Configurable Containerized Testbed for Dataset Building for Anomaly Detection in Data Processing Infrastructure using Machine Learning

Minh Hieu Nguyen, Dmitry Ilin

Abstract


The article presents a fully container-based experimental testbed for producing high-resolution monitoring data with controlled anomalies, allowing for the methodical assessment of machine learning techniques for infrastructure-level anomaly detection. The platform creates synchronized application, database, and system-level metrics at 1 Hz across 18 workload configurations by integrating a FastAPI-PostgreSQL service, workload generation using Locust, and telemetry collection via Prometheus and cAdvisor. Deterministic fault-triggering mechanisms inject two realistic anomaly types, CPU saturation and database latency, online during workload execution. A comprehensive dataset is constructed and statistically analyzed, revealing distinct resource utilization patterns associated with each anomaly. Eight machine learning models are evaluated, including four supervised classifiers (logistic regression, random forest, XGBoost, and lightGBM) and four unsupervised anomaly detection methods (isolation forest, one-class SVM, local outlier factor, and PCA-based reconstruction error). The supervised models show superior detection performance, but the unsupervised approaches are less sensitive to even the smallest degradation of resources. The proposed infrastructure and dataset provide a reproducible basis for investigating performance anomalies in microservice contexts and enable future research on automated monitoring and anomaly detection.

Full Text:

PDF

References


Z. Zhong, Q. Fan, J. Zhang, M. Ma, S. Zhang, Y. Sun, Q. Lin, Y. Zhang, and D. Pei, “A survey of time series anomaly detection methods in the AIOps domain,” arXiv preprint arXiv:2308.00393, 2023.

F. Wang, Y. Jiang, R. Zhang, A. Wei, J. Xie, and X. Pang, “A survey of deep anomaly detection in multivariate time series: taxonomy, applications, and directions,” Sensors, vol. 25, no. 1, Art. no. 190, 2025.

A. Garg, W. Zhang, J. Samaran, S. Ramasamy, and C.-S. Foo, “An evaluation of anomaly detection and diagnosis in multivariate time series,” IEEE Trans. Neural Netw. Learn. Syst., 2021.

D. Abshari and M. Sridhar, “A survey of anomaly detection in cyber-physical systems,” arXiv preprint arXiv:2502.13256, 2025.

K. Hundman, V. Constantinou, C. Laporte, I. Colwell, and T. Soderstrom, “Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding,” in Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2018, pp. 387–395.

M. Llugiqi and R. Mayer, “An empirical analysis of synthetic-data-based anomaly detection,” in Machine Learning and Knowledge Extraction, Lecture Notes in Computer Science, 2022.

Y. Dang, Q. Lin, and P. Huang, “AIOps: Real-world challenges and research innovations,” in Proc. IEEE/ACM 41st Int. Conf. Software Engineering: Companion Proc. (ICSE-Companion), May 2019.

V. Mahavaishnavi, R. Saminathan, and R. Prithviraj, “Container security intelligence: Leveraging machine learning for anomaly detection in containerized applications,” Tuijin Jishu/Journal of Propulsion Technology, vol. 44, no. 3, 2023.

M. Raeiszadeh, A. Ebrahimzadeh, R. H. Glitho, J. Eker, and R. A. F. Mini, “Asynchronous real-time federated learning for anomaly detection in microservice cloud applications,” IEEE Trans. Mach. Learn. Commun. Netw., vol. 3, pp. 176–194, 2025.

T. Higgins, D. N. Jha, and R. Ranjan, “Swarm storm: An automated chaos tool for Docker Swarm applications,” in Proc. 33rd Int. Symp. High-Performance Parallel and Distributed Computing (HPDC), 2024, pp. 367–369.

S. Sondhi, S. Saad, K. Shi, M. Mamun, and I. Traore, “Chaos engineering for understanding consensus algorithms performance in permissioned blockchains,” arXiv preprint arXiv:2108.08441, 2021.

M. Allam, N. Boujnah, N. E. O’Connor, and M. Liu, “Synthetic time series for anomaly detection in cloud microservices,” arXiv preprint arXiv:2408.00006, 2024.

M. S. Islam, M. S. Rakha, W. Pourmajidi, J. Sivaloganathan, J. Steinbacher, and A. Miranskyy, “Anomaly detection in large-scale cloud systems: An industry case and dataset,” in Proc. IEEE/ACM 47th Int. Conf. Software Engineering: Software Engineering in Practice, 2025.

S. V. Kochergin, S. V. Artemova, A. A. Bakaev, E. S. Mityakov, Z. G. Vegera, and E. A. Maksimova, “Cybersecurity of smart grids: Comparison of machine learning approaches training for anomaly detection,” Russian Technological Journal, vol. 12, no. 6, pp. 7–19, 2024.

D. Kohyarnejadfard, D. Aloise, S. V. Azhari, and M. R. Dagenais, “Anomaly detection in microservice environments using distributed tracing data analysis and NLP,” Journal of Cloud Computing, 2022.

E. Hitimana, G. Bajpai, R. Musabe, L. Sibomana, and K. Jayavel, “Containerized architecture performance analysis for IoT framework based on enhanced fire prevention case study: Rwanda,” Sensors, vol. 22, no. 17, Art. no. 6462, 2022.

M. A. Rodriguez and R. Buyya, “Container-based cluster orchestration systems: A taxonomy and future directions,” arXiv preprint

S. Magomedov, D. Ilin, and E. Nikulchev, “Resource analysis of the log files storage based on simulation models in a virtual environment,” Applied Sciences, vol. 11, no. 11, Art. no. 4718, 2021.

Q. Wang, S. Kar, P. Mishra, C. Linduff, R. Izard, K. Anjam, G. Barrineau, J. Zulfiqar, and K.-C. Wang, “Container resource allocation versus performance of data-intensive applications on different cloud servers,” arXiv preprint arXiv:2311.07818, 2023.

G. Turin, A. Borgarelli, S. Donetti, F. Damiani, E. B. Johnsen, and S. L. Tapia Tarifa, “Predicting resource consumption of Kubernetes container systems using resource models,” Journal of Systems and Software, vol. 203, Art. no. 111750, 2023.

T. Rak, “Performance evaluation of an API stock exchange web system on cloud Docker containers,” Applied Sciences, vol. 13, no. 17, Art. no. 9896, 2023.

J. Wang, Y. Li, C. Jiang, and S. Guo, “Container performance prediction: Challenges and solutions,” in Communications and Networking, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2021.

S. Chen, “Locust swarms: A new multi-optima search technique,” in Proc. IEEE Congress on Evolutionary Computation (CEC), 2009.

P. Christen, D. J. Hand, and N. Kirielle, “A review of the F-measure: Its history, properties, criticism, and alternatives,” ACM Computing Surveys, vol. 56, no. 3, Art. no. 73, pp. 1–24, 2023.

J. Davis and M. Goadrich, “The relationship between precision-recall and ROC curves,” in Proc. 23rd Int. Conf. Machine Learning (ICML), 2006, pp. 233–240.

M. K. Chung, “Introduction to logistic regression,” arXiv preprint arXiv:2008.13567, 2020.

Y. M. Indah, R. Aristawidya, A. Fitrianto, and E. Erfiani, “Comparison of random forest, XGBoost, and LightGBM methods for the human development index classification,” Jambura Journal of Mathematics, vol. 7, no. 1, pp. 14–18, 2025.

R. P. Nathan, N. Nikolaou, and O. Lahav, “Finding Pegasus: Enhancing unsupervised anomaly detection in high-dimensional data using a manifold-based approach,” arXiv preprint arXiv:2502.04310, 2025.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162