Building a Modular AI Deployment Framework for Model Sharing Across Cloud Environments
Keywords:
AI deployment, cloud computing, model portability, Kubernetes, containerization, model orchestration, MLOpsAbstract
The proliferation of AI models across industries has spurred the need for flexible and interoperable deployment strategies that enable seamless migration and sharing across heterogeneous cloud environments. This paper proposes a modular AI deployment framework that decouples model development, packaging, and orchestration layers to ensure cloud-agnostic portability. Leveraging containerization, API standardization, and automated orchestration tools like Kubernetes, the framework supports scalable deployment with enhanced reproducibility and reduced vendor lock-in. Evaluation across AWS, Azure, and GCP environments demonstrates the framework's efficiency, adaptability, and cost-effectiveness.
References
Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., ... & Dennison, D. (2015). Hidden technical debt in machine learning systems. In Advances in Neural Information Processing Systems (pp. 2503-2511).
Subramanyam, S.V. (2019). The role of artificial intelligence in revolutionizing healthcare business process automation. International Journal of Computer Engineering and Technology (IJCET), 10(4), 88–103.
Hohpe, G. (2017). Cloud Strategy: A Decision-based Approach to a Cloud Journey. Google Cloud Whitepaper.
Liu, Y., Xie, Q., Zhang, H., & Lin, C. (2020). Containerized Machine Learning Model Deployment on Multi-cloud Platforms. Journal of Cloud Computing, 9(1), 15.
Subramanyam, S.V. (2022). AI-powered process automation: Unlocking cost efficiency and operational excellence in healthcare systems. International Journal of Advanced Research in Engineering and Technology (IJARET), 13(1), 86–102.
Zaharia, M., Chen, A., Davidson, A., Ghodsi, A., Hong, M., Konwinski, A., ... & Stoica, I. (2022). Accelerating the Machine Learning Lifecycle with MLflow. IEEE Data Engineering Bulletin, 45(1), 21–30.
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. Communications of the ACM, 59(5), 50–57.
Subramanyam, S.V. (2024). Transforming financial systems through robotic process automation and AI: The future of smart finance. International Journal of Artificial Intelligence Research and Development (IJAIRD), 2(1), 203–223.
Villamizar, M., Garcés, O., Ochoa, L., Castro, H., Verano, M., Salamanca, L., & Casallas, R. (2015). Evaluating the monolithic and the microservice architecture pattern to deploy web applications in the cloud. Proceedings of the 10th Computing Colombian Conference (10CCC), 583–590.
Subramanyam, S.V. (2023). The intersection of cloud, AI, and IoT: A pre-2021 framework for healthcare business process transformation. International Journal of Cloud Computing (IJCC), 1(1), 53–69.
Boettiger, C. (2015). An introduction to Docker for reproducible research. ACM SIGOPS Operating Systems Review, 49(1), 71–79.
Breck, E., Cai, S., Nielsen, E., Salib, M., & Sculley, D. (2017). The ML test score: A rubric for ML production readiness and technical debt reduction. Proceedings of the SysML Conference.
Miao, Y., Hu, C., Liu, D., Zhang, H., & Pan, J. (2020). Deploying AI models at scale using Kubernetes and KubeEdge. IEEE Internet Computing, 24(6), 28–37.
Bernstein, D. (2014). Containers and cloud: From LXC to Docker to Kubernetes. IEEE Cloud Computing, 1(3), 81–84.
Subramanyam, S.V. (2021). Cloud computing and business process re-engineering in financial systems: The future of digital transformation. International Journal of Information Technology and Management Information Systems (IJITMIS), 12(1), 126–143.
Bentayeb, F., Darmont, J., & Boussaïd, O. (2020). Challenges in deploying machine learning in production environments. Journal of Intelligent Information Systems, 54(3), 457–474.
Al-Ali, A., Salman, Y. A., & Al-Kabi, M. N. (2019). Towards efficient MLOps: A survey of tools and practices. International Journal of Advanced Computer Science and Applications (IJACSA), 10(6), 446–454.
Krishnan, S., Franklin, M. J., Goldberg, K., & Wu, E. (2018). ActiveClean: Interactive data cleaning for statistical modeling. Proceedings of the VLDB Endowment, 9(12), 948–959.
Raj, P., & Raman, A. (2017). The cloud-native architecture for deploying scalable AI workloads. In Demystifying Cloud Computing (pp. 123–138). Springer.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Jay Sarvesh Borole Patil (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
