用集成学习预测南非自由空间光通信的服务质量，提升系统可靠性。
Optimized Quality of Service prediction in FSO Links over South Africa using Ensemble Learning
- 融合随机森林、AdaBoost等集成模型预测光链路性能。
- 模型在四地测试中均实现超99%的决定系数，误差低于0.0073。
- 适合通信网络优化与气象影响评估的研究人员参考。
光纤通信系统因诸多优势，预计将在应用上呈指数增长。尽管其具备远距离传输、低功耗、高带宽等优点，但自由空间光通信仍受雾、降水、暴风雪、烟尘及大气颗粒物等恶劣天气严重影响，导致服务质量（QoS）下降。本文旨在通过集成学习模型——随机森林、自适应增强回归、堆叠回归、梯度提升回归和多层神经网络——优化南非四个地点（波洛克瓦内、金伯利、布隆方丹、乔治）2010至2019年气象数据（包括能见度、风速、海拔）的传输性能预测。基于数据估算出数据速率、接收功率、雾致衰减、误码率及功率代价。各站点模型的均方根误差（RMSE）分别为0.0073、0.0065、0.0060、0.0032，决定系数（R²）分别为0.9951、0.9998、0.9941、0.9906。结果表明，集成学习显著提升了信噪比与接收端服务质量，有效保障服务等级协议（SLA）。
原文摘要 · Abstract (English)
Fibre optic communication system is expected to increase exponentially in terms of application due to the numerous advantages over copper wires. The optical network evolution presents several advantages such as over long-distance, low-power requirement, higher carrying capacity and high bandwidth among others Such network bandwidth surpasses methods of transmission that include copper cables and microwaves. Despite these benefits, free-space optical communications are severely impacted by harsh weather situations like mist, precipitation, blizzard, fume, soil, and drizzle debris in the atmosphere, all of which have an impact on the Quality of Service (QoS) rendered by the systems. The primary goal of this article is to optimize the QoS using the ensemble learning models Random Forest, ADaBoost Regression, Stacking Regression, Gradient Boost Regression, and Multilayer Neural Network. To accomplish the stated goal, meteorological data, visibility, wind speed, and altitude were obtained from the South Africa Weather Services archive during a ten-year period (2010 to 2019) at four different locations: Polokwane, Kimberley, Bloemfontein, and George. We estimated the data rate, power received, fog-induced attenuation, bit error rate and power penalty using the collected and processed data. The RMSE and R-squared values of the model across all the study locations, Polokwane, Kimberley, Bloemfontein, and George, are 0.0073 and 0.9951, 0.0065 and 0.9998, 0.0060 and 0.9941, and 0.0032 and 0.9906, respectively. The result showed that using ensemble learning techniques in transmission modeling can significantly enhance service quality and meet customer service level agreements and ensemble method was successful in efficiently optimizing the signal to noise ratio, which in turn enhanced the QoS at the point of reception.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。