MARATTO

article

Boosting Cell Site Stability: LTE Congestion Prediction with Machine Learning and Deep Learning

Abstract

This paper presents a novel approach to predicting LTE congestion and improving network stability by comparing the performance of machine learning (Random Forest, XGBoost) and deep learning (LSTM, GRU) models. Using a real-world dataset from Orange Egypt, the study focuses on predicting Physical Resource Block (PRB) utilization, a key indicator of congestion and stability. Random Forest, using other KPIs to predict PRB utilization, achieved the highest accuracy (RMSE<4%), while GRU effectively forecasted congestion one week in advance (RMSE ~7%). The comparative evaluation of these models offers unique insights into their strengths, providing practical applications in real-time LTE network management, enabling proactive congestion control and enhanced network stability.

Research topics

  • Advanced MIMO Systems Optimization
  • Advanced Wireless Network Optimization
  • Wireless Communication Networks Research

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.1109/3ict64318.2024.10824526

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.