Abstract

The arrival of 5G fomented an explosive growth in the complexity of networks, as well as the number of operational events generated by network functions. Today’s monolithic monitoring implementations simply aren’t designed to cope with the high velocity and mixed cardinality of such data. This paper presents and evaluates cloud-native telemetry pipelines specifically for 5G event-based operations. Leveraging microservices architecture, the solution incorporates containers on ingestion layers, streaming processing and persistent storage for real-time observability. A simulated dataset consisting of 446 unique samples of 5G Radio Access Network (RAN) and Core network events. The stack used in the implementation consists of Apache Kafka for message streaming, Prometheus as a time series metric collector and a Kubernetes cluster to orchestrate everything. The study shows that a cloud-native separation of telemetry generation and processing can significantly reduce latency while achieving more granularity in network intelligence. This is the first work to provide action recipe to analyze network health with respect to service plans based on the scalable design of large-scale event ingestion.

References

• S. J. Warnett and U. Zdun, "On the Understandability of MLOps System Architectures," in IEEE Transactions on Software Engineering, vol. 50, no. 5, pp. 1015-1039, May 2024.
• T. V. Kale and S. Mendhe, "A Review on Advances in Sentiment Analysis: A Deep Learning Approach Using Transformer Based Models," 2025 4th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Bhimdatta, Nepal, 2025, pp. 235-239
• S. R. Kadam and M. P. Dhore, "Review of Deep Learning Methods," 2024 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA), Pune, India, 2024, pp. 1-8.
• Z. Chi, Z. Ciling and Z. Weiwei, "Refining Automation in Power Dispatching Systems: A Cloud Optimization Investigation," 2024 International Conference on Inventive Computation Technologies (ICICT), Lalitpur, Nepal, 2024, pp. 1899-1904.
• D. Taibi, V. Lenarduzzi, and C. Pahl, “Processes, motivations, and issues for migrating to microservices architectures: An empirical investigation,” IEEE Cloud Computing, vol. 4, no. 5, pp. 22–32, 2017.
• B. Bokkena, "Optimizing Cloud Infrastructure Management Using Large Language Models: A DevOps Perspective," 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India, 2024, pp. 1401-1406.
• P. Jamshidi, C. Pahl, N. Mendonça, J. Lewis, and S. Tilkov, “Microservices: The journey so far and challenges ahead,” IEEE Software, vol. 35, no. 3, pp. 24–35, 2018.
• L. Li, Z. Han and C. Liu, "A Novel Unsupervised Anomaly Detection Method Based on Improved Collaborative Discrepancy Optimization," 2024 36th Chinese Control and Decision Conference (CCDC), Xi'an, China, 2024, pp. 4576-4581
• Z. Yang, P. Nguyen, H. Jin, and K. Nahrstedt, “MIRAS: Model-based reinforcement learning for microservice resource allocation over scientific workflows,” in Proceedings of the IEEE International Conference on Distributed Computing Systems (ICDCS), Dallas, TX, USA, Jul. 2019, pp. 122–132.
• T. Wang, W. Zhang, J. Xu, and Z. Gu, “Workflow-aware automatic fault diagnosis for microservice-based applications with statistics,” IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2350–2363, 2020.
• J. Bogatinovski, S. Nedelkoski, J. Cardoso, and O. Kao, “Self-supervised anomaly detection from distributed traces,” in Proceedings of the IEEE/ACM International Conference on Utility and Cloud Computing (UCC), Leicester, UK, Dec. 2020, pp. 342–347.
• P. Liu, H. Xu, Q. Ouyang, R. Jiao, Z. Chen, S. Zhang, and D. Pei, “Unsupervised detection of microservice trace anomalies through service-level deep Bayesian networks,” in Proceedings of the IEEE International Symposium on Software Reliability Engineering (ISSRE), Coimbra, Portugal, Oct. 2020, pp. 48–58.
• F. Al-Doghman, N. Moustafa, I. Khalil, N. Sohrabi, Z. Tari, and A. Zomaya, “AI-enabled secure microservices in edge computing: Opportunities and challenges,” IEEE Transactions on Services Computing, vol. 16, no. 3, pp. 1485–1504, 2023.