Abstract

Cloud-native order management systems (OMS) built on microservice architectures must maintain high reliability while supporting frequent deployments and dynamic workloads. Conventional regression testing approaches often struggle to detect performance degradations in distributed cloud environments where services interact asynchronously. This paper presents an AI-driven continuous verification framework designed to monitor and validate the behavior of cloud-native OMS platforms during the deployment lifecycle. The framework integrates synthetic transaction data generation with machine-learning-based regression analytics to simulate realistic order processing scenarios while avoiding exposure of sensitive production data. A dataset consisting of 417 synthetic order transactions was generated to emulate a range of operational conditions including peak workloads, service delays, and edge-case failures. Telemetry metrics collected from distributed services such as latency, CPU utilization, and memory consumption were analyzed using regression-based anomaly detection models. Experimental observations indicate that the proposed framework can identify subtle performance regressions and service anomalies before they affect production environments. By integrating automated verification within CI/CD pipelines, the framework enables faster release cycles while maintaining operational reliability. The study demonstrates the practical value of combining synthetic data generation with intelligent analytics for scalable and privacy-preserving validation of enterprise cloud platforms.

References

• D. Gannon, R. Barga, and N. Sundaresan, “Cloud-native applications,” IEEE Cloud Computing, vol. 4, no. 5, pp. 16–21, 2017. https://doi.org/10.1109/MCC.2017.4250939
• W. Hasselbring and G. Steinacker, "Microservice Architectures for Scalability, Agility and Reliability in E-Commerce," 2017 IEEE International Conference on Software Architecture Workshops (ICSAW), Gothenburg, Sweden, 2017, pp. 243-246, doi: 10.1109/ICSAW.2017.11.
• S. Jahan, I. Riley, C. Walter, R. F. Gamble, M. Pasco, P. K. McKinley, and B. H. C. Cheng, “MAPE-K/MAPE-SAC: An interaction framework for adaptive systems with security assurance cases,” Future Generation Computer Systems, vol. 109, pp. 197–209, 2020. https://doi.org/10.1016/j.future.2020.03.031
• J. Kosińska and K. Zieliński, “Experimental evaluation of rule-based autonomic computing management framework for cloud-native applications,” IEEE Transactions on Services Computing, vol. 16, no. 2, pp. 1172–1183, 2023. https://doi.org/10.1109/TSC.2022.3159001
• J. Kosińska, B. Baliś, M. Konieczny, M. Malawski, and S. Zieliński, “Toward the observability of cloud-nativ applications: State-of-the-art overview,” IEEE Access, vol. 11, pp. 73036–73052, 2023. https://doi.org/10.1109/ACCESS.2023.3281860
• J. Thönes, “Microservices,” IEEE Software, vol. 32, no. 1, pp. 116–116, 2015. https://doi.org/10.1109/MS.2015.11
• J. P. K. Santos Nunes, S. Nejati, M. Sabetzadeh, and E. Y. Nakagawa, “Self-adaptive, requirements-driven autoscaling of microservices,” in Proc. IEEE/ACM SEAMS, 2024, pp. 168–174. https://doi.org/10.1145/3643915.3644094
• B. Burns, B. Grant, D. Oppenheimer, E. Brewer, and J. Wilkes, “Borg, Omega, and Kubernetes,” ACM Queue, vol. 14, no. 1, 2016. https://doi.org/10.1145/2898442.2898444
• B. R. Siqueira, F. C. Ferrari, and R. De Lemos, “Design and evaluation of controllers based on microservices,” in Proc. IEEE/ACM SEAMS, 2023, pp. 13–24. https://doi.org/10.1109/SEAMS59076.2023.00013
• J. Dean and L. A. Barroso, “The tail at scale,” Communications of the ACM, vol. 56, no. 2, pp. 74–80, 2013. https://doi.org/10.1145/2408776.2408794
• S. M. Shivam, A. P V and P. Jayachandran, "Anomaly Detection in Cloud Networks using Machine Learning Techniques," 2025 3rd International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Erode, India, 2025, pp. 1054-1058, DOI: 10.1109/ICSCDS65426.2025.11167399.
• C. Pahl, “Containerization and the PaaS cloud,” IEEE Cloud Computing, vol. 2, no. 3, pp. 24–31, 2015. https://doi.org/10.1109/MCC.2015.51