An accurate estimation algorithm for channel parameters in Opportunistic Spectrum model

In Opportunistic Spectrum Access model (OSA) it is essential to have some knowledge about the primary user's activity in order to increase the QoS for the secondary users. In this paper we build an algorithm for maximum likelihood (ML) estimator to predict and estimate the channel statistics parameters upon the primary user activity. The estimator is built for a Markovian channel model in which the channel is sensed in a periodic manner. The estimated channel utilization and occupancy rate will be used to determine the suitable number of samples that provide the required degree of confidence. To evaluate our proposed algorithm we compare it with three other algorithms. Our proposed algorithm shows a great improvement over the other three tested algorithms.