PAPR Reduction Technique for Mobile Communication Systems Using Neural Networks

This work proposes a new solution to reduce the PAPR in OFDM systems using NN. The NN leverages a training dataset generated by the MCSA, which fine-tunes the NN for attaining a similar PAPR reduction of the MCSA. Compared to traditional techniques such as the PTS, the proposed solution offers superior performance by achieving a PAPR reduction of up to 4 dB. Nevertheless, a significant advantage is that the trained NN presents a lower computational complexity compared to the MCSA, without compromising its PAPR reduction capabilities