Optimizing Cloud Resource Allocation Through Deep Reinforcement Learning and Predictive Scheduling
Main Article Content
Abstract
Cloud computing has become an essential technology for delivering scalable, flexible, and cost-effective computing services. However, the increasing demand for cloud resources creates significant challenges in resource allocation, workload management, energy consumption, and service quality. Traditional resource allocation techniques often rely on static rules and predefined scheduling policies, which may not efficiently respond to dynamic workload variations. This research proposes an intelligent cloud resource allocation framework using Deep Reinforcement Learning (DRL) and predictive scheduling to improve resource utilization, reduce operational costs, and maintain Quality of Service (QoS). The proposed approach integrates workload prediction models with DRL algorithms to dynamically allocate computational resources, including CPU, memory, storage, and network bandwidth. Predictive scheduling estimates future resource requirements using historical workload patterns, while DRL continuously learns optimal allocation strategies through interactions with the cloud environment. The framework considers multiple performance indicators, such as resource utilization, task completion time, response time, energy consumption, and service-level agreement violations. A simulation-based experimental approach is proposed to evaluate the performance of the framework against conventional scheduling and resource allocation algorithms. The expected outcomes include improved resource efficiency, reduced task execution delays, lower energy consumption, and enhanced adaptability to changing cloud workloads. This research aims to establish an intelligent and scalable resource management strategy for modern cloud computing environments.
Article Details
Section
How to Cite
References
1. Hu, P., Dhelim, S., Ning, H., & Qiu, T. (2017). Survey on fog computing: Architecture, key technologies, applications and open issues. Journal of Network and Computer Applications, 98, 27–42. https://doi.org/10.1016/j.jnca.2017.09.002
2. Reddy, K. V. (2022). Power-aware verification closure using AI-enhanced UVM and dynamic voltage and frequency scaling models. International Journal of Research and Applied Innovations, 5(4), 7424–7436.
3. Gadige, C. D. (2023). Scalable CRM workflow automation for high-volume customer onboarding: An event-driven Salesforce architecture. The Eastasouth Journal of Information System and Computer Science, 1 (1), 253–265.
4. Kannan, K. S., Sunitha, G., Deepa, S. N., Babu, D. V., & Avanija, J. (2022). A multi-objective load balancing and power minimization in cloud using bio-inspired algorithms. Computers and Electrical Engineering, 102, 108225.
5. Shewale, V. (2022). IT/OT convergence: A zero trust architecture for energy sector. American International Journal of Computer Science and Technology, 4(5), 52–60. https://doi.org/10.63282/3117-5481/AIJCST-V4I5P106
6. Kommineni, R. (2023). Hub-and-spoke GitOps delivery for multi-tenant SaaS: Multi-source applications, deterministic environment isolation, and run-once lifecycle tasks. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 6(2), 8401–8408.
7. Bitragunta, S. L. V. (2022). High level modeling of high-voltage gallium nitride (GaN) power devices for sophisticated power electronics applications. Journal of Artificial Intelligence, Machine Learning and Data Science, 1(1), 2011-2015.
8. Potdar, A. (2022). Hybrid Sovereign Cloud Framework for Artificial Intelligence Powered Enterprise Analytics and Secure Data Integration. International Journal of Future Innovative Science and Technology (IJFIST), 5(5), 9265.
9. Neela, S. (2022). Semantic Interoperability in Real-Time Enterprise Integration Using Middleware Abstractions. American International Journal of Computer Science and Technology, 4(6), 56-66.
10. Basavala, S. R. (2022). Security assessment framework for microservices-based applications using automated penetration testing. International Journal of Humanities and Information Technology, 4(1–3), 327–341.
11. Kalakoti, M. K. R. (2023). AI-driven infrastructure orchestration for large-scale e-commerce platforms during global product launches. International Journal of Computer Technology and Electronics Communication, 6(4), 7388–7399.
12. Badam, L. R. (2022). Machine learning-based catastrophic loss prediction for climate-related insurance risk. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 5(1), 6230-6240.
13. Namdeo, A. (2023). Generative synthetic data pipelines for balanced BI training. International Journal of Emerging Research in Engineering and Technology, 4(1), 228–235. https://doi.org/10.63282/3050-922X.IJERET-V4I1P124
14. Karuturi, Y. (2023). Energy-aware capacity governance for large-scale SAP HANA deployments. International Journal of Research and Applied Innovations, 6(3), 6000–6009.
15. Jinna, K. R., & Thilagaraj, S. V. (2022). From application server to pod: A readiness-scoring framework for migrating legacy J2EE middleware workloads to enterprise Kubernetes platforms. International Journal of Engineering & Extended Technologies Research (IJEETR), 4(3), 4953-4963.
16. Nunnaguppala, L. S. C., Sayyaparaju, K. K., & Padamati, J. R. (2021). Securing The Cloud: Automating Threat Detection with SIEM, Artificial Intelligence & Machine Learning", International Journal For Advanced Research In. Science & Technology, 11(3), 385.
17. Bellundagi, M. (2023). Blockchain based secure data sharing framework for smart applications. International Journal of Humanities and Information Technology, 5(2), 95–109.
18. Shaik, N. (2022). Engineering global resilience: Multi-cluster Istio for zero-downtime traffic management. International Journal of Computer Technology and Electronics Communication, 5(5), 5813–5825.
19. Basavala, S. R. (2023). Enterprise application security governance through continuous compliance monitoring and risk assessment. International Journal of Engineering & Extended Technologies Research, 5(4), 6942–6952.
20. Rosenthal, A., Mork, P., Li, M. H., Stanford, J., Koester, D., & Reynolds, P. (2010). Cloud computing: A new business paradigm for biomedical information sharing. Journal of Biomedical Informatics, 43(2), 342–353. https://doi.org/10.1016/j.jbi.2009.08.014