Dynamic Workload Placement across Multi-Clouds: AI-Driven Cost Optimization without Downtime
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P114Keywords:
Multi-Cloud, Workload Placement, AI Orchestration, Cost Optimization, Live Migration, Cloud Federation, AWS, Azure, GCP, Hybrid CloudAbstract
Dynamic workload placement across multiple cloud providers enables organizations to optimize cost, performance, and reliability. This paper proposes an AI-driven framework that continuously evaluates pricing, latency, and resource availability across providers such as AWS, Azure, and Google Cloud Platform (GCP) to determine the most cost-effective environment for each workload. The system dynamically migrates workloads between providers without downtime by using predictive analytics, live-migration containers, and federated orchestration policies. This conceptual study outlines the architecture, algorithms, and benefits of intelligent workload placement while highlighting challenges in interoperability, cost modeling, and compliance
References
[1] Rajkumar Buyya. 2009. Market-Oriented Cloud Computing: Vision, Hype, and Reality of Delivering Computing as the 5th Utility. In Proceedings of the 2009 9th IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID '09). IEEE Computer Society, USA, 1. https://doi.org/10.1109/CCGRID.2009.97
[2] Furnadzhiev, R., Shopov, M., & Kakanakov, N. (2025). Efficient Orchestration of Distributed Workloads in Multi-Region Kubernetes Cluster. Computers, 14(4), 114. https://doi.org/10.3390/computers14040114
[3] Haoyu Wang, Haiying Shen, Qi Liu, Kevin Zheng, and Jie Xu. 2020. A Reinforcement Learning Based System for Minimizing Cloud Storage Service Cost. In 49th International Conference on Parallel Processing - ICPP (ICPP '20), August 17–20, 2020
[4] Mahamedi, E., Suliman, A., & Wonders, M. (2025). A Cloud-Based Framework for Creating Scalable Machine Learning Models Predicting Building Energy Consumption from Digital Twin Data. Architecture, 5(2), 29.
[5] Duc, T. L., Nguyen, C., & Östberg, P.-O. (2025). Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications. Electronics, 14(16), 3333
[6] Karima Velasquez, David Perez Abreu, Marilia Curado, Edmundo Monteiro, Resource Orchestration in 5G and beyond: Challenges and opportunities, Computer Communications, 192, 2022.
[7] Singh, G., Singh, P., Hedabou, M., Masud, M., & Alshamrani, S. S. (2022). A Predictive Checkpoint Technique for Iterative Phase of Container Migration. Sustainability, 14(11), 6538.
