Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations

Accurate path loss prediction is essential for optimizing Long-Range Wide-Area Network (LoRaWAN) performance. Previous studies have employed various Machine Learning (ML) models for path loss prediction. However, environmental factors such as temperature, humidity, barometric pressure, and particula...

Full description

Saved in:
Bibliographic Details
Main Authors: Maram A. Alkhayyal, Almetwally M. Mostafa
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/4101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427454481924096
author Maram A. Alkhayyal
Almetwally M. Mostafa
author_facet Maram A. Alkhayyal
Almetwally M. Mostafa
author_sort Maram A. Alkhayyal
collection DOAJ
description Accurate path loss prediction is essential for optimizing Long-Range Wide-Area Network (LoRaWAN) performance. Previous studies have employed various Machine Learning (ML) models for path loss prediction. However, environmental factors such as temperature, humidity, barometric pressure, and particulate matter have been largely neglected. This study bridges this gap by evaluating the performance of five boosting ML models—AdaBoost, XGBoost, LightGBM, GentleBoost, and LogitBoost—under dynamic environmental conditions. The models were compared with theoretical models (Log-Distance and Okumura-Hata) and existing studies that employed the same dataset based on metrics such as RMSE, MAE, and R<sup>2</sup>. Furthermore, a detailed performance vs. complexity analysis was conducted using metrics such as training time, inference latency, model size, and energy consumption. Notably, barometric pressure emerged as the most influential environmental factor affecting path loss across all models. Bayesian Optimization was applied to fine-tune hyperparameters to improve model accuracy. Results showed that LightGBM outperformed other models with the lowest RMSE of 0.5166 and the highest R<sup>2</sup> of 0.7151. LightGBM also offered the best trade-off between accuracy and computational efficiency. The findings show that boosting algorithms, particularly LightGBM, are highly effective for path loss prediction in LoRaWANs.
format Article
id doaj-art-d6191102aa384593bb90154917e50abc
institution Kabale University
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-d6191102aa384593bb90154917e50abc2025-08-20T03:29:02ZengMDPI AGSensors1424-82202025-06-012513410110.3390/s25134101Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental VariationsMaram A. Alkhayyal0Almetwally M. Mostafa1Department of Information Systems, College of Computers and Information Sciences, King Saud University, Riyadh 11451, Saudi ArabiaDepartment of Information Systems, College of Computers and Information Sciences, King Saud University, Riyadh 11451, Saudi ArabiaAccurate path loss prediction is essential for optimizing Long-Range Wide-Area Network (LoRaWAN) performance. Previous studies have employed various Machine Learning (ML) models for path loss prediction. However, environmental factors such as temperature, humidity, barometric pressure, and particulate matter have been largely neglected. This study bridges this gap by evaluating the performance of five boosting ML models—AdaBoost, XGBoost, LightGBM, GentleBoost, and LogitBoost—under dynamic environmental conditions. The models were compared with theoretical models (Log-Distance and Okumura-Hata) and existing studies that employed the same dataset based on metrics such as RMSE, MAE, and R<sup>2</sup>. Furthermore, a detailed performance vs. complexity analysis was conducted using metrics such as training time, inference latency, model size, and energy consumption. Notably, barometric pressure emerged as the most influential environmental factor affecting path loss across all models. Bayesian Optimization was applied to fine-tune hyperparameters to improve model accuracy. Results showed that LightGBM outperformed other models with the lowest RMSE of 0.5166 and the highest R<sup>2</sup> of 0.7151. LightGBM also offered the best trade-off between accuracy and computational efficiency. The findings show that boosting algorithms, particularly LightGBM, are highly effective for path loss prediction in LoRaWANs.https://www.mdpi.com/1424-8220/25/13/4101boosting algorithmsenvironmental variationsLoRaWANpath loss
spellingShingle Maram A. Alkhayyal
Almetwally M. Mostafa
Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations
Sensors
boosting algorithms
environmental variations
LoRaWAN
path loss
title Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations
title_full Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations
title_fullStr Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations
title_full_unstemmed Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations
title_short Enhancing LoRaWAN Performance Using Boosting Machine Learning Algorithms Under Environmental Variations
title_sort enhancing lorawan performance using boosting machine learning algorithms under environmental variations
topic boosting algorithms
environmental variations
LoRaWAN
path loss
url https://www.mdpi.com/1424-8220/25/13/4101
work_keys_str_mv AT maramaalkhayyal enhancinglorawanperformanceusingboostingmachinelearningalgorithmsunderenvironmentalvariations
AT almetwallymmostafa enhancinglorawanperformanceusingboostingmachinelearningalgorithmsunderenvironmentalvariations