An adaptive method for assessing traffic characteristics in high-speed multiservice communication networks based on a fuzzy control procedure

We propose an adaptive method and a vector algorithm for assessing the main characteristics of traffic in high-speed multiservice communication networks. The adaptive algorithm for assessing the characteristics of network traffic operates online. The method is based on the conditionally nonlinear Pareto-optimal filtering principle, in which the estimation of the unknown traffic parameters is performed in two stages. At the first stage, we estimate the value of the latest forecast function of unknown traffic parameters, and at the second stage, the forecast is corrected. An analysis of the research results for the method and algorithm proposed for assessing the main characteristics of traffic in high-speed multiservice communication networks has shown their high efficiency. The average relative error of the resulting estimates does not exceed 10% of the current values of the traffic characteristics being estimated.