Adaptive modulation in an OFDM communications system with artificial neural networks

In order to combat fading in an OFDM communications system, adaptive modulation techniques have been employed which can improve the performance. We propose that an artificial neural network (ANN) can be inserted in an OFDM system that would provide the information necessary to perform an adaptive modulation of the subcarriers. The performance of the system is evaluated in terms of symbol error probability. The results of our simulations allow us to validate our hypothesis.