Fast and robust Hurst parameter estimation of traffic data traces tops the bill of nowadays problems of the field of traffic engineering. Almost every existent approach fits up the goal of as far as possible precise H parameter estimation; however this option is not as necessary as approximate estimation of boundaries of H parameter if traffic demonstrates long range dependence. Often this is the satisfactory condition for defining adequate traffic engineering operations. In this paper we verify a possibility of heuristic H parameter estimation algorithm which is based on wavelet transform of fractional Brownian motion synthesized data traces, and forthcoming operating with neural network learning capabilities. In this paper algorithm is described. Experimental data are depicted and future research subjects are pointed.