Observability and Monitoring of Machine Learning Models in Microservices-Based AI Platforms
Keywords:
Machine Learning Monitoring, Microservices, Observability, AI Platforms, Telemetry, Drift Detection, MLOps, Cloud-native, Model HealthSynopsis
Purpose: This study aims to investigate strategies for observability and monitoring of machine learning (ML) models within microservices-based AI platforms, identifying essential practices for ensuring reliability, scalability, and transparency in real-time intelligent systems.
Design/methodology/approach: A comprehensive literature review of foundational studies is followed by conceptual analysis, diagrams, and comparative tables to explore monitoring architectures and tools. Case-based abstraction of real-world implementations supports discussion.
Findings: Microservices and ML create operational complexity that traditional monitoring tools cannot handle. The convergence of observability practices with ML monitoring—through telemetry, explainability, and automation—is essential for dependable AI platforms.
Practical implications: Developers and AI engineers can improve fault detection, drift monitoring, and service health by adopting cloud-native observability platforms and ML-specific monitoring workflows integrated with CI/CD pipelines.
Originality/value: This paper uniquely bridges the disciplines of DevOps, MLOps, and service observability, highlighting pre-2020 research to support modern AI system stability.
References
(1) Bento, A. P. (2019). Observing and controlling performance in microservices. ProQuest. Link
(2) Rana, K. M. (2019). The impact of cloud-native observability platforms on service performance visibility. ResearchGate. Link
(3) Chakraborty, A., Ganguly, S., & Das, S. (2019). Architectural pattern for implementing XAI as a service. Taylor & Francis. Link
(4) Gummadi, V. P. K. (2019). Microservices architecture with APIs: Design, implementation, and MuleSoft integration. Journal of Electrical Systems, 15(4), 130–134. https://doi.org/10.52783/jes.9328
(5) Thompson, A. (2019). Integrating automation and AI in microservices architectures. IJAI&ML. Link
(6) Kumar, T. V. (2015). Cloud-native model deployment for financial applications. PhilPapers. Link
(7) Dalal, A. (2017). Developing scalable applications through serverless architectures. SSRN. Link
(8) Sidharth, S. (2019). Enhancing security of cloud-native microservices with service mesh technologies. PhilPapers. Link
(9) Prosper, J. (2019). Microservices architecture for agile integration. ResearchGate. Link
(10) Sethupathy, A., & Kumar, U. (2018). Self-healing systems and telemetry-driven automation in DevOps pipelines. ResearchGate. Link
(11) Yok, B. (2019). DevOps best practices for multi-cloud environments. IJAI&ML. Link
Published
Series
Categories
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
