A Machine Learning-Based Framework for Predictive Performance Optimization and Fault Detection in Cloud-Native Distributed Computing Infrastructure
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V7I3P109Keywords:
Distributed computing infrastructure, Machine learning, Predictive performance, Fault detection, Anomaly detection, Resource optimization, KubernetesAbstract
Scales, resilient and highly available applications depend on cloud-native distributed computing infrastructure. The complexity of interactions between microservices, containers, orchestration platforms, workloads and shared resources, however, poses a significant challenge in the areas of optimal performance and early fault detection. In this paper, a novel machine learning-based framework that focuses on predictive performance optimization and fault detection in cloud-native distributed computing infrastructure is presented. The proposed framework is based on continuous infrastructure monitoring, telemetry data collection, data preprocessing, feature engineering, machine learning-based performance prediction, resource optimization, anomaly detection, fault classification, and intelligent decision-making, all of which are part of a closed-loop system. The heterogeneous telemetry data (CPU and Memory utilization, network activity, input/output operations, response latency, throughput, error rate, logs, distributed trace, orchestration event) is analyzed to understand the patterns of systems behavior and forecast the future state of the systems. The prediction layer forecasts the behaviour of workloads, resource requirements and potential performance degradation which can then lead to proactive decisions on how to handle workloads, including the possibility of autoscaling, reallocating resources or redistributing workloads. Concurrently, the fault and anomaly detection engine detects anomalies, categorizes failures and helps to conduct early failure mitigation and root cause analysis. The experimental evaluation shows the potential of the proposed approach to improve the accuracy of the predictions, to reduce the response latency, to minimize the breach of the service level agreements, to optimize the utilization of the resources and to improve the fault-detection performance, over the conventional reactive approaches. The framework is designed to be scalable and adaptable to create intelligent, self-adaptive and resilient cloud-native distributed computing environments.
References
[1] Soldani, J., & Brogi, A. (2022). Anomaly detection and failure root cause analysis in (micro) service-based cloud applications: A survey. ACM Computing Surveys (CSUR), 55(3), 1-39.
[2] Muzeeb Mohammad . Survey on AI-based Reliability and Anomaly Detection in Microservices. International Journal of Computer Applications. 187, 74 ( Jan 2026), 56-63. DOI=10.5120/ijca2026926263
[3] Saxena, D., Kumar, J., Singh, A. K., & Schmid, S. (2023). Performance analysis of machine learning centered workload prediction models for cloud. IEEE Transactions on Parallel and Distributed Systems, 34(4), 1313-1330.
[4] Saxena, D., & Singh, A. K. (2021). Workload forecasting and resource management models based on machine learning for cloud computing environments. arXiv preprint arXiv:2106.15112.
[5] Bodra, D., & Khairnar, S. (2025). Machine learning-based cloud resource allocation algorithms: a comprehensive comparative review. Frontiers in computer science, 7, 1678976.
[6] Duc, T. L., Leiva, R. G., Casari, P., & Östberg, P. O. (2019). Machine learning methods for reliable resource provisioning in edge-cloud computing: A survey. ACM Computing Surveys (CSUR), 52(5), 1-39.
[7] Hagemann, T., & Katsarou, K. (2020, December). A systematic review on anomaly detection for cloud computing environments. In Proceedings of the 2020 3rd Artificial Intelligence and Cloud Computing Conference (pp. 83-96).
[8] Kaul, D. (2024). Ai-driven self-healing container orchestration framework for energy-efficient kubernetes clusters. Emerg. Sci. Res, 2024, 1-13.
[9] Nawrocki, P., & Smendowski, M. (2024). FinOps-driven optimization of cloud resource usage for high-performance computing using machine learning. Journal of Computational Science, 79, 102292.
[10] Patchamatla, P. S. S. R. (2025). Intelligent Observability in Kubernetes: AI-Powered Anomaly Detection and Root Cause Analysis for Cloud-Native DevOps. Journal of Advances in Computational Intelligence Theory, 7(2).
[11] Vadisetty, R., & Polamarasetti, A. (2025). AI-driven Kubernetes orchestration: utilizing intelligent agents for automated cluster management and optimization. Cuestiones de Fisioterapia, 54(5), 28-36.
[12] Soundappan, S. J. (2024). Generative AI Enabled Enterprise Systems with Autonomous Operations and Cloud-Native Architectures. International Journal of Computer Technology and Electronics Communication, 7(4), 9247-9253.
[13] Feng, G., Xu, J., Jian, W., & Liu, Z. (2022, November). Load prediction optimization based on machine learning in cloud computing environment. In Proceedings of the 4th International Conference on Advanced Information Science and System (pp. 1-5).
[14] Yu, G., Huang, Z., & Chen, P. (2023). TraceRank: Abnormal service localization with dis‐aggregated end‐to‐end tracing data in cloud native systems. Journal of Software: Evolution and Process, 35(10), e2413.
[15] Kumaresan, Mageshwaran (2025) A Reinforcement Learning Approach to Real-Time, Cost-Aware Kubernetes Auto-Scaling. Masters thesis, Dublin, National College of Ireland.
[16] Zou, X., Jiang, X., Huang, R., He, H., Kapoor, P., Wu, H., ... & Zhao, J. (2025). Towards generalizable context-aware anomaly detection: A large-scale benchmark in cloud environments. arXiv preprint arXiv:2508.01844.
[17] Fernando, D. T. (2026). Anomaly Detection and Diagnosis for Microservices-based IoT Applications in Edge Computing Environments.
[18] Eje, D., Sharma, T., Patel, K., Mazzara, M., & Johard, L. (2026). LogNEO: A GPT-Neo Reinforcement Learning Framework for Accurate Real-Time Log Anomaly Detection. arXiv preprint arXiv:2606.08153.
[19] Floroiu, M. S., Russo, S., Giamattei, L., Guerriero, A., Malavolta, I., & Pietrantuono, R. (2024, July). Anomaly detection and root cause analysis of microservices energy consumption. In 2024 IEEE International Conference on Web Services (ICWS) (pp. 590-600). IEEE.
[20] Job Antunes Grabher, G., Machida, F., & Ropars, T. (2025, December). Modeling Anomaly Detection in Cloud Services: Analysis of the Properties that Impact Latency and Resource Consumption. In Proceedings of the 18th IEEE/ACM International Conference on Utility and Cloud Computing (pp. 1-10).
[21] Shaikh, F., Reali, G., & Femminella, M. (2025, October). Intelligent Autoscaling with Attention-based Reinforcement Learning for SLA-Aware Resource Management in Edge-Cloud Environments. In 2025 21st International Conference on Network and Service Management (CNSM) (pp. 1-9). IEEE.
[22] Brahmandam, L. M. K. (2026). A Decision Framework for Multi-Cloud Microservice Deployment across AWS and GCP: Empirical Evaluation of EKS, Cloud Functions, Cloud Run, and Cross-Cloud Networking Patterns. International Journal of Emerging Trends in Computer Science and Information Technology, 7(1), 365-373. https://doi.org/10.63282/3050-9246.IJETCSIT-V7I1P152
[23] Paruchuri, J. K. (2024). Apache Kyuubi on Kubernetes: Building Elastic Multi-Tenant Spark SQL Platforms. INDO-CONTINENTAL ACADEMIC PUBLISHERS.
[24] Sunkara, R. (2024). Improving Observability and Stability in Wayland-Based Compositors: Lifecycle Logging, Buffer Validation, and Crash Hardening in Production Display Stacks. American International Journal of Computer Science and Technology, 6(1), 60-64. https://doi.org/10.63282/3117-5481/AIJCST-V6I1P106
[25] Gantikota, S. (2023). Integrating SonarQube and IBM AppScan into Enterprise CI/CD Pipelines: A Vulnerability Mitigation Framework Achieving Over Eighty Percent Risk Reduction. International Journal of Emerging Trends in Computer Science and Information Technology, 4(3), 240-244. https://doi.org/10.63282/3050-9246.IJETCSIT-V4I3P124
