| W.-C. Lau, A. Erramilli, J. L. Wang, and W. Willinger, "Self-similar traffic parameter estimation: A semi-parametric periodogram based algorithm, " in IEEE GLOBECOM, Nov. 1995, pp. 2225--2231. |
....stochastic component Wt are combined to give the total traffic rate by mr, rat ax 5 ,Wt, 1) where Wt is a stationary stochastic process with zero mean, and unit variance, and a is a parameter sometimes referred to as the peakedhess. This type of model has been widely used see for example [15 17] and considerable evidence for the model s applicability to ISP backbone traffic is given in [12] The mean traffic rate rat is intended to capture the predictable components, namely the trend, and the weekly and daily cycles. The variation in the periodic components increases in proportion to ....
W.-C. Lau, A. Erramilli, J.L.Wang, and W. Willinger, "Self-similar traffic parameter estimation: a semiparametric periodogram-based algorithm," in GLOBECOM'95, 1995.
....EfZ t g = 0 for all t; ffl V arfZ t g = EfZ 2 t g = jtj 2H for all t, where H 2 [1=2; 1) 7 ffl Z t has continuous paths; ffl Z t is a Gaussian process, i.e. all its finite dimensional marginal distributions are Gaussian. This model seems a good choice and has popularity in the literature [13,15,21 23] because it has the advantage of simple characterization of a rather complex burst within burst traffic. There are only three parameters of this traffic model: m (input rate) a (variance coefficient) and H (Hurst parameter) The estimation of mean and variance coefficients is theoretically ....
W-C. Lau, A. Erramilli, J. L. Wang, and W. Willinger. Self-similar traffic parameter estimation: A semi-parametric periodogram-based algorithm. 1995.
....M Evaluation Table 3.2 gives the Hurst, mean (M) and variance (V 2 ) parameters used by M to model the UVAnet traces. M and V 2 were obtained using a maximum likelihood estimator (MLE) for the arrival process measured in the UVAnet traces. We used the semi parametric algorithm developed in [56] to approximate the Hurst parameter at H = 0:80. Trace Mean Packets 100 ms (M ) Variance (V 2 ) Hurst (H) 2AM Trace 23:49 96:67 0:80 3PM Trace 60:73 272:39 0:80 9PM Trace 46:16 193:43 0:80 Table 3.2: Parameters used to model UVAnet arrivals. In Figure 3.16, the distribution of packet ....
W. Lau, A. Erramilli, J. L. Wang, and W. Willinger. Self-Similar Traffic Parameter Estimation: A Semi-Parametric Periodogram-Based Algorithm. In Proc. IEEE Globecom '95, Singapore, 1995. Bibliography151
....t g = 0 for all t; ffl V arfZ t g = EfZ 2 t g = jtj 2H for all t, where H 2 [1=2; 1) ffl Z t has continuous paths; ffl Z t is a Gaussian process, i.e. all its finite dimensional marginal distributions are Gaussian. This model seems to be a good choice and has popularity in the literature [13, 15, 22, 23, 24] because it has the advantage of simple characterization of a rather complex burst within burst traffic. There are only three parameters of this traffic model: m (input rate) a (variance coefficient) and H (Hurst parameter) The estimation of mean and variance coefficients is theoretically ....
W-C. Lau, A. Erramilli, J. L. Wang, and W. Willinger. Self-similar traffic parameter estimation: A semi-parametric periodogram-based algorithm. 1995.
....Hurst s parameter (Tab.IV) Trace N. H estimate V T plot H estimate R S diagr. 1 Vphone 0.70 0.76 2 Vconf 0.68 0.70 3 Vphone 0.69 0.69 4 H.261 0.69 0.68 5 Starwars 0.78 0.82 Tab. IV The problem of a correct estimation of the Hurst parameter using recent statistical approaches is presented in [10]; the results shown in Tab. IV are only directed to confirm the self similar nature of the traces corresponding to different video formats and coding schemes. Two kinds of problems are posed by these experimental evidences: self similar queueing performances, whose evaluation is a challenging ....
W-C. Lau, A. Erramilli, J. L. Wang and W. Willinger "Self-similar traffic parameter estimation: a semi-parametric periodogram-based algorithm" IEEE Globecom '95 Singapore Nov. 1995
....listing additional techniques. More specifically, R S analysis is discussed in [18, 24, 26, 28, 130, 200, 258, 272, 273, 286, 288, 290 292, 302, 310, 394] see also [10,131] variance time analysis in [24,26,77,258,310,331,394,399] and for spectral domain methods using periodograms, see [24,26,48,84,140,149,157, 159,183,203,204,206,249,253,353,357 366,393,407, 418]. Examples of new statistical techniques in this area include [3, 7, 20,21,25,27, 52, 53, 57, 58, 80 82, 86, 98, 99, 154, 155, 189, 190, 197, 247, 258, 381, 382, 410, 415] For a practical evaluation of the different techniques see [392 394] The paper [76] provides a general overview on the ....
W.-C. Lau, A. Erramilli, J. L. Wang, and W. Willinger. Self-similar traffic parameter estimation: a semi-parametric periodogram-based algorithm. In Proceedings of the IEEE Globecom '95, pages 2225--2231, Singapore, 1995.
No context found.
W.-C. Lau, A. Erramilli, J. L. Wang, and W. Willinger, "Self-similar traffic parameter estimation: A semi-parametric periodogram based algorithm, " in IEEE GLOBECOM, Nov. 1995, pp. 2225--2231.
No context found.
W.-C. Lau, A. Erramilli, J.L.Wang, and W. Willinger, "Self-similar traffic parameter estimation: a semiparametric periodogram-based algorithm," in GLOBECOM'95, 1995.
No context found.
W.-C. Lau, A. Erramilli, J.L.Wang, and W. Willinger, "Self-similar traffic parameter estimation: a semi-parametric periodogram-based algorithm," in Global Telecommunications Conference, GLOBECOM '95, 1995.
No context found.
W.-C. Lau, A. Erramilli, J.L.Wang, and W. Willinger, "Self-similar traffic parameter estimation: a semiparametric periodogram-based algorithm," in GLOBECOM'95, 1995.
No context found.
W.-C. Lau, A. Erramilli, J.L.Wang, and W. Willinger, "Self-similar traffic parameter estimation: a semi-parametric periodogram-based algorithm," in Global Telecommunications Conference, GLOBECOM '95, 1995.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC