Advanced Smart Channel Estimation Scheme for MIMO OSTBC Systems Based Wireless Communication

Abstract

Labeling diversity is used in an orthogonal space-time block coded (OSTBC) scheme to improve wireless connection reliability without reducing spectral efficiency. Compared to the conventional STBC system, it achieves improved link dependability. The purpose of this work is to provide a blind wireless channel estimator that is bandwidth-efficient for the OSTBC system. Methods for channel estimation, such as least-squares (LS) & minimum mean square error (MMSE) methods typically use the channel bandwidth inefficiently. The receiver noise variance and prior broadcast pilot symbols knowledge & statistics information of channel are required for LS & MMSE channel estimating algorithms to accurately estimate the channel. An neural network machine learning (NNML) channel estimation with transmitter end power-share is suggested in order to make blind channel estimator simpler for the OSBC-based MIMO transmission & to lessen amount of bandwidth requirement for estimation of channel. By using mathematical modeling equivalent to noise power, we determine the ideal transmit fraction of power that reduces bandwidth consumption due to channel estimate. It is demonstrated that the blind NN-ML nased channel estimation with transmitter power-share uses 20% of the bandwidth of the MMSE & LS wireless channel estimators in order to achieve the OSTBC system's low bit error rate (BER) in the case of M-PSK modulation.