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

Citation Author(s):
Antonios
Lionis
University of Peloponnese, Department of Informatics and Telecommunications
Kostas
Peppas
University of Peloponnese, Department of Informatics and Telecommunications
Andreas
Tsigkopoulos
Division of Combat Systems, Naval Operations, Sea Sciences, Navigation, Electronics & Telecommunications Sector of the Hellenic Naval Academy
Antonios
Sklavounos
Division of Combat Systems, Naval Operations, Sea Sciences, Navigation, Electronics & Telecommunications Sector of the Hellenic Naval Academy
Argyris
Stasinakis
Section of Electronic Physics and Systems, Department of Physics, National and Kapodistrian University of Athens
Hector
Nistazakis
Section of Electronic Physics and Systems, Department of Physics, National and Kapodistrian University of Athens
Keith
Kohn
Physics Department of the Naval Postgraduate School, California, USA
Konstantinos
Aidinis
Department of Electrical and Computer Engineering and Centre of Medical, Ajman University, Ajman, United Arab Emirates
Submitted by:
Kostas Peppas
Last updated:
Fri, 09/23/2022 - 17:24
DOI:
10.21227/8bqw-gy72
License:
0
0 ratings - Please login to submit your rating.

Abstract 

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 link’s availability. This study provides a comprehensive comparison between six machine learning (ML) regression algorithms for modeling the refractive index structure parameter Cn^2. 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 Cn^2from 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 R2 and the RMSE metric. 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 (Pout) 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

Instructions: 

Please rename files data1.zip, data2.zip, data13.zip, data4.zip, data5.zip, data6.zip, data7.zip, data8.zip as

data.zip.001, data.zip.002, data.zip.003, data.zip.004, data.zip.005, data.zip.006, data.zip.007 and data.zip.008, respectively and extract them.

You will find four excel files, namely Sklavounos and Cohn, Autumn. 2022.xlsx  Sklavounos and Cohn, Spring 2022.xlsx, Sklavounos and Cohn, Summer. 2022.xlsx and Sklavounos and Cohn, Winter. 2022.xlsx