; 3.6.4 Whittle's method; 3.6.5 Haslett and Raftery's MV approximate estimator; 3.6.6 Abry and Veitch'swavelet estimator; 3.7 Bi-spectrum and linearity test; 3.8 KPSS stationarity test; 4 State-space modeling; 4.1 Introduction; 4.2 TARFIMAmodel; 4.2.1 Multistep prediction with the Kalman filter; 4.2.2 The prediction power of the TARFIMA model; 4.3 Series exploratory analysis; 4.3.1 ARFIMA(0; 0.4; 0) series; 4.3.2 MWM series with H = 0.9; 4.3.3 Nile river series.
- 4.4 Prediction empirical studywith the TARFIMAmodel4.4.1 ARFIMA(0, d, 0) series; 4.4.2 MWMseries; 4.4.3 Nile river series between years 1007 and 1206; 4.4.4 Conclusions; 5 Modeling of Internet traffic; 5.1 Introduction; 5.2 Modeling of the UNC02 trace; 5.2.1 Exploratory analysis; 5.2.2 Long memory local analysis of the UNC02 trace; 5.2.3 Empirical prediction with the TARFIMA model; 6 Conclusions; Bibliography; Index; About the Authors.