Caracterización de Usuarios Primarios para la Implementación de un Modelo Predictor para la Toma de Decisiones en Redes Inalámbricas de Radio Cognitiva

Abstract

The current shortage and inefficient use of the frequency spectrum leads researchers to seek technological solutions to this problem, it is proposed therefore Cognitive Radio (CR), which allows more efficient management of existing resources so they can be exploited opportunistic way by cognitive users. This paper presents the design and use of a Bayesian network for characterization of primary user (PU) on wireless networks (GSM 824.9 MHz) in order to generate a predictor of PU activity, which could serve as a central entity a cognitive network in making decisions spectral. From the results, it is concluded that artificial intelligence technique based on Bayesian networks allows to model and predict the behavior of the main user above 80% for future short periods of time.