XGBoost-Driven Adaptive Spreading Factor Allocation for Energy-Efficient LoRaWAN Networks

Farhan Nisar^1*Muhammad Ameen²Muhammad Touseef Irshad²Hassan Hadi^3*Naveed Ahmad³Mohamad Ladan³

• ¹Qurtuba University of Sciences and Information Technology - Peshawar Campus, Peshawar, Pakistan
• ²National University of Modern Languages, Islamabad, Pakistan
• ³Prince Sultan University, Riyadh, Saudi Arabia

The pervasive growth of the Internet of Things (IoT) necessitates efficient communication 3 technologies, among which Long Range Wide Area Network (LoRaWAN) is prominent due to its 4 long-range, low-power characteristics. A significant challenge in dense LoRaWAN deployments is 5 the efficient management of resources, particularly Spreading Factor (SF) allocation. In this paper, 6 we propose a machine learning-based approach for optimal SF allocation to enhance network 7 performance. We developed a simulation-driven framework utilizing the ns-3 simulator to generate 8 a comprehensive dataset mapping network conditions, including RSSI, SNR, device coordinates, 9 and distance to the gateway, to optimal SF assignments determined through an energy-aware 10 optimization process. An XGBoost model was trained on this dataset to predict the optimal 11 SF based on real-time network parameters. Our methodology focuses on balancing packet 12 delivery ratio and energy consumption. The performance evaluation demonstrates that the trained 13 XGBoost model effectively classifies optimal SFs, exhibiting strong diagonal dominance in the 14 confusion matrix and achieving competitive accuracy with efficient computational characteristics, 15 making it suitable for resource-constrained LoRaWAN environments.