Learning for Cognitive Wireless Users

This paper studies the value of learning for cognitive transceivers in dynamic wireless networks. We quantify the utility improvement that can be obtained by a wideband cognitive user which learns the stationary usage pattern of the spectrum occupied by narrowband users and, based on this information adapt its transmission. Specifically, we investigate the trade-off between the learning duration and the achievable performance in stationary environments. We apply optimization and large deviations theory to analytically derive an upper bound of the minimum required learning duration, given the user's tolerable performance loss and outage probability. Furthermore, noticing that learning techniques require the information feedback of the spectrum usage pattern between the transceivers, we investigate how the cognitive user can further improve its performance by taking account of its feedback delay. The impact of inaccurate delay estimation on the achievable performance is quantified.