Ivanov

Results of calculations of incoming and outgoing traffic’s dynamic characteristics were presented in this paper along with the distribution of hardware capacities by the example of the university’s corporate network server. Lyapunov and Hurst exponents, which characterize chaotic and fractal properties of the processes, were evaluated for network traffic. Traffic’s phase diagrams were investigated and, for the first time, appearance of attractors was revealed; these attractors allow one to conduct a more detailed analysis of the impact of load on the network’s traffic capacity. A self-similarity was found for all the processes; this fact confirms the possibility of using fractal models for working with data, including solving urgent problems of predicting behavior of the time series.