A Survey on Performance Optimization of OFDM based System by using Neural Network

In order to oppose the fading problems in an OFDM communication systems, adaptive modulation techniques have been used for the improved performance. MIMO (Multiple Input Multiple Output) and OFDM (Orthogonal frequency division multiplexing) forms a combination. Both gives a good possibility of being the next-generation (4th generation) of mobile wireless systems. The technology however imposes a challenge that is the increased complexity of channel equalization. Wireless channels are multipath fading channels, It can cause deformation in the signal. Channel impulse response (CIR) is used to remove the effect of deformation in the signal. This CIR is used in receiver provided by a separate channel estimator. The artificial neural network is used with the MIMO-OFDM system for channel estimation. This system is proposed with the back propagation algorithm with the feed forward network. The original sequence of data will be trained by using ANN and observations will be made. ANN is trained for different values of Eb/No and used with the receiver circuit. The evaluated results are done by mathematical analysis (FFT and IFFT) in MATLAB