On the estimation of channel state transitions for cognitive radio systems

Coexistence by means of shared access is a cognitive radio application. The secondary user models the slotted primary users channel access as a Markov process. The model parameters, i.e, the state transition probabilities (α,β) help secondary user to determine the channel occupancy, thereby enables secondary user to rank the primary user channels. These parameters are unknown and need to be estimated by secondary users for each channel. To do so, the secondary users have to sense all the primary user channels in every time slot, which is unrealistic for a large and sparsely allocated primary user spectrum. With no other choice left, the secondary user has to sense a channel at random time intervals and estimate the parametric information for all the channels using the observed slots.