Incident Intelligence in Telecom: A Framework for Real-Time Production Defect Triage and P0 Resolution
DOI:
https://doi.org/10.15662/gh9a4s41Keywords:
Telecom, P0, Production, Incident IntelligenceAbstract
The rising intricacy of the telecom platforms drives the need of the intelligent, automated incident response systems. The current paper describes a real-time incident intelligence platform that was implemented into Charter Communications Mobile 2 ecosystem. Using Kafka-based ingestion of logs, the machine learning logic of chooser responder, and RCA pipelines that are automatic with Splunk and Datadog, this framework will lower the mean time to detect, assign, and resolve P0 incidents considerably. The deployment in the real world illustrates the better levels of keeping to the SLA, automation of the triage and resilience of the systems. The architecture will combine well-organized playbooks and feedback loops to permit continuous learning. The findings indicate that these structures can be the framework to provide a model of scalable, intelligent triage of production defects in a telco-grade application
References
[1] Tiwari, P., Patel, S., Bharti, H., & Chintala, M. (2022, January 18). US20230245011A1 - Cognitive incident triage (cit) with machine learning - Google Patents. https://patents.google.com/patent/US20230245011A1/en
[2] Zhang, K., Kalander, M., Zhou, M., Zhang, X., & Ye, J. (2021). An influence-based approach for root cause alarm discovery in telecom networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2105.03092
[3] Wang, H., Wu, Z., Jiang, H., Huang, Y., Wang, J., Kopru, S., & Xie, T. (2021). Groot: An event-graph-based approach for root cause analysis in industrial settings. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2108.00344
[4] Remil, Y., Bendimerad, A., Mathonat, R., & Kaytoue, M. (2024). AIOPs Solutions for Incident Management: Technical guidelines and a comprehensive literature review. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2404.01363
[5] Varadaraj, N. P. G. (2025). Automating Data Observability Metrics with Splunk ML AI: A Technical Analysis. International Journal of Scientific Research in Computer Science Engineering and Information Technology, 11(2), 2284–2291. https://doi.org/10.32628/cseit25112703
[6] Misal, N. J. (2024). Mastering automation tools for incident management and monitoring. International Journal of Scientific Research in Computer Science Engineering and Information Technology, 10(6), 1465–1481. https://doi.org/10.32628/cseit241061184
[7] Mahida, A. (2023). Real-Time Incident Response and Remediation-A review Paper. Journal of Artificial Intelligence & Cloud Computing, 1–3. https://doi.org/10.47363/jaicc/2023(2)247
[8] Ranjan, P., Najana, M., Chintale, P., & Dahiya, S. (2024). Building Resilient Systems Through Observability. Building Resilient Systems Through Observability. https://doi.org/10.21428/e90189c8.bbe6ce75
[9] Ahmed, T., Ghosh, S., Bansal, C., Zimmermann, T., Zhang, X., & Rajmohan, S. (2023). Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2301.03797
[10] Li, Y., Zhang, X., He, S., Chen, Z., Kang, Y., Liu, J., Li, L., Dang, Y., Gao, F., Xu, Z., Rajmohan, S., Lin, Q., Zhang, D., & Lyu, M. R. (2022). An intelligent framework for timely, accurate, and comprehensive cloud incident detection. ACM SIGOPS Operating Systems Review, 56(1), 1–7. https://doi.org/10.1145/3544497.3544499
