Skip to main content

Adaptive Kubernetes Resource Optimization for Cloud Native Enterprise Platforms using Reinforcement Learning

Dr.V. P. Gladis Pushparathi, R.M.Shiny

Department of Computer Science & Engineering, Velammal Institute Technology, Chennai, India

Abstract

Kubernetes has become a fundamental orchestration platform for cloud-native enterprise applications because it enables automated deployment, scaling, scheduling, and management of containerized workloads. However, efficiently allocating CPU, memory, replicas, and other resources remains challenging because enterprise workloads exhibit dynamic and unpredictable demand patterns. Conventional Kubernetes resource-management mechanisms frequently depend on manually configured requests, limits, autoscaling thresholds, and predefined scheduling policies. Although these mechanisms provide operational stability, they may not continuously adapt to changing workload characteristics or optimize multiple objectives simultaneously. This paper proposes an adaptive Kubernetes resource optimization framework based on reinforcement learning. The proposed framework continuously observes workload behavior, resource utilization, application performance, and cluster conditions before selecting resource-management actions through a learning-based decision process. The reinforcement learning agent is designed to balance resource utilization, application latency, service-level objectives, scalability, and infrastructure efficiency rather than optimizing a single resource dimension. Historical workload traces and controlled experiments are used to train and evaluate the agent under stable, bursty, seasonal, and unpredictable workload conditions. The methodology compares the proposed approach with conventional Kubernetes autoscaling and resource-management strategies using metrics including resource utilization, latency, throughput, scaling responsiveness, scheduling efficiency, service-level compliance, and computational overhead. Safety constraints are incorporated to prevent actions that could cause unacceptable service degradation. The proposed framework aims to establish an adaptive resource-management mechanism capable of learning workload-specific optimization policies while maintaining operational reliability in cloud-native enterprise Kubernetes platforms

Article Information

Journal

International Journal of Science, Research and Technology

Volume (Issue)

Vol. 7 No. 6 (2024): International Journal of Science, Research and Technology (IJSRAT)

DOI

https://doi.org/10.15662/IJSRAT.2024.0706018

Pages

13329-13337

Published

December 18, 2024
Copyright

Open Access

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Dr.V. P. Gladis Pushparathi, R.M.Shiny (%2024). Adaptive Kubernetes Resource Optimization for Cloud Native Enterprise Platforms using Reinforcement Learning. International Journal of Science, Research and Technology , Vol. 7 No. 6 (2024): International Journal of Science, Research and Technology (IJSRAT) , pp. 13329-13337. https://doi.org/10.15662/IJSRAT.2024.0706018

References

1. Abdullah, S. M., Chy, M. S. K., Gazi, M. S., Alam, A., Himeluzzaman, M., Onik, T. A., & Jakir, T. (2023). Quantum-Enhanced Machine Learning for Early Disease Diagnosis: A Systematic Review and Public Health Innovation Perspective. International Journal of Science, Research and Technology, 6(4), 10384-10392.
2. Sandhu, Y. S. (2024). Real time ETL optimization using change data capture incremental. International Journal of Emerging Trends in Engineering and Management Research, 9(3), 15711–15721.
3. Ramasamy, M. (2022). Closed-loop network automation: Architectural principles from Catalyst Center-scale systems. International Research Journal of Innovative Engineering, 6(3), 10698–10708.
4. Polamarasetty, V. K. (2021). Modernizing SAP sales and distribution systems through ABAP-based enterprise solutions. International Journal of Research and Applied Innovations, 4(2), 4925–4930.
5. Bitragunta, S. L. V. (2024). AI-driven deep learning-based animal intrusion detection and early warning system for railroad tracks. International Research Journal of Innovative Engineering, 8(1), 13909–13918.
6. Li, Y. J., Huang, A., Sanku, B. S., & He, J. S. (2023, March). Designing an empathy training for depression prevention using virtual reality and a preliminary study. In 2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (pp. 44-52). IEEE.
7. Kondapalli, K. K., & Gunupudi, C. (2023). Artificial intelligence ethics and principles in public sector healthcare: A governance framework for responsible AI adoption in local and sub-national health services. Lex localis-Journal of Local Self-Government, 21 (S2), 61–81.
8. Jain, R. (2019). The hidden tax: A production framework for cloud cost architecture in enterprise data workloads. International Journal of Science, Research and Technology (IJSRAT), 2(6), 2522–2530.
9. Sugumar, R. (2022). Federated Learning and Distributed AI Architectures for Cloud-Based Cyber Healthcare Data Collaboration Systems. International Journal of Future Innovative Science and Technology (IJFIST), 5(5), 9232.
10. Vedula, J. (2023). Enterprise release assurance for interconnected energy data, cloud, and application platforms: A governance framework for coordinated, multi-team release delivery. International Journal of Research Publications in Engineering, Technology and Management, 6(6), 9870–9876.
11. Jeyaraj, S. A. L., Kumar, S., Revathy, S., Yenigalla, G., Krishna, K. B., & Jayabalan, K. (2024). Machine Learning Algorithms for E-Commerce Security: A Practical Approach. In Strategies for E-Commerce Data Security: Cloud, Blockchain, AI, and Machine Learning (pp. 361-385). IGI Global Scientific Publishing.
12. Venkatasalam, K., Rajendran, P., & Thangavel, M. (2019). Improving the accuracy of feature selection in big data mining using accelerated flower pollination (AFP) algorithm. Journal of medical systems, 43(4), 96.
13. Manda, P. (2024). Oracle E-Business Suite modernization: The transition from 12.1.3 to 12.2.8. International Journal of Research and Applied Innovations, 7(3), 10838–10842.
14. Bellundagi, M. (2024). An intelligent digital transformation framework for smart enterprises using AI and cloud computing. International Journal of Science, Research and Technology, 7(4), 12433-12446.
15. Soundappan, S. J. (2021). Integrated Artificial Intelligence Framework for Enterprise Cloud Modernization and Intelligent Threat Management Systems. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 4(4), 5274-5284.
16. Punithavathi, R., Selvi, R. T., Latha, R., Kadiravan, G., Srikanth, V., & Shukla, N. K. (2022). Robust node localization with intrusion detection for wireless sensor networks. Intelligent Automation and Soft Computing, 33(1), 143-156.
17. Raja, G. V. (2022). AI Enabled Cloud and Data Engineering Frameworks for Secure, Scalable, and Intelligent Cyber Physical Analytics Systems. International Journal of Research and Applied Innovations, 5(4), 7395-7409.
18. Ambalakannu, M. (2024). Driving operational efficiency and clinical insights via unified care management. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 7(4), 10693-10702.
19. Koganti, H. (2024). Beyond reactive scaling: A review of AI-driven proactive and context-aware auto-scaling in cloud-edge environments. International Journal of Engineering & Extended Technologies Research, 6(3), 8175–8183.
20. Sudhan, S. K. H. H., & Kumar, S. S. (2016). Gallant Use of Cloud by a Novel Framework of Encrypted Biometric Authentication and Multi Level Data Protection. Indian Journal of Science and Technology, 9, 44.
21. Selvarajan, K. (2023). Improving data reliability through automated data quality frameworks in distributed systems. International Journal of Future Innovative Science and Technology (IJFIST), 6(3), 10630–10640.
22. Mathew, A. (2021). Artificial intelligence and cognitive computing for 6G communications & networks. International Journal of Computer Science and Mobile Computing, 10(3), 26-31.
23. Selvarajan, K. (2023). Improving data reliability through automated data quality frameworks in distributed systems. International Journal of Future Innovative Science and Technology (IJFIST), 6(3), 10630–10640.
24. Srikanth, V., Walia, R., Augustine, P. J., Simla, J., & Jegajothi, B. (2022, March). Chaotic Whale Optimization based Node Localization Protocol for Wireless Sensor Networks Enabled Indoor Communication. In 2022 International Conference on Electronics and Renewable Systems (ICEARS) (pp. 702-707). IEEE.
25. Bandhela, R. R., Onteddu, A. R., & Kundavaram, R. R. (2022). Enhancing precision healthcare machine learning for advanced diagnostics and personalized treatment. South Eastern European Journal of Public Health. https://doi.org/10.70135/seejph.vi.6690
26. Kavuru, R. R., & Balaji, R. (2023). Extending the service mesh into a compliance enforcement fabric: A policy-aware architecture for regulated financial platforms. International Journal of Emerging Trends in Engineering and Management Research, 8(3), 13612–13618.
27. Badam, L. R. (2022). Machine learning-based catastrophic loss prediction for climate-related insurance risk. International Journal of Future Innovative Science and Technology (IJFIST), 5(1), 7807.
28. Gopinathan, V. R. (2023). Modernizing Enterprise Applications Using Intelligent API Frameworks Machine Learning and Cloud Native Computing. International Journal of Science, Research and Technology, 6(5), 10690-10697.
29. Jayaraman, S., Rajendran, S., & P, S. P. (2019). Fuzzy c-means clustering and elliptic curve cryptography using privacy preserving in cloud. International Journal of Business Intelligence and Data Mining, 15(3), 273-287.