Cross-Entropy Optimized Cognitive Radio Policies

Abstract : In this paper we consider cognitive processes and their impact on the performance of cognitive radio networks (CRN). We model the cognition cycle, during which cognitive radio (CR) sequentially senses and estimates the environment state, makes decisions in order to optimize certain objectives and then acts. Model-based analysis of CRN is used to solve control and decision making tasks, which actually gives the radio its “cognitive” ability. Particularly, we design an efficient strategy for accessing the vacant spectrum bands and managing the transmission-sampling trade-off. In order to cope with the high complexity of this problem the policy search uses the stochastic optimization method of cross-entropy. The developed model represents CRN ability to intelligently react to the network’s state changes and gives a good understanding of the cross-entropy optimized policies.