New Approach to Converged Networks

This paper describes a new approach to converged communication and computer networks. It was designed a new architecture of nodal active network element that is powerful enough and supports priority processing of different types of connection. It is exactly the missing support of priority processing that constitutes the greatest drawback of the majority of present-day active network elements. The proposed new architecture is based on the technology of artificial neural networks. Neural networks are used to optimize switching input requirements to outputs. This paper also describes design and computer simulations of a new architecture network element, based on artificial neural network technology with the support of priority processing for different connection types. As an example of a network element was selected switching area. This network element with optimized switching area is able to transfer large data quantity with minimum delay. Architecture of network element, that contains artificial neural network for optimized priority switching is described in this paper. It describes implementation of neural network in control process for data units switching. The programming language MATLAB 7.0 was used for software simulation. Network elements with new architecture, which uses a neural network, as well as intimated simulation, are suitable for working for example in personal wireless network communication systems.