Architecting Autonomous Cloud Platforms with AI-Driven Self-Optimization Capabilities

Article Sidebar

PDF
Published: 2024-01-10
DOI: https://doi.org/10.15662/xsawcq37
Keywords:
Cloud computing, Autonomous Systems, AI-driven optimization, machine learning, Self-healing infrastructure, Kubernetes, microservices, reinforcement learning, resource management, cloud orchestration

Main Article Content

Venkatramana Reddy Panyala
Production Engineer, Yahoo, United States of America

Abstract

It is with the introduction of sophisticated cloud computing systems that sophisticated operating environments are being built wherein intelligent automation is a must. This paper develops the architectural design of developing smart cloud platforms capable of self-optimizing using artificial intelligence methods. It is proposed that the suggested framework deployed machine learning, real-time telemetry systems, and decision engines with constraints to create smart cloud platforms capable of analyzing usage trends and re-configuring resources on-the-fly. It has a five- layer architecture, which is infrastructure layer, monitoring layer, decision making layer, actuation layer and learning layer. Theoretical study reveals that the framework has the following advantages: it reduces overheads, optimizes the use of resources, improves services, and minimizes the cost of infrastructure. The architecture is cloud native, having its foundation in reinforcement learning and other machine learning and orchestration concepts.

Article Details

Issue

Vol. 7 No. 1 (2024): International Journal of Research Publications in Engineering, Technology and Management

Section

Articles

How to Cite

Architecting Autonomous Cloud Platforms with AI-Driven Self-Optimization Capabilities. (2024). International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 7(1), 10000-10003. https://doi.org/10.15662/xsawcq37

References

[1] Optimus: An efficient dynamic resource scheduler for deep learning clusters. Proceedings of the ACM European Conference on Computer Systems (EuroSys), 2018, 3–16.

[2] Sanusi, A.N., Bayeroju, O.F. &Nwokediegwu, Z.Q.S., 2023. Framework for Leveraging Artificial Intelligence in Monitoring Environmental Impacts of Green Buildings. International Journal of Advanced Multidisciplinary Research and Studies, 3(1), pp.1194- 1203.

[3] Mao, H., Netravali, R., & Alizadeh, M. (2017). Real experience-driven network video streaming with Pensieve. Proceedings of the ACM Special Interest Group on Data Communication (SIGCOMM), 117(4), 1–14.

[4] Guneet Kaur Walia, Mohit Kumar, and Sukhpal Singh Gill. ”AI-empowered fog/edge resource management for IoT applications: A comprehensive review, research challenges and future perspectives.” IEEE Communications Surveys & Tutorials (2023).

[5] Sijing Duan, Dan Wang, Ju Ren, Feng Lyu, Ye Zhang, Huaqing Wu, and Xuemin Shen. ”Distributed artificial intelligence empowered by end-edge-cloud computing: A survey.” IEEE Communications Surveys & Tutorials 25, no. 1 (2022): 591-624.

[6] Mohit Kumar, Atul Rai, Surbhit, and Neeraj Kumar. ”Autonomic edge cloud assisted framework for heart disease prediction using RF-LRG algorithm.” Multimedia Tools and Applications 83, no. 2 (2024): 5929-5953.

[7] (32)Victor Casamayor Pujol, Praveen Kumar Donta, Andrea Morichetta, Ilir Murturi, and Schahram Dustdar. ”Edge intelligence—research opportunities for distributed computing continuum systems.” IEEE Internet Computing 27, no. 4 (2023): 53-74.

[8] Sukhpal Singh Gill and Rajkumar Buyya. 2024. Transforming Research with Quantum Computing. Journal of Economy and Technology 2 (2024), 1–8.

[9] Jolly I. Ogbole1” A Generative AI Framework for Self-Learning and Autonomous Optimization in Cloud Infrastructure Management” (IJCSMT) E-ISSN 2545-5699 P-ISSN 2695-1924 Vol 10. No. 6, 2024.

[10] Shetty, M., Singh, A., and Patel, R.,“AI-Driven Autonomous Cloud Operations Using AIOps,”arXiv preprint arXiv:2407.12165, pp. 1–12, 2024.

[11] Reddy K., Kumar, S., and Rao, P., Autonomous Cloud Systems: A Survey on Self-Managing Infrastructure,”ACM Computing Surveys, vol. 56, no. 1, pp. 1–36, 2024.

[12] Chen, X., Zhang, Y., and Liu, H.,“AI-Powered Resource Orchestration in Cloud-Native Environments,”IEEE Access, vol. 12, pp. 34567–34580, 2024.

[13] Gupta, A., Verma, S., and Yadav, N.,“Machine Learning-Based Dynamic Scaling for Microservices in Kubernetes,” Journal of Systems and Software, vol. 210, pp. 111–125, 2024.

[14] Hassan, M., and Rahman, A., “Intelligent Cloud Operations Using AIOps: Techniques and Challenges,”Future Internet, vol. 16, no. 2, pp. 1–18, 2024.

[15] Das, S., Banerjee, P., and Roy, S.,“Deep Learning for Autonomous Cloud Resource Management: Recent Advances,”IEEE Transactions on Artificial Intelligence, pp. 1–12, 2024.

[16] Mirhoseini, A., Goldie, A., Yazgan, M., Jiang, J. W., Songhori, E., Wang, S., Lee, Y.-J., Johnson, E., Pathak, O., Nazi, A., Pak, J., Tong, A., Srinivasa, K., Hang, W., Tuncer, E., Le, Q. V., Laudon, J., Ho, R., Carpenter, R., & Dean,

J. (2021). A graph placement methodology for fast chip design. Nature, 594(7862), 207–212.

[17] Burns, B., Grant, B., Oppenheimer, D., Brewer, E., & Wilkes, J. (2016). Borg, Omega, and Kubernetes: Lessons learned from three container-management systems over a decade. ACM Queue, 14(1), 70–93.

[18] Rzadca, K., Findeisen, P., Swiderski, J., Zych, P., Bronson, P., Brokowski, D., Burczynski, C., Chaiken, R., Holler, A., & Solnica, A. (2020). Autopilot: Workload autoscaling at Google. Proceedings of the ACM European Conference on Computer Systems (EuroSys), 2020, 1–16.

[19] Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. Proceedings of the IEEE International Conference on Data Mining (ICDM), 2008, 413–422.

[20] Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.