Analysis and Compensation for HPA Nonlinearity with Neural Network in MIMO-STBC Systems

In order to provide high data rate over wireless channels and improve the system capacity, Multiple-Input Multiple-Output (MIMO) wireless communication systems exploit spatial diversity by using multiple transmit and receive antennas. Moreover, MIMO systems are equipped with High Power Amplifiers (HPA). However, HPA causes nonlinear distortions and affect the receiver’s performance. Since a few decades, Neural Networks (NN) have shown excellent performance in solving complex problems like classification, recognition and approximation. In this paper, we present a receiver technique based on NN schemes for the compensation of HPA non linearization in MIMO Space-Time Block Coding (STBC) systems. Specifically, we assess the impact of HPA nonlinearity and NN on the average symbol error rate (SER) and the error vector magnitude (EVM) of MIMO-STBC in uncorrelated Rayleigh fading channels. Computer simulation results confirm the accuracy and validity of our proposed analytical approach.