A new training scheme for neural network based non-linear channel equalizers in wireless communication system using Cuckoo Search Algorithm

Abstract

Abstract Widespread use of internet technologies has resulted in a massive rise in the data rate of a wireless communication system. Eventually, to mitigate the effect of inter-symbol interference (ISI), designing an effective channel equalizer becomes a challenging task. It is well-known fact that the neural network (NN) based non-linear channel equalizers provide better performance than the adaptive filter based linear equalizers for severely non-linear and highly dispersive channels. The NN equalizers are generally trained with gradient-descent based algorithms such as back-propagation algorithm which unfortunately has limitations of slower convergence, local minima entrapment and sensitivity to initialization. To overcome these limitations, this paper proposes a new training scheme using Cuckoo Search Algorithm (CSA) for functional link artificial NN (FLANN) based channel equalizers. The proposed training scheme has a better ability to escape from local minima, higher exploitation and exploration capabilities. To select the optimum values of the parameters, the sensitivity analysis of the proposed approach is performed with respect to its key parameters. Furthermore, three non-linear channels have been simulated to demonstrate the equalization performance of the CSA based training scheme and the results have been compared with recent and well-regarded algorithms. The simulation results confirm that the proposed training scheme performs substantially better than existing metaheuristic algorithms in terms of BER and MSE performance. To show the robustness in the performance of the proposed method, the burst error scenario has been considered and results proved that the method is more successful in handling such scenarios when compared to other methods. The performance of the proposed scheme has been validated for a wide range of signal-to-noise ratio through extensive simulation studies and it is observed that the scheme outperforms the other algorithms in poor SNR conditions as well. In addition, to examine the statistical significance of the results obtained from the proposed scheme, the Wilcoxon test is performed and the test reveals that the obtained results are statistically significant.