A decision tree cognitive routing scheme for cognitive radio mesh networks

Routing in a cognitive radio network operating in a dynamic environment is a complex decision problem. Diversity in the number of available spectrum bands and their stability, in addition to the secondary users' heterogeneities, affect the consequence of the routing decision. We use a decision theory framework to model the problem of routing under uncertainties involved in a cognitive radio network. A utility function is designed to capture the effect of spectrum measurement, fluctuation of bandwidth availability, and path quality. A node cognitively decides its best candidate among its neighbors by utilizing a decision tree. Each branch of the tree is quantified by the utility function and a posterior probability distribution that predicts the suitability of available neighbors. In decision tree cognitive routing (DTCR), nodes learn their operational environment and adapt their decision-making accordingly. We compared our scheme with the optimal performance in a highly dynamic environment and local coordination-based routing and spectrum assignment protocol [1]. Our results show that the DTCR tends to perform near optimum. It easily adapts to environmental dynamics. Copyright (c) 2013 John Wiley & Sons, Ltd.