Intelligent Resource Orchestration Using AI-Driven Predictive Algorithms for Scalable Cloud Systems
DOI:
https://doi.org/10.63282/3117-5481/AIJCST-V5I6P102Keywords:
Cloud Computing, Resource Orchestration, Artificial Intelligence, Predictive Algorithms, Reinforcement Learning, Scalability, LSTM Forecasting, Container OrchestrationAbstract
The scalability and performance of a contemporary cloud system depends on the efficient orchestration of the resources. Conventional methods of allocating resources commonly make use of a static or responsive scheduling framework, which is unable to flexibly respond to changing workloads and a multi-tenant requirement. This paper is a proposal of a predictive orchestration, an intelligent, scalable cloud environment framework, which is AI-powered. The model employs machine learning (ML) and deep learning (DL) applications to forecast future workload trends, which can supply proactive resources scaling and allocation over virtualized infrastructures. We combine time-series predictions, decision optimization through reinforcement learning, and container-based orchestration by using Kubernetes and OpenStack technologies in our model. These predictive algorithms use Long short-term memory (LSTM) networks to predict CPU, memory as well as I/O with an adaptive accuracy of 94.6%. Reinforcement learning agents extend the decision making by reducing resource wastage, and at the same time complying with service-level agreement (SLA). The high-throughput of the system is verified by simulation using Google cloud platform datasets and then it is compared with reactive and heuristic orchestration methods as the baseline. Findings indicate a 31 per cent increase in the efficiency of resource utilization and a decrease in latency of response by 26 per cent. This study indicates the possibilities of AI-oriented orchestration as a radical paradigm in cloud computing as a way of providing an elasticity, affordability, and long-term scalability to emergent data-driven ecosystems
References
[1] Beloglazov, A., Buyya, R., Lee, Y. C., & Zomaya, A. Y. (2011). A taxonomy and survey of energy-efficient data centers and cloud computing systems. Advances in Computers, 82, 47–111. https://doi.org/10.1016/B978-0-12-385512-1.00003-7
[2] Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A., & Buyya, R. (2011). CloudSim: A toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and Experience, 41(1), 23–50. https://doi.org/10.1002/spe.995
[3] Meng, X., Pappas, V., & Zhang, L. (2010). Improving the scalability of data center networks with traffic-aware virtual machine placement. In Proceedings of the IEEE INFOCOM (pp. 1–9). IEEE.
[4] Wang, L., Xu, J., & Zhao, W. (2020). Machine learning-based auto-scaling for cloud resource management using regression models. IEEE Transactions on Cloud Computing, 8(4), 1032–1045. https://doi.org/10.1109/TCC.2020.2968312
[5] Zhang, Q., Hsu, C. H., & Wang, S. (2021). Deep learning for resource demand prediction in cloud environments. Future Generation Computer Systems, 115, 590–602. https://doi.org/10.1016/j.future.2020.10.034
[6] Li, Y., Chen, X., & Liu, Z. (2022). Energy-aware cloud resource management using Deep Q-Networks. Journal of Network and Computer Applications, 202, 103382. https://doi.org/10.1016/j.jnca.2022.103382
[7] Mao, H., Alizadeh, M., Menache, I., & Kandula, S. (2016). Resource management with deep reinforcement learning. In Proceedings of the 15th ACM Workshop on Hot Topics in Networks (pp. 50–56). ACM.
[8] Xu, J., Zhao, W., & Wang, L. (2019). Intelligent cloud resource orchestration: A machine learning perspective. IEEE Access, 7, 116386–116399. https://doi.org/10.1109/ACCESS.2019.2935654
[9] Kaur, T., & Chana, I. (2015). Energy aware scheduling of deadline-constrained tasks in cloud computing: A heuristic-based approach. Journal of Cloud Computing, 4(1), 1–20. https://doi.org/10.1186/s13677-015-0030-0
[10] Roy, N., Dubey, A., & Gokhale, A. (2018). Efficient autoscaling in the cloud using predictive models for workload forecasting. IEEE International Conference on Cloud Computing (pp. 321–328). IEEE.
[11] Abhishek, S., Singh, P., & Sahoo, J. (2021). Hybrid LSTM–CNN models for workload prediction in cloud data centers. IEEE Transactions on Parallel and Distributed Systems, 32(9), 2285–2296.
[12] Zheng, Z., & Li, M. (2020). A hybrid deep learning approach for dynamic resource orchestration in multi-cloud environments. Future Internet, 12(8), 132. https://doi.org/10.3390/fi12080132
[13] Ghrada, N., Kessaci, Y., & Melab, N. (2022). A reinforcement learning-based framework for adaptive resource allocation in cloud computing. Concurrency and Computation: Practice and Experience, 34(10), e6852. https://doi.org/10.1002/cpe.6852
[14] Zhang, Y., Qiu, M., Tsai, C. W., Hassan, M. M., & Alamri, A. (2017). Health-CPS: Healthcare cyber-physical system assisted by cloud and big data. IEEE Systems Journal, 11(1), 88–95. https://doi.org/10.1109/JSYST.2015.2470662
[15] Buyya, R., & Dastjerdi, A. V. (2016). Internet of Things: Principles and paradigms. Morgan Kaufmann.
[16] Enabling Mission-Critical Communication via VoLTE for Public Safety Networks - Varinder Kumar Sharma - IJAIDR Volume 10, Issue 1, January-June 2019. DOI 10.71097/IJAIDR.v10.i1.1539
[17] Thallam, N. S. T. (2020). The Evolution of Big Data Workflows: From On-Premise Hadoop to Cloud-Based Architectures.
[18] The Role of Zero-Emission Telecom Infrastructure in Sustainable Network Modernization - Varinder Kumar Sharma - IJFMR Volume 2, Issue 5, September-October 2020. https://doi.org/10.36948/ijfmr.2020.v02i05.54991
[19] Security and Threat Mitigation in 5G Core and RAN Networks - Varinder Kumar Sharma - IJFMR Volume 3, Issue 5, September-October 2021. DOI: https://doi.org/10.36948/ijfmr.2021.v03i05.54992
[20] Thallam, N. S. T. (2021). Privacy-Preserving Data Analytics in the Cloud: Leveraging Homomorphic Encryption for Big Data Security. Journal of Scientific and Engineering Research, 8(12), 331-337.
[21] Kulasekhara Reddy Kotte. 2022. ACCOUNTS PAYABLE AND SUPPLIER RELATIONSHIPS: OPTIMIZING PAYMENT CYCLES TO ENHANCE VENDOR PARTNERSHIPS. International Journal of Advances in Engineering Research , 24(6), PP – 14-24, https://www.ijaer.com/admin/upload/02%20Kulasekhara%20Reddy%20Kotte%2001468.pdf
[22] Arpit Garg. (2022). Behavioral biometrics for IoT security: A machine learning framework for smart homes. Journal of Recent Trends in Computer Science and Engineering, 10(2), 71–92. https://doi.org/10.70589/JRTCSE.2022.2.7
[23] Naga Surya Teja Thallam. (2022). Cost Optimization in Large-Scale Multi-Cloud Deployments: Lessons from Real-World Applications. International Journal of Scientific research in Engineering and Management, 6(9).
[24] Cloud-Native 5G Deployments: Kubernetes and Microservices in Telco Networks - Varinder Kumar Sharma - IJIRMPS Volume 10, Issue 3, May-June 2022. DOI:https://doi.org/10.37082/IJIRMPS.v10.i3.232706
[25] Kanji, R. K. (2022). A Unified Data Warehouse Architecture for Multi-Source Forest Inventory Integration and Automated Remote Sensing Analysis. Sarcouncil Journal of Engineering and Computer Sciences, 1, 10-16.
[26] Gopi Chand Vegineni. 2022. Intelligent UI Designs for State Government Applications: Fostering Inclusion without AI and ML, Journal of Advances in Developmental Research, 13(1), PP – 1-13, https://www.ijaidr.com/research-paper.php?id=1454
