Cellular neural network approach to a class of communication problems

In this paper me discuss the design of a cellular neural network (CNN) to s olve a class of optimization problems of importance for communication netwo rks. The CNN optimization capabilities are exploited to implement an effici ent cell scheduling algorithm in a fast packet switching fabric. The neural -based switching fabric maximizes the cell throughput and, at the same time , it is able to meet a variety of quality of service (QoS) requirements by optimizing a suitable function of the switching delay and priority of the c ells. We also show that the CNN approach has advantages with respect to tha t based on Hopfield neural networks (HNN's) to solve the considered class o f optimization problems. In particular, we exploit existing techniques to d esign CNN's with a prescribed set of stable binary equilibrium points as a basic tool to suppress spurious responses and, hence to optimize the neural switching fabric performance.