Autonomous Cloud Management Systems Using Reinforcement Learning and Predictive Analytics for Proactive Resource Provisioning
Keywords:
Autonomous Cloud Management, Reinforcement Learning, Predictive Analytics, Resource Provisioning, Proactive Scaling, Cloud Computing, Workload Prediction, Dynamic Resource Allocation, Cost-Efficiency, Intelligent SystemsAbstract
The complexity of managing cloud infrastructure has led to a shift toward autonomous systems capable of making intelligent decisions without human intervention. Traditional resource provisioning strategies based on rule-based thresholds lack adaptability and responsiveness to rapidly changing workloads. As a result, service level violations and resource wastage become common in large-scale environments.
This paper explores the integration of Reinforcement Learning (RL) and Predictive Analytics (PA) to develop an intelligent, proactive cloud management framework. The proposed hybrid approach anticipates workload patterns using historical data while dynamically adjusting allocation policies through continuous learning. Comparative evaluations suggest substantial improvements in performance, cost-efficiency, and resource utilization over conventional strategies.
References
Mao, H., Alizadeh, M., Menache, I., Kandula, S. (2016). Resource management with deep reinforcement learning. In Proceedings of the ACM Workshop on Hot Topics in Networks, 50–56.
Tesauro, G., Jong, N.K. (2017). Online resource allocation using decompositional reinforcement learning. In AAAI Conference on Artificial Intelligence, 1444–1449.
Zhang, Q., Cheng, L., Boutaba, R. (2019). Cloud computing: state-of-the-art and research challenges. Journal of Internet Services and Applications, 1(1), 7–18.
Li, J., Zhang, H., Zhao, Y. (2020). Elastic resource management with deep reinforcement learning. IEEE Transactions on Cloud Computing, 8(3), 878–890.
Salehi, M., Mohammadi, S., Haghparast, M. (2021). Predictive resource provisioning using machine learning. Cluster Computing, 24, 993–1005.
Verma, A., Kaushal, S. (2020). Reinforcement learning-based elastic scaling in cloud. Journal of Supercomputing, 76(12), 9505–9530.
Chen, Y., Sato, Y., Hara, T. (2018). A survey on predicting resource usage in cloud. Future Generation Computer Systems, 79, 1071–1088.
Kumar, P., Singh, R. (2021). Hybrid prediction for workload and SLA compliance. Journal of Grid Computing, 19(1), 119–137.
Gohil, A., Patel, D. (2022). Combining ML and RL for cloud auto-scaling. Concurrency and Computation, 34(12), e6332.
Zhao, W., Li, M. (2021). LSTM-based resource forecasting in edge-cloud systems. Future Internet, 13(3), 68.
Ahmad, I., Malik, A. (2023). Federated RL for distributed cloud management. Journal of Cloud Computing, 12(1), 78–95.
Hussain, M., Anwar, Z. (2020). SLA-aware prediction in autonomous clouds. Journal of Network and Computer Applications, 152, 102534.
Patel, H., Shah, K. (2021). Adaptive autoscaling using DQN. International Journal of Cloud Applications and Computing, 11(3), 45–61.
Wang, F., Lin, M., Fu, X. (2019). Deep learning for intelligent cloud control. ACM Computing Surveys, 52(2), 1–36.
