Development of an AI-Based Cloud Auto-Scaling System for Predicting and Managing Resource Demand.

Deane Brickxylle T. Sanipa Sanipa; Janred Saito Saito; Jaspreet Singh Singh; Daron Gerard Morton Morton

Authors

Deane Brickxylle T. Sanipa Sanipa student Author
Janred Author
Jaspreet Author
Daron Author

Keywords:

cloud computing, auto-scaling, artificial intelligence, machine learning, workload prediction, resource management

Abstract

Cloud applications experience changing workloads, making it necessary to adjust computing resources according to demand. Traditional auto-scaling commonly reacts to current resource usage, which may lead to delayed scaling, over-provisioning, or under-provisioning. This study proposes the development of an AI-based cloud auto-scaling system that predicts future resource demand and automatically manages cloud resources. The proposed system will use historical and real-time CPU and memory data to train an AI model for predicting future resource requirements. Its main components will include resource monitoring, data processing, AI-based prediction, scaling decisions, automatic resource scaling, and performance monitoring. The study will use a Descriptive-Developmental Research Design with a Quantitative Approach and an Agile-inspired iterative development methodology. The system will be tested through Unit Testing, Integration Testing, and User Acceptance Testing. Evaluation will consider prediction accuracy, resource utilization, scaling performance, and application performance under different workload conditions. The study aims to combine monitoring, AI prediction, and automatic scaling in one practical system that can help reduce unnecessary resource allocation while maintaining sufficient resources for changing demand.

References

Arya, T. F., Rachmadi, R. F., & Affandi, A. (2024). Cloud node auto-scaling system automation based on computing workload prediction. Jurnal RESTI, 8(5), 597–606.

https://doi.org/10.29207/resti.v8i5.5928

Chouliaras, S., & Sotiriadis, S. (2022). Auto-scaling containerized cloud applications: A workload-driven approach. Simulation Modelling

Practice 121, 102654. https://doi.org/10.1016/j.simpat.2022.102654

and Theory, Chouliaras, S., & Sotiriadis, S. (2023). An adaptive auto-scaling framework for cloud resource provisioning

Future Generation Computer Systems, 148, 173–183.

https://doi.org/10.1016/j.future.2023.05.017

Hao, H., Chu, Z., Zhu, S., Jiang, G., Wang, Y., Jiang, C., Zhang, J., Jiang, W., Xue, S., & Zhou, J.

(2023).

Continual learning in predictive autoscaling. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 4616–4622.

https://doi.org/10.1145/3583780.3615463

Khan, T., Tian, W., Zhou, G., Ilager, S., Gong, M., & Buyya, R. (2022). Machine learning (ML)centric resource management in cloud computing: A review and future directions. Journal of Network and Computer Applications, 204, 103405. https://doi.org/10.1016/j.jnca.2022.103405

Nashaat, M., Moussa, W., Rizk, R., & Saber, W. (2026). Dynamic machine learning approach for workload prediction in cloud environments. Scientific

https://doi.org/10.1038/s41598-026-40777-z

Rossi, A., Visentin, A., Carraro, D., Prestwich, S., & Brown, K. N. (2025). Forecasting workload in cloud computing: Towards uncertainty-aware predictions and transfer learning. Cluster Computing, 28, 258. https://doi.org/10.1007/s10586-024-04933-2

Suleiman, B., Alibasa, M. J., Chang, Y.-Y., & Anaissi, A. (2024). Predictive auto-scaling: LSTMbased multi-step cloud workload prediction. In Service-oriented computing – ICSOC 2023 workshops (pp. 5–16).

Springer. https://doi.org/10.1007/978-981-97-0989-2_1

Xue, S., Qu, C., Shi, X., Liao, C., Zhu, S., Tan, X., Ma, L., Wang, S., Wang, S., Hu, Y., Lei, L., Zheng, Y., Li,

J., & Zhang, J. (2022). A meta reinforcement learning approach for predictive autoscaling in the cloud. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 4290–4299.

https://doi.org/10.1145/3534678.3539063

Yekta, M., & Shahhoseini, H. S. (2023). A review on machine learning methods for workload prediction in cloud computing. 2023 13th International Conference on Computer and Knowledge Engineering (ICCKE).

https://doi.org/10.1109/ICCKE60553.2023.10326297