Bit Error Rate Improvement by using Active Constellation Extension and Neural Network in OFDM System

The demand for multimedia data services has grown up rapidly. One of the most promising multi-carrier system, Orthogonal Frequency Division Multiplexing (OFDM) form basis for all 4G wireless communication systems due to its large capacity to allow the number of subcarriers, high data rate and ubiquitous coverage with high mobility. OFDM is drastically affected by peak-to-average-power ratio (PAPR). In this paper, an effort has been made to analyze how well an OFDM system can perform when a signal, of various PAPR reduction techniques, is transmitted over Additive White Gaussian Noise (AWGN) channel using 16-QAM modulation technique. The performances of PAPR reduction schemes have been evaluated in terms of the bit error rate (BER). Simulation results reveal that, the OFDM system with Active constellation extension (ACE) and Neural Network (NN) schemes improve the BER performance and robust to high PAPR. Index Terms – OFDM; PAPR; ACE; NN; BER.