Management and control of the access network segment of future mobile communications systems by means of neural networks

An important issue in future cellular communication systems is the design of the interconnecting network of their access segment and the best distribution of the systems´ capacity in order to provide the predefined quality of service (QoS). In this context the following topic arises; to find the minimum-cost configuration of cell site switches (CSSs) given the base transceiver station (BTS) layout, that satisfy a set of performance constraints (that derive from the traffic and mobility patterns in the system). An extended version of the problem may also comprise the deployment of the above configuration in different load configurations. The problem is formally defined, optimally formulated, and solved by using a neural network technique. Finally, results are provided and subsequent conclusions are drawn