Tuning the parameters of a free-space optical channel using machine learning

Abstract

The present work uses artificial intelligence (AI) methodology to simulate the data transmission process through free-space optical (FSO) technology. With machine learning procedures, the data are obtained by multiparametric simulation using Optisystem software. For the first simulation set, the input parameters were distance, attenuation, gain in the input signal amplifier, and gain in the output signal amplifier. For the second set, the effects of beam divergence and the receiver diameter were also evaluated. Additional sets were added to increase the data and characterize the underfitting and overfitting processes. With the data generated, artificial intelligence models were trained using decision tree regression (DTR), random forest regression (RFR), gradient boosting regressor (GBR), histogram gradient boosting regression (HGBR), and AdaBoost + deciston tree regression (ADDTR). The results showed that for the first scenario the models (DTR) and (RFR) showed an excellent estimate for the maximum quality factor (MaxQFactor), with a value of the coefficient of determination R2 above 95.00%, and, for the second scenario, the algorithms (DTR) and (RFR) also have shown excellent results, with R2 above 94.00%. The results obtained from the artificial intelligence procedures were compared graphically with the values obtained by multiparametric numerical simulation, confirming the effectiveness of the methodology used to predict the output values of the FSO channel.