AI-based optimization of EM radiation estimates from GSM base stations using traffic data

Authors: Lal R, Singh RK, Nishad DK, et al.

Year: 2024

Category: Artificial Intelligence, Electromagnetic Safety, Telecommunications Engineering

Journal: Discov Appl Sci

DOI: 10.1007/s42452-024-06395-y

URL: https://link.springer.com/article/10.1007/s42452-024-06395-y

Abstract

Overview

The rapid growth of mobile networks has raised concerns about the health impacts of electromagnetic (EM) radiation from base stations. Traditionally, EM radiation assessments often neglect actual traffic load and instead rely solely on maximum power output values.

Methodology

  • Introduces the application of Artificial Intelligence (AI) and Machine Learning (ML) on real-world network traffic data to optimize EM radiation estimates for GSM base stations.
  • Collects EM radiation measurements alongside relevant traffic data from selected GSM sites based on their location and configuration.
  • Trains predictive models (linear regression, random forests, neural networks) using traffic patterns to forecast EM radiation levels.
  • Applies unsupervised learning to cluster base stations by their radiation output profiles.

Findings

  • The AI/ML approach delivers more accurate EM radiation predictions compared to standard power-based estimates and demonstrates strong applicability across various types of base stations.
  • Daily site-specific factors significantly affect EM radiation patterns, as revealed by clustering analysis.
  • The proposed optimization framework accounts for regulatory compliance and measurement practicality to reduce estimation errors.

Conclusion

The findings enable telecom operators and regulators to efficiently monitor and analyze EM radiation using traffic data and AI, supporting improved public health and safety measures. The study suggests that future work should extend to 5G, small cells, and smart city integrations to further enhance data-driven safety solutions.

Importantly, the study underscores the connection between EM radiation levels and potential health risks, reinforcing the need for ongoing monitoring and regulation as mobile networks expand.

EM radiation GSM base stations AI machine learning traffic data public safety health risk
← Back to Stats