Machine learning based performance estimation of terrestrial Ro-FSO Link

Abstract

In this work, a radio over free-space optical communication (Ro-FSO) link has been examined considering quadrature amplitude modulation (64-QAM) based orthogonal frequency division multiplexing (OFDM) technique for a turbulence channel. The performance of the system has been investigated considering log normal and gamma-gamma atmospheric scintillation models under clear air, rain and fog weather conditions. Artificial neural network (ANN), k-nearest neighbour (KNN), and decision tree (DT) machine learning (ML) techniques have been applied for estimation of quality of received signal in terms of bit error rate BER. ANN model exhibits the highest value of R-squared (R2) of 0.9967 and lowest value of root mean square error (RMSE) of 0.0134 as compared to other ML techniques resulting in the best fit model.