Reinforcement Learning–Driven Kubernetes Resource Scheduling for High-Performance Enterprise Distributed Cloud Computing

Dr. Vinoth Kumar M; Dr. Vinoth Kumar M

doi:10.15662/IJSRAT.2025.0806018

Reinforcement Learning–Driven Kubernetes Resource Scheduling for High-Performance Enterprise Distributed Cloud Computing

Dr. Vinoth Kumar M

Associate Professor, Department of Information Science and Engineering, RV Institute of Technology and Management, Bangalore, India

Abstract

Modern enterprise distributed cloud environments rely heavily on Kubernetes to orchestrate containerized workloads across geographically dispersed edge, hybrid, and multi-cloud nodes. However, native Kubernetes scheduling algorithms employ static, heuristic-based mechanisms that depend on pre-declared resource requests. These static models fail to account for dynamic network topologies, variable cross-site latencies, noisy-neighbor contention, and fluctuating execution demands in distributed cloud fabrics, often causing severe resource strandedness, elevated SLA breaches, and sub-optimal cluster efficiency. This paper presents an advanced Deep Reinforcement Learning (DRL) framework integrated natively into the Kubernetes scheduling pipeline for distributed cloud computing. By formulating workload orchestration as a Markov Decision Process (MDP), the proposed framework captures high-dimensional distributed telemetry, including real-time CPU/memory utilization, network round-trip time (RTT), inter-node link bandwidth, and local storage I/O. Leveraging a Proximal Policy Optimization (PPO) agent enhanced with graph neural networks (GNNs) to model distributed node topologies, the system dynamically learns optimal pod placement policies. Experimental evaluations across heterogeneous, multi-region enterprise cloud benchmarks demonstrate that the DRL-driven scheduler improves overall cluster resource utilization by 33%, reduces cross-site latency for latency-sensitive microservices by 38%, and cuts SLA violation rates by 46% compared to default Kubernetes scheduling policies. This provides a robust blueprint for intelligent distributed cloud orchestration.

Article Information

Journal	International Journal of Science, Research and Technology
Volume (Issue)	Vol. 8 No. 6 (2025): International Journal of Science, Research and Technology (IJSRAT)
DOI	https://doi.org/10.15662/IJSRAT.2025.0806018
Pages	15424-15430
Published	December 10, 2025
Copyright	All rights reserved
Open Access	This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite	Dr. Vinoth Kumar M (%2025). Reinforcement Learning–Driven Kubernetes Resource Scheduling for High-Performance Enterprise Distributed Cloud Computing. International Journal of Science, Research and Technology , Vol. 8 No. 6 (2025): International Journal of Science, Research and Technology (IJSRAT) , pp. 15424-15430. https://doi.org/10.15662/IJSRAT.2025.0806018

References

1. Mohammed, S. (2024). Resilient multi-region cloud architecture for high availability and disaster recovery. International Journal of Multidisciplinary and Scientific Emerging Research, 12(3), 1412–1427. https://doi.org/10.15662/IJMSERH.2024.1203046
2. Billah, M. M., Nath, A. D., Das, D., Mahmud, T., & Rahman, R. (2023). Skin cancer classification using NasNet. World Journal of Advanced Research and Reviews, 19, 1652–1658.
3. Gunda, S. R. (2025). Optimizing cloud computing resource utilization through intelligent allocation and containerization strategies. Journal of Computer Science and Technology Studies, 7(8), 238–244.
4. Anand, L., & Neelanarayanan, V. (2020, October). Enchanced multiclass intrusion detection using supervised learning methods. In AIP Conference Proceedings (Vol. 2282, No. 1, p. 020044). AIP Publishing LLC.
5. Chaba, A. (2025). Agent orchestration: A new paradigm for autonomous and scalable MarTech ecosystems. ISCSITR-International Journal of Computer Science and Engineering (ISCSITR-IJCSE), 6(4), 63–76.
6. Sojol, J. I., Piya, N. F., Sadman, S., & Motahar, T. (2018). Smart bus: An automated passenger counting system. International Journal of Pure and Applied Mathematics, 118(18), 3169–3177.
7. Narayanan, S. (2024). Cyber risk orchestration for systemic financial stability: An autonomous financial impact forecasting. International Journal of Research in Computer Applications and Information Technology, 7(2), 2927–2939. https://philarchive.org/archive/NARCRO
8. Gurram, S. K. (2025). Revolutionizing financial infrastructure: The convergence of blockchain and cloud in next-generation payment networks. Journal of Computer Science and Technology Studies, 7(4), 607–618.
9. Konakalla, K. (2022). Migrating home-grown sales systems to Salesforce CRM: Challenges, solutions, and long-term benefits. International Journal of Future Management Research, 4(1).
10. Kesarpu, S. (2025, June). Contract testing with PACT: Ensuring reliable API interactions in distributed systems. The American Journal of Engineering and Technology, 7(6), 14–23. https://doi.org/10.37547/tajet/Volume07Issue06-03
11. Potdar, A., Kodela, V., Srinivasagopalan, L. N., Khan, I., Chandramohan, S., & Gottipalli, D. (2025, July). Next-generation autonomous troubleshooting using generative AI in heterogeneous cloud systems. In 2025 International Conference on Information, Implementation, and Innovation in Technology (I2ITCON) (pp. 1–7). IEEE.
12. Kumar Adabala, P. (2021). Optimizing ERP modernization: A smart data migration framework approach. International Journal of Enhanced Research in Science, Technology &Amp, 61–72.
13. 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.
14. Vayyasi, N. K. (2020). Decoding token volatility patterns with generative models deployed on cloud-native Java environments. International Journal of Engineering & Extended Technologies Research (IJEETR), 2(4), 1552–1565.
15. Kale, P. (2023). A federated learning approach to distributed DevOps automation in platform engineering architectures. International Journal of AI, BigData, Computational and Management Studies, 4(4), 200–208.
16. Rohit Wadhwa. (2024). Designing event-driven enterprise systems with distributed data sharding and partitioning strategies. ISCSITR-International Journal of Computer Applications (ISCSITR-IJCA), 5(1), 22–35.
17. Raja, G. V. (2020). Metadata gets a makeover: The machine learning approach. International Journal of Computer Technology and Electronics Communication, 3(6), 2900–2903.
18. Juvvadi, R. R. (2024). Embedding ESG and carbon accounting into the financial ledger: A sub-ledger architecture for CSRD-aligned reporting. International Journal of Engineering & Extended Technologies Research (IJEETR), 6(1), 7531–7535.
19. Gujarathi, M. (2024). Monolith-to-microservices migration in enterprise operations platforms: A workflow-oriented architecture. International Journal of Research Publications in Engineering, Technology and Management, 7(1), 10018–10029.
20. Polamreddy, V. R. (2022). Architectural patterns for progressive enterprise platform transformation through controlled data synchronization. International Journal of Science, Research and Technology (IJSRAT), 5(1), 7164–7167.
21. Rajula, A. (2022). Cloud-based virtual patient engagement with intelligent scheduling and secure document management. International Journal of Future Innovative Science and Technology, 5(5), 9233–9245.
22. Alex Roney Mathew. (2019). Malware analysis of API calls using FPGA hardware level security. International Journal for Research in Applied Science & Engineering Technology, 7(3), 898–900.
23. Chaganti, S. (2022, November). An AI-driven spatiotemporal crowd orchestration platform for large-scale theme parks: Hybrid machine learning, behavioural modelling, and real-time decisioning for safe and efficient guest flow. International Journal on Recent and Innovation Trends in Computing and Communication, 10(11), 275–283.
24. Vasa, M. R. (2025). Cloud-oriented deep learning models for smart healthcare automation and predictive risk analytics. International Journal of Future Innovative Science and Technology (IJFIST), 8(4), 15306.
25. Umasankar, P., & Saravanan, K. (2016). Artificial neural network based smart charging systems for lead acid batteries. Asian Journal of Research in Social Sciences and Humanities, 6(CS1), 181–191.
26. Gopisetty, S. (2024). When healthcare lags, banking leaks: A generative AI framework to stop time-based data spills in cross-sector federated learning. International Journal of AI, BigData, Computational and Management Studies, 5(4), 238–260.
27. 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.
28. Meesala, A. (2025). An enterprise-scale retrieval-augmented generative intelligence platform for real-time financial document synthesis and regulatory compliance automation. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(1), 293–299.
29. Meesala, L. K. (2022). Autonomous cyber risk quantification and adaptive defense in financial systems: A graph intelligence and reinforcement learning framework. World Journal of Advanced Research and Reviews, 16(3), 1489–1496.
30. Sudhan, S. K. H. H., & Kumar, S. S. (2015). An innovative proposal for secure cloud authentication using encrypted biometric authentication scheme. Indian Journal of Science and Technology, 8(35), 1–5.
31. Anbazhagan, R. S. K. (2016). A proficient two level security contrivances for storing data in cloud.