Parametric controlled transient chaotic neural network for the channel assignment problem

The problem of assigning calls in a cellular mobile network has become increasingly important because of limited usable range of the frequency spectrum. In this paper a new channel assignment algorithm using transiently chaotic neural network (TCNN) is proposed. A significant property of the TCNN model is that the chaotic neurodynamics are temporarily generated for searching and self-organizing in order to escape the local minima. Therefore, the neural network gradually approaches, through the transient chaos, a dynamical structure similar to such conventional models as the Hopfield neural network which converges to a stable equilibrium point.