Solving Channel Assignment Problems for Cellular Radio Networks Using Transiently Chaotic Neural Networks

The channel-assignment problem (CAP) in cellular radio networks is known to belong to the class of NPcomplete optimization problems. Many heuristic techniques including Hopfield neural networks (HNN) have been devised for solving the CAP. However, HNNs often suffer from local minima. On the other hand, a recently proposed transiently chaotic neural network (TCNN) has been successfully used in solving travelling the salesman problems (TSP). The transient chaotic neurodynamics can prevent the network from being trapped in local minima and can search for the globally optima or near-optima efficiently. In this paper we show that the TCNN can also be a useful tool for tackling the CAP.