Kalman filter based prediction of broadband traffic burstiness

In this paper, we propose tracking and control algorithms for controlling network congestion with bursty traffic modeled by multifractal cascade processes. The multifractal multiplicative cascades are characterized by the Holder exponents. The value of the Holder exponent at an interval indicates the burstiness in the traffic at that point. This value has to be estimated and used for the estimation of the congestion and predictive control of the traffic policing in networks. The estimation of the local Holder exponent can be done by employing the wavelet transforms and a Kalman filter based predictor to predict the burstiness of the traffic.