Neural network based admission controller for proximity aware mobile services

Technological advancement in mobile devices is driving the demand for valued added services. Proximity aware mobile application is one such service which user consumes services offered by service providers in the user´s environment. One key issue in providing proximity aware services in a wireless networking environment is congestion control at the server. To handle this problem, an effective connection admission control (CAC) mechanism is required. This paper investigate the feasibility of such a mechanism by comparing simulated back-propagation and learning vector quantization neural networks. The back-propagation neural networks was shown to have a higher performance.