Neural networks for location management in mobile cellular communication networks

In a mobile communication network, the movements of users, are, in general, preplanned, and highly dependent on individual characteristics. A neural network, with its learning and generalization ability, may act as a suitable tool to predict the location of a terminal, provided it is trained appropriately by the personal mobility profile of the individual user. The paper first studies the performance of a multilayer perceptron (MLP) network for location prediction. A new paging technique is proposed based on this predicted location. Next, a hybrid network composed of a self-organizing feature map (SOFM) network followed by a number of MLP networks is employed for prediction. Simulation studies show that the latter performs better for location management. This approach is free from all unrealistic assumptions about the movement of users. It is applicable to any arbitrary cell architecture. It attempts to reduce the total location management cost and paging delay.