Sklavounos and Cohn data for free space optics measurements 2022

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^2 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 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.

在自由空间中传播的激光束会受到多种劣化效应的影响。在自由空间光通信（FSOC）场景下，该效应会导致链路可用性降低。本研究针对用于建模折射率结构常数Cₙ²的六种机器学习（ML）回归算法开展了全面对比分析。研究采用人工神经网络（ANN）、随机森林（RF）、决策树（DT）、梯度提升回归器（GBR）、k近邻（KNN）以及深度神经网络（DNN）六种模型，基于美国海军研究生院（NPS）校园内11个月间通过多台设备实测得到的宏观气象参数，对Cₙ²进行估算。本次数据集被划分为四个季度，基于决定系数R²与均方根误差（RMSE）两项指标，评估了每种算法在各季度的表现。本研究的第二部分通过假设信道为伽马-伽马（GG）建模的湍流信道并计算中断概率（Pout），探究了大气湍流对概念性自由空间光通信链路可用性的影响。研究设定链路正常工作的可用性阈值为99%。随后，基于前述气象参数，开发了一款DNN分类算法以对链路状态（通-断）进行建模。