Optimization of Energy Consumption in LoRaWAN Networks Using Machine Learning Methods

Батырбек Жоламанов, Sayat Orynbassar, Kymbat Kopbay, Madiyar Nurgaliyev, Gulnaz Abzhanova

2026

Closed access Metadata (CSL-JSON)
DOI 10.52209/1609-1825_2026_3_448
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Optimal trade-off between energy efficiency and data transmission reliability serves as a solid foundation for improving the stability and performance of LoRaWAN networks in diverse Internet of Things (IoT) applications. This study investigates the modeling and optimization of energy consumption (EC) in wireless sensor networks (WSNs) using LoRa technology. Key transmission parameters – spreading factor (SF), bandwidth (BW), code rate (CR), and transmission power (TP) – along with the node-to-gateway distance were analyzed for their impact on network performance and energy efficiency. The simulations were conducted using the FLoRa simulation framework integrated with OMNeT++, and the XGBoost machine learning model was used to predict the optimal configurations. The results show that the proposed optimization approach achieves 28% reduction in energy consumption and 24% improvement in packet delivery ratio (PDR) compared to traditional adaptive data rate (ADR) algorithm.