Network Downtime Prediction Using Alert System in Telecommunications Industry

Aloka Simpson Chisom; AgbakwuruA Onyekachi

doi:10.56201/ijemt.vol.11.no7.2025.pg231.237

📄 Download Paper

Network Downtime Prediction Using Alert System in Telecommunications Industry

Aloka Simpson Chisom, AgbakwuruA Onyekachi

Abstract

Network downtime remains a critical challenge in the telecommunications industry, particularly in developing regions like Nigeria where reliable connectivity is essential for economic, educational, and healthcare activities. This work proposed a network downtime prediction with alert system using machine learning techniques, aimed at transitioning from reactive fault management to proactive network reliability strategies. The motivation for this research stems from the increasing demand for uninterrupted internet service and the limitations of existing monitoring systems in forecasting failures. This work promises to reduce downtime occurrence by predicting and alerting network admin of possible downtime for necessary action. A hybrid methodological approach combining Structured Systems Analysis and Design Methodology (SSADM) and Object-Oriented Analysis and Design Methodology (OOADM) was employed. SSADM guided the functional decomposition and data flow modeling, while OOADM facilitated the modular and scalable design of the predictive system. Historical network data was analyzed to identify failure patterns, environmental triggers, and performance anomalies using time series and classification models. The predictive system was developed using Python, due to its extensive libraries for data analysis and machine learning, including Scikit-learn, Pandas, and TensorFlow. A key feature of the system is its ability to alert network admin of potential downtime via emails or SMS, enabling timely for preventive action. The resulting system architecture includes data flow diagrams, use case models, and a working prototype, offering a practical solution for improved fault prediction and reduced downtime. This paper supports the development of more resilient telecommunications infrastructure in resource-constrained environments.

Keywords

SMSAlertNetworksMachine Learning

References

[1]. Sharma, V., & Patel, K. (2020). Scalable machine learning architecture for fault detection in large telecom networks: The AT&T experience. IEEE Communications Magazine, 58(11), 24–30. https://doi.org/10.1109/MCOM.001.2000323 [2]. Jiang, S., & Tsai, C. F. (2020). Network traffic classification for bandwidth allocation using machine learning. Applied Soft Computing, 86, Article https://doi.org/10.1016/j.asoc.2019.105879 [3]. International Telecommunication Union – Telecommunication Standardization Sector. (2016). Quality of Experience: A Framework (Recommendation P.10/G.100). https://www.itu.int/rec/T-REC-P.10 [4]. Okonkwo, F. C., & Adebayo, A. O. (2021). Network reliability in the Nigerian telecommunications sector: Challenges and strategic interventions. Nigerian Journal of Communications Technology, 18(1), 15–27. https://doi.org/10.4314/njct.v18i1.2 [5]. Li, Y., Wu, X., & He, Q. (2020). Real-time big data analytics for network monitoring using Apache Kafka and Apache Spark. Future Generation Computer Systems, 100, 460–473. https://doi.org/10.1016/j.future.2019.05.002 [6]. Buhalis, D., & Sinarta, Y. (2019). Real-time co-creation and nowness service: Lessons from tourism and hospitality. Journal of Travel & Tourism Marketing, 36(5), 563–582. https://doi.org/10.1080/10548408.2019.1592059 [7]. Oluwaseun, A., & Laryea, E. (2019). Environmental stress and telecommunications reliability in West Africa: A system-level analysis. International Journal of Network Management, 29(3), Article e2075. https://doi.org/10.1002/nem.2075 [8]. Kumar, R., & Bansal, A. (2022). A hybrid CNN-Transformer approach for fault prediction in edge-enabled smart networks. Future Generation Computer Systems, 129, 121–132. https://doi.org/10.1016/j.future.2021.11.006 [9]. Kumar, S., & Singh, R. (2020). Transmission link failure prediction using ensemble learning: A practical deployment case study. International Journal of Network Management, 30(5), Article e2105. https://doi.org/10.1002/nem.2105 [10]. Wang, J., He, Y., & Sun, Q. (2020). Comparative study of deep learning models for predictive network fault detection. IEEE Transactions on Network and Service Management, 17(3), 1623–1635. https://doi.org/10.1109/TNSM.2020.2994452 [11]. Zhang, H., & Yang, J. (2022). Deep ensemble models for fault prediction in software-defined networking: A theoretical and empirical study. Computer Networks, 212, Article 108053. https://doi.org/10.1016/j.comnet.2022.108053 [12]. Davies, T., Brown, C., & Lin, Y. (2020). Information-theoretic foundations of predictive network monitoring under noisy conditions. IEEE Transactions on Network and Service Management, 17(4), 2215–2228. https://doi.org/10.1109/TNSM.2020.3033321 [13]. Roberts, M., & Smith, A. (2019). Entropy-based anomaly detection in complex networks: A theoretical framework. Journal of Network and Computer Applications, 144, 99–111. https://doi.org/10.1016/j.jnca.2019.06.015 [14]. Quang, D., & Kim, K. (2019). A survey of anomaly detection methods in network intrusion detection systems. Journal of Network and Computer Applications, 112, 13–22. https://doi.org/10.1016/j.jnca.2018.04.002 [15]. Reichheld, F. F. (2003). The one number you need to grow. Harvard Business Review, 81(12), 46–54.

Network Downtime Prediction Using Alert System in Telecommunications Industry

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY