Throughput Maximization in Cognitive Radio Networks using Levenberg-Marquardt Algorithm

Abstract: Cognitive radio network is the promising technology of the next generation communication networks which enables the secondary users (SUs) to use the free spectrum bands which are licensed originally to the primary users (PUs) without causing interference and utilize the spectrum more efficiently. Spectrum sensing should be carried out frequently in order to transmit the data successfully through SU without causing significant interference with the PU and to achieve the maximum throughput. In this paper we propose an artificial neural network model which is known as Levenberg-Marquardt (L-M) algorithm for predicting the propagation. The simulation results show that there is a significant gain in the throughput when compared with both random and HMM methods and it explains the superiority of the algorithm. Also, it is found that the L-M algorithm is faster than the other algorithms.

Keywords: Cognitive Radio Networks, Throughput, Neural Network, Levenberg-Marquardt algorithm