The Bit Error Performance of Diffuse Indoor Optical Wireless Channel PPM System Employing Artificial Neural Networks for Channel Equalization

The bit error rate (BER) performance of a pulse position modulation (PPM) scheme for non line-of-sight (LOS) indoor optical links employing channel equalization based on the artificial neural network (ANN) is reported in the paper. Channel equalization is achieved by training a multilayer perceptrons (MLP) ANN. A comparative study of the unequalized „soft‟ decision decoding and the „hard‟ decision decoding along with the neural equalized „soft‟ decision decoding is presented for different bit resolutions for optical channels with different delay spread. We show that the unequalized „hard‟ decision decoding performs the worst for all values of normalized delayed spread becoming impractical beyond normalized delayed spread of 0.6. However, „soft‟ decision decoding with/without equalization displays relatively improved performance for all values of the delay spread. The study shows that for a highly diffuse channel the signal-to-noise ratio (SNR) requirement to achieve a BER of 10 -5 for the ANN based equalizer is ~ 10 dB lower compared with the unequalized „soft‟ decoding for 16PPM at a data rate of 155 Mbps. Our results indicate that for all range of delay spread, neural network equalization is an effective tool of mitigating the ISI.