- Conference Article
- 10.1109/icidca66325.2025.11280504
Big Data Learning for Forecasting and Reducing Energy Consumption in Mobile Communication Systems
- Oct 06, 2025
- Anusha Peyyala + 5 more +5
The exponential growth of mobile data services has created unprecedented challenges in terms of energy efficiency and sustainable network design. This study applies big data learning and predictive analytics to investigate the influence of traffic load, user density, and signal strength on energy consumption in cellular systems. Using historical datasets and Taguchi-based experimental design, the analysis identifies critical parameters and their contribution rates through signal-to-noise ratio and ANOVA methods. The results reveal that traffic load exerts the highest impact on energy consumption (90.5%), followed by active users (3.8%), with signal strength contributing minimally (0.75%). Predictive modeling further highlights the optimal configuration for minimizing energy usage: a traffic load of 900 Mbps, 4000 users, and signal strength of -85 dBm. By integrating big data-driven insights with predictive optimization strategies, this research provides a scalable framework for designing energy-efficient and sustainable mobile networks to meet rising global demand for data-intensive services.
Read more