Channel allocation using Learning Automata in Cognitive Radio Networks

The lack of frequency, low utilization and static allocation of spectrum have been important problems in wireless network in prior methods. To solve this problem, a concept called Cognitive Radio Network was introduced to allow the use of empty spaces of licensed spectrum. The purpose of this paper was to provide an intelligent method for detecting and allocating spectrum in cognitive radio network. In this method, Hidden Marcov model is used to predict the status of free or occupied channels, then some types of learning automata are used to allocate channel to secondary users. Also, it is a way to reduce the waiting time of users who were simultaneously requesting a channel to use a mechanism for fairness in this algorithm. The simulation results indicated that the proposed method is more effective in channel allocation to secondary users thanks to using the proposed mechanisms whose results have a greater convergence speed.