WASP: Workload Agent-Based Simulation Platform for Migration Recommendations in Federated Kubernetes Environments

• Andre Cunha UFCG
• Jose Lima UFCG
• Lilia Sampaio UFCG
• Giovanni Farias UFCG
• Fabio Morais UFCG

DOI: https://doi.org/10.5753/sbrc_estendido.2026.22230

Resumo

Workload migration in federated Kubernetes environments is a complex task that requires well-defined migration strategies capable of operating under dynamic system conditions and constraints to balance performance, cost, and availability. However, enforcing them directly in production may lead to performance degradation, particularly under unvalidated autonomous agent-based operation. This paper presents WASP (Workload Agent-Based Simulation Platform), a decision-support tool that enables operators to simulate agent-based migration strategies before production deployment. WASP adopts a modular architecture with monitoring, recommendation, and execution control layers, supporting configurable policies with human-in-the-loop approval.

Referências

Abdel Khaleq, A. and Ra, I. (2023). Intelligent microservices autoscaling module using reinforcement learning. Cluster Computing, 26(5):2789–2800.

Amershi, S., Cakmak, M., Knox, W., and Kulesza, T. (2014). Power to the people: The role of humans in interactive machine learning. Ai Magazine, 35:105–120.

Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., Teevan, J., Kikin-Gil, R., and Horvitz, E. (2019). Guidelines for human-ai interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI ’19, page 1–13, New York, NY, USA. Association for Computing Machinery.

Dias, T. M. R., Ferreira, L., Fevereiro, D., Rosa, L., Cordeiro, L., and Fernandes, J. F. P. (2025). Cloud-native scheduling and resource orchestration: a deep dive into ai-driven approaches. IFIP Advances in Information and Communication Technology, pages 101–114.

Docker Inc. (2025a). Docker 28.3.2. [Accessed: Apr. 16, 2026].

Docker Inc. (2025b). Docker Compose 2.36.2. [Accessed: Apr. 16, 2026].

Fawad, E. a. A. (2023). Efficient workload allocation and scheduling strategies for ai-intensive tasks in cloud infrastructures. Power System Technology, 47:82–102.

Free Software Foundation (2020). GNU Make 4.3. [Accessed: Apr. 16, 2026].

Golang (2026). Golang: Build simple, secure, scalable systems with go. [link]. [Accessed: Feb. 10, 2026].

Kamran and Nazir, B. (2018). Qos-aware vm placement and migration for hybrid cloud infrastructure. J. Supercomput., 74(9):4623–4646.

Karmada (2026). Karmada: Kubernetes armada. [link]. [Accessed: Feb. 10, 2026].

KWOK (2026). Kwok: Kubernetes without kubelet. [link]. [Accessed: Feb. 10, 2026].

Lima, J., Cunha, A., Pedroza, N. F., Sampaio, L., Farias, G., and Morais, F. (2025). Ai-driven workload migration framework for multi-cluster environments. In 2025 IEEE International Conference on Cloud Computing Technology and Science (CloudCom), pages 1–8. IEEE.

LINC-BIT (2023). K8ssim: A kubernetes cluster simulator for scheduling optimization. [link]. Accessed: Feb. 10, 2026.

Ltd., C. (2026). Ubuntu Linux. [Accessed: Apr. 16, 2026].

MongoDB (2026). Mongodb: The world’s leading modern database. [link]. [Accessed: Feb. 10, 2026].

Nedoshivina, L., Levacher, K., Fraser, K., Halimi, A., and Braghin, S. (2024). Ai-driven workload management in meta os. In Proceedings of the 1st International Workshop on MetaOS for the Cloud-Edge-IoT Continuum, MECC ’24, page 14–20, New York, NY, USA. Association for Computing Machinery.

OpenRouter (2026). Openrouter: The unified interface for llms. [link]. [Accessed: Feb. 10, 2026].

Panda, S. K. and Jana, P. K. (2015). A multi-objective task scheduling algorithm for heterogeneous multi-cloud environment. In 2015 International Conference on Electronic Design, Computer Networks Automated Verification (EDCAV), pages 82–87.

Python (2026). Python: Getting started. [link]. [Accessed: Feb. 10, 2026].

React (2026). React: The library for web and native user interfaces. [link]. [Accessed: Feb. 10, 2026].

Sanjalawe, Y., Al-E’mari, S., Salam, F., and Makhadmeh, S. N. (2025). Ai-driven job scheduling in cloud computing: a comprehensive review. Artificial Intelligence Review, 58.

Straesser, M., Haas, P., Frank, S., Hakamian, A., Hoorn, A. v., and Kounev, S. (2024). Kubernetes-in-the-loop: enriching microservice simulation through authentic container orchestration. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, pages 82–98.

Vite (2026). Vite: Next generation frontend tooling. [link]. [Accessed: Feb. 10, 2026].

Wang, b., Wang, C., Song, Y., Cao, J., Cui, X., and Zhang, L. (2020). A survey and taxonomy on workload scheduling and resource provisioning in hybrid clouds. Cluster Computing, 23.

Wen, S., Han, R., Qiu, K., Ma, X., Li, Z., Deng, H., and Liu, C. H. (2023). K8ssim: a simulation tool for kubernetes schedulers and its applications in scheduling algorithm optimization. Micromachines, 14:651.

Zhang, Q. and Boutaba, R. (2014). Dynamic workload management in heterogeneous cloud computing environments. In 2014 IEEE Network Operations and Management Symposium (NOMS), pages 1–7.