Neural networks for logical partitioning of ATM networks

One of the most important tasks in ATM networks is to satisfy the requirements of different services. An efficient way of providing the quality of service is the logical separation of network resources. It means that on top of the physical network a number of logical (virtual) subnetworks are established in which the logical links share the capacities of physical links. There are several advantages of logical resource separation, such as the network can operate more safely, the management can be simplified and some important structures, e.g. virtual leased networks, are much easier to implement. In this paper we describe how neural networks can be used in the algorithms that optimize the logical configuration. The validity and usefulness of the methods are shown by computer simulation. The most important practical implication is that the proposed neural structures can operate very fast in a parallel implementation, thus providing the network manager with the opportunity of running realtime applications of complex reconfiguration algorithms to enhance network flexibility via accelerated network intelligence