Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Effective Feature Selection for Predicting Spreading Factor with ML in Large LoRaWAN-based Mobile IoT Networks

Aman Prakash, Nikumani Choudhury, Anakhi Hazarika, Alekhya Gorrela

TL;DR

This work tackles the challenge of predicting LoRaWAN spreading factor (SF) using machine learning to optimize SF allocation in large mobile IoT networks. It exhaustively evaluates 31 feature combinations derived from five LoRaWAN features across four classifiers (k-NN, Decision Tree, Random Forest, Multinomial Logistic Regression) on a large public dataset, identifying RSSI and SNR as the most informative pair. The results show that the RSSI+SNR combination achieves strong predictive performance, enabling reductions in data-collection costs and training time while extending device battery life. The findings offer practical guidance for efficient SF allocation in LoRaWAN systems and point to avenues for future improvements with deeper models and broader feature sets.

Abstract

LoRaWAN is a low-power long-range protocol that enables reliable and robust communication. This paper addresses the challenge of predicting the spreading factor (SF) in LoRaWAN networks using machine learning (ML) techniques. Optimal SF allocation is crucial for optimizing data transmission in IoT-enabled mobile devices, yet it remains a challenging task due to the fluctuation in environment and network conditions. We evaluated ML model performance across a large publicly available dataset to explore the best feature across key LoRaWAN features such as RSSI, SNR, frequency, distance between end devices and gateways, and antenna height of the end device, further, we also experimented with 31 different combinations possible for 5 features. We trained and evaluated the model using k-nearest neighbors (k-NN), Decision Tree Classifier (DTC), Random Forest (RF), and Multinomial Logistic Regression (MLR) algorithms. The combination of RSSI and SNR was identified as the best feature set. The finding of this paper provides valuable information for reducing the overall cost of dataset collection for ML model training and extending the battery life of LoRaWAN devices. This work contributes to a more reliable LoRaWAN system by understanding the importance of specific feature sets for optimized SF allocation.

Effective Feature Selection for Predicting Spreading Factor with ML in Large LoRaWAN-based Mobile IoT Networks

TL;DR

This work tackles the challenge of predicting LoRaWAN spreading factor (SF) using machine learning to optimize SF allocation in large mobile IoT networks. It exhaustively evaluates 31 feature combinations derived from five LoRaWAN features across four classifiers (k-NN, Decision Tree, Random Forest, Multinomial Logistic Regression) on a large public dataset, identifying RSSI and SNR as the most informative pair. The results show that the RSSI+SNR combination achieves strong predictive performance, enabling reductions in data-collection costs and training time while extending device battery life. The findings offer practical guidance for efficient SF allocation in LoRaWAN systems and point to avenues for future improvements with deeper models and broader feature sets.

Abstract

LoRaWAN is a low-power long-range protocol that enables reliable and robust communication. This paper addresses the challenge of predicting the spreading factor (SF) in LoRaWAN networks using machine learning (ML) techniques. Optimal SF allocation is crucial for optimizing data transmission in IoT-enabled mobile devices, yet it remains a challenging task due to the fluctuation in environment and network conditions. We evaluated ML model performance across a large publicly available dataset to explore the best feature across key LoRaWAN features such as RSSI, SNR, frequency, distance between end devices and gateways, and antenna height of the end device, further, we also experimented with 31 different combinations possible for 5 features. We trained and evaluated the model using k-nearest neighbors (k-NN), Decision Tree Classifier (DTC), Random Forest (RF), and Multinomial Logistic Regression (MLR) algorithms. The combination of RSSI and SNR was identified as the best feature set. The finding of this paper provides valuable information for reducing the overall cost of dataset collection for ML model training and extending the battery life of LoRaWAN devices. This work contributes to a more reliable LoRaWAN system by understanding the importance of specific feature sets for optimized SF allocation.

Paper Structure

This paper contains 20 sections, 1 equation, 3 figures, 7 tables.

Table of Contents

  1. Introduction
  2. LoRaWAN
  3. Spreading Factor (SF)
  4. Related Work
  5. Methodology
  6. LoRaWAN Dataset
  7. Dataset Description
  8. Data Collection Setup
  9. Feature Selection and Combination Approach
  10. Picking Features
  11. Feature Combination Approach
  12. Machine Learning Models
  13. Evaluation Metrics
  14. Computing Specifications
  15. Experimental Results and Analysis
  16. ...and 5 more sections

Figures (3)

  • Figure 1: LoRaWAN network architecture
  • Figure 2: Visualization of metrics: Average Accuracy % and F1 %
  • Figure 3: Feature Ranking Based on Pearson Correlation