Reduction of Power Fluctuation in ECMA-368 Ultra Wideband Communication Systems Using Multilayer Perceptron Neural Networks

ECMA-368 Ultra Wideband (UWB) wireless communication Standard adopts Multiband Orthogonal Frequency Division Multiplexing (MB-OFDM) technology to transmit information with high data rate (480 Mbits/s). However, the high Peak to Average Power Ratio of MB-OFDM UWB signals, limits the power efficiency of the high power amplifier due to nonlinear distortion. In order to avoid this drawback, an efficient scheme based on multilayer perceptron, artificial neural networks is proposed. The neural network is adjusted by using active constellation extension technique which provides satisfactory results. This proposed solution gives good performance compared to previously available methods with much lower complexity, without iterations, good bit error rate and no increase in transmitted signal power and bandwidth.