Borrowing channel assignment strategy using computational intelligence methods

Computational intelligence methods such as neural networks (NNs) and evolutionary algorithms (EAs) have found a wide use in the field of communications. This paper examines and compares two specific heuristic techniques: the Hopfield NN and the combinatorial evolution strategy (CES) concerning their application to a borrowing channel assignment (BCA) strategy in cellular networks. At first, a cellular mobile model is constructed. By considering specific assumptions, BCA becomes a combinatorial optimization problem and may be solved by these two specific methods. Simulation results, derived for uniform and nonuniform traffic distributions, are presented and show the ability of these heuristics to handle such problems.