STATIC AND DYNAMIC CHANNEL ASSIGNMENT USING NEURAL NETWORKS

In this paper, we examine the problem of assigning calls in a cellular mobile network to channels in the frequency domain. Such assignments must be made so that interference between calls is minimized, while de mands for channels are satisfied. A new nonlinear integer programming representation of the static channel assignment (SCA) problem is formu lated. We then propose two different neural networks for solving this problem. The first is an improved Hopfield neural network which resolv es the issues of infeasibility and poor solution quality which have pl agued the reputation of the Hopfield network The second approach is a new self-organizing neural network which is able to solve the SCA prob lem and many other practical optimization problems due to its generali zing ability. A variety of test problems are used to compare the perfo rmances of the neural techniques against more traditional heuristic ap proaches. Finally, extensions to the dynamic channel assignment proble m are considered.