ARTIFICIAL INTELLIGENCE–BASED PREDICTION OF CRITICAL FAILURES IN 5G NETWORK INFRASTRUCTURES AND REAL TIME QUALITY OF SERVICE (QOS) OPTIMIZATION
- Authors
-
-
Hayder Majid Sachit
University of Wasit / College of Science
Author
-
- Keywords:
- Artificial Intelligence, 5G Networks, Failure Prediction, Quality of Service, Machine Learning, Deep Learning, Network Optimization.
- Abstract
-
The rapid deployment of fifth-generation (5G) network system brings further complexity, heterogeneity and new performance requirements at the network side as well, which makes it increasingly difficult for telecommunications operators to offer reliable guarantees over QoS. The traditional Rule based and reactive network management mechanism could not be able to easily support static patterns as well as to process such high volumes of data generated in 5G scenarios. In the light of this development, AI has been considered for intelligent failure prediction as well as real-time network optimization.
In this paper a machine learning approach is proposed to predict critical failure of 5G network infrastructure and QoS parameters optimization on the fly. The study adopts a quantitative and experimental methodology leveraging synthetic and real-world (5G) datasets that are publicly accessible. Different types of traditional machine learning and deep learning models, e.g., Random Forest, Support Vector Machines (SVM) and Long Short Term Memory (LSTM) networks are used and compared to predict failures. In addition, a QoS optimization module based on reinforcement learning is introduced to dynamically assign the network bandwidth and optimize the service performance. - References
-
1.Akinlabi, A. A., Dahunsi, F. M., Popoola, J. J., & Okegbemi, L. B. (2025). Real-Time Mobile Broadband Quality of Service Prediction Using AI-Driven Customer-Centric Approach. Advances in Computing and Engineering.
2.Almeida, A., Rito, P., Brás, S., Pinto, F. C., & Sargento, S. (2024). A Machine Learning Approach to Forecast 5G Metrics in a Commercial 5G Platform. Computer Communications, 228, 107974.
3.Alnfiai, M. M. AI-Powered Cyber Resilience: Reinforcement Learning for Threat Hunting in 5G Networks. EURASIP Journal on Wireless Communications and Networking, 2025. https://doi.org/10.1186/s13638-025-02497-2
4.Al-Thaedan, A., Shakir, Z., Mjhool, A. Y., Alsabah, R., Al-Sabbagh, A., Nembhard, F., & Salah, M. (2024). ML Framework for Predicting Downlink Throughput in 4G-LTE/5G Networks. International Journal of Information Technology. https://doi.org/10.1007/s41870-023-01678-w
5.Bikkasani, D. C. & Yerabolu, M. R. AI-Driven 5G Network Optimization: A Comprehensive Review of Resource Allocation, Traffic Management, and Dynamic Network Slicing. American Journal of Artificial Intelligence, 8(2), 55-62, 2024.
6.Dong, R., She, C., Hardjawana, W., Li, Y., & Vucetic, B. (2020). Deep Learning for Radio Resource Allocation with Diverse QoS Requirements in 5G. arXiv preprint.
7.Ghanem, H., Samarah, S., & Mahmoud, Q. H. (2021). DISTINQT: A Distributed Privacy-Aware Learning Framework for QoS Prediction in Future Networks. arXiv preprint.
- Downloads
- Published
- 2026-03-01
- Issue
- Vol. 2 No. 2 (2026)
- Section
- Articles
- License
-
This work is licensed under a Creative Commons Attribution 4.0 International License.
