Preliminary Results of a Systematic Mapping Study of AIOps Practices and Trends

• Juan Ignacio Irabedra ORT
• Martín Solari ORT

DOI: https://doi.org/10.5753/cibse.2025.35336

Abstract

This work aims at identifying the main AIOps techniques reported in peer-reviewed literature in the last six years (1) and classify the techniques according to what software quality attribute to they contribute to. It presents the preliminary results of a systematic mapping study considering peer-reviewed literature. 72 peer-reviewed studies were analyzed in order to extract strategies and practices. Anomaly detection and fault prediction were the strategies most often applied on AIOps. Classical machine learning techniques, as well as deep learning techniques were the most frequently found groups of techniques in literature. Availability and maintainability are the most frequently software quality attributes improved by applying AIOps techniques.

Keywords: AIOps, DevOps, AI, Software Engineering, Software Quality

References

Durrani, U. K., Akpinar, M., Fatih Adak, M., Talha Kabakus, A., Maruf Ozturk, M., and Saleh, M. (2024). A decade of progress: A systematic literature review on the integration of ai in software engineering phases and activities (2013-2023). IEEE Access, 12.

Potts, W. C. and Carver, C. (2024). Best practices implementing aiops in large organizations. In 2024 International Conference on Smart Applications, Communications and Networking (SmartNets).

Zhang, C., Chen, W., and Xie, Y. (2024). Research on aiops-based intelligent monitoring technology for meteorological business. In 2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).