Channel assignment in a cellular mobile communication system and an application of neural networks

In cellular mobile communication, the same channel is shared by a number of cells. Up to now, the model has been considered where the same channel is used with a sufficient separation, so that the radiowave interference is sufficiently small for any call generated in the cell. Recently, on the other hand, a model has been proposed where the same channel is assigned independently of the specified cell separation, as long as the carrier-interference ratio is above a certain value. Although the assignment algorithm has been discussed for the traditional model, no report has been made on the detailed assignment procedure for the new model. With such a situation as the background, this paper proposes an application of Hopfield's neural net as an approach to the channel assignment in the new model and derives the energy function. Several results of computer simulation are shown where the proposed neural net is applied to the mobile communication model. It is not always true that the neural net produces the optimal solution, but it is interesting that an unexpected improvement of the channel utilization is observed in the communication traffic as far as the result of computer simulation is concerned.