Two-dimensional evaluation of the queueing network equilibrium based on clustering and self-organizing map

A new approach to two-dimensional evaluation of the queueing network equilibrium, based on calculations of the steady-state probability vector with use of neural modeling and clustering, is considered in this paper. The equilibrium of queueing networks is a mean for performance evaluation of real communication systems presented as Markov chains. The experimental results were obtained with use of clustering analysis and self-organizing map, and the proposed method was compared with direct techniques on the base of obtained results