A smart proactive routing protocol in cognitive radio networks

Abstract

In this paper, we introduce a smart proactive routing protocol based on the Q-learning algorithm to find the most stable routes which imposes a minimum interference on the primary users. Unlike traditional proactive routing protocols, in our proposed method control packets are not broadcast whenever the network topology changes. Indeed, we apply a generalised version of Q-learning to predict the model of the routes stability. This model is used to prevent the flood of state information that is ineffective for routing decisions. The frequency of changes in the model is much less than that in the network topology. In the new approach, secondary users broadcast control packets following any changes in the model which reduces the routing overhead. Evaluation of the simulation results show that our routing protocol outperforms existing schemes in terms of throughput and the interference imposed on the primary users' spectrum as well as routing overhead.