Experimental Machine Learning Approach for Optical Turbulence and FSO Outage Performance Modeling

A laser beam propagating in the free space suffers numerous degradation effects. In the context of free space optical communications (FSOCs), this results in reduced availability of the link. This study provides a comprehensive comparison between six machine learning (ML) regression algorithms for modeling the refractive index structure parameter (Cn2). A single neural network (ANN), a random forest (RF), a decision tree (DT), a gradient boosting regressor (GBR), a k-nearest neighbors (KNN) and a deep neural network (DNN) model are applied to estimate Cn2 from experimentally measured macroscopic meteorological parameters obtained from several devices installed at the Naval Postgraduate School (NPS) campus over a period of 11 months. The data set was divided into four quarters and the performance of each algorithm in every quarter was determined based on the R-2 and the RMSE metric. The corresponding RMSE were 0.091 for ANN, 0.064 for RF, 0.075 for GBR, 0.073 for KNN, 0.083 for DT and 0.085 for DNN. The second part of the study investigated the influence of atmospheric turbulence in the availability of a notional FSOC link, by calculating the outage probability (P-out) assuming a gamma gamma (GG) modeled turbulent channel. A threshold value of 99% availability was assumed for the link to be functional. A DNN classification algorithm was then developed to model the link status (On-Off) based on the previously mentioned meteorological parameters.