Predictive Database Infrastructure Scaling Through Machine Learning–Driven Forecasting in Cloud and Enterprise Environments
DOI:
https://doi.org/10.15662/IJRAI.2020.0301005Keywords:
Predictive Scaling, Database Infrastructure, Machine Learning, Autoscaling, Capacity Planning, Cloud Databases, Time-Series Forecasting, High Availability, Workload PredictionAbstract
Modern database infrastructures operate under highly dynamic and unpredictable workloads shaped by seasonal business cycles, user interaction patterns, and the growing complexity of distributed, service-oriented application architectures. Traditional reactive autoscaling mechanisms typically driven by fixed CPU, memory, or I/O thresholds respond only after resource saturation has occurred, making them ill-suited for stateful database systems where scale-out operations incur non-trivial warm-up costs, replication lag, and consistency management overhead. As a result, reactive policies frequently lead to transient performance degradation, SLA violations, and inefficient over-provisioning during recovery periods. This paper examines predictive scaling approaches for database infrastructure using machine learning (ML), synthesizing academic research and industry implementations published between 2000 and 2019, with emphasis on time-series forecasting, probabilistic workload modeling, and hybrid policy-driven autoscaling systems deployed in production environments. By analyzing empirical studies and real-world cloud platforms, the paper proposes a conceptual framework for ML-driven predictive scaling that integrates demand forecasting, uncertainty-aware capacity planning, and database-specific operational constraints, enabling proactive resource provisioning that improves availability, optimizes cost efficiency, and enhances the operational reliability of modern stateful data platforms.
References
1. Barr, J. (2018). New – Predictive scaling for EC2, powered by machine learning. Amazon Web Services Blog. https://aws.amazon.com/blogs/aws/new-predictive-scaling-for-ec2-powered-by-machine-learning/
2. Buyya, R., Calheiros, R. N., & Li, X. (2012). Autonomic cloud computing: Open challenges and architectural elements. Proceedings of the Third International Conference of Emerging Applications of Information Technology((EAIT 2012). https://arxiv.org/abs/1209.3356
3. Gandhi, A., Harchol-Balter, M., Raghunathan, R., & Kozuch, M.A. (2012). AutoScale: Dynamic, robust capacity management for multi-tier data centers. ACM Transactions on Computer Systems, 30(4), Article 14, 1-26. https://doi.org/10.1145/2382553.2382556
4. Herbst, N. R., Kounev, S., & Reussner, R. (2013). Elasticity in cloud computing: What it is, and what it is not. Proceedings of the 10th International Conference on Autonomic Computing (ICAC), 23–27. https://www.usenix.org/system/files/conference/icac13/icac13_herbst.pdf
5. Lorido-Botran, T., Miguel-Alonso, J., & Lozano, J. A. (2014). A review of auto-scaling techniques for elastic applications in cloud environments. Journal of Grid Computing 12, 559–592. https://doi.org/10.1007/s10723-014-9314-7
6. Mell, P., & Grance, T. (2011). The NIST definition of cloud computing (NIST Special Publication 800-145). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-145
7. Roy, N., Dubey, A., & Gokhale, A. (2011). Efficient autoscaling in the cloud using predictive models for workload forecasting. Proceedings of the 2011 IEEE International Conference on Cloud Computing, 500–507. https://doi.org/10.1109/CLOUD.2011.42
8. Urgaonkar, B., Shenoy, P., Chandra, A., Goyal, P., & Wood, T. (2008). Agile dynamic provisioning of multi-tier Internet applications. ACM Transactions on Autonomous and Adaptive Systems, 3(1), Article 1, 1-39. https://doi.org/10.1145/1342171.1342172
9. Verma, A., Pedrosa, L., Korupolu, M., Oppenheimer, D., Tune, E., & Wilkes, J. (2015). Large-scale cluster management at Google with Borg. Proceedings of the Tenth European Conference on Computer Systems (EuroSys ’15), Article 18, 1-17. https://doi.org/10.1145/2741948.2741964
10. Xu, J., Zhao, M., Fortes, J., Carpenter, R., & Yousif, M. (2008). Autonomic resource management in virtualized data centers using fuzzy logic-based approaches. Cluster Computing 11, 213–227. DOI: https://doi.org/10.1007/s10586-008-0060-0
11. Xiao, Z., Song, W., & Chen, Q. (2013). Dynamic resource allocation using virtual machines for cloud computing environment (Skewness). IEEE Transactions on Parallel and Distributed Systems, 24 , Article 6, 1-11. https://www.cs.cornell.edu/~weijia/papers/Skewness.pdf
12. Zheng, Z., Zhang, Y., & Lyu, M. R. (2010). Distributed QoS evaluation for real-world web services. IEEE Transactions on Services Computing, 83-90. DOI: https://doi.org/10.1109/ICWS.2010.10
13. Arpan Gujarati, Sameh Elnikety, Yuxiong He, Kathryn S. McKinley, & Brandenburg, B.B. (2017). Swayam: Distributed autoscaling to meet SLAs of machine learning inference services with resource efficiency. Proceedings of Middleware 2017, 109-120. DOI: https://doi.org/10.1145/3135974.3135993
14. Zhu, X., Young, D., Watson, B. J., Wang, Z., Rolia, J., Singhal, S., McKee, B., Hyser, C., & Gmach, D, et al. (2008). 1000 islands: Integrated capacity and workload management for the next generation data center. Proceedings of the 2008 IEEE International Conference on Autonomic Computing, 172–181. DOI: https://doi.org/10.1109/ICAC.2008.32
15. Buyya, R., Calheiros, R. N., & Li, X. (2012). Autonomic cloud computing: Open challenges and architectural elements. Proceedings of the Distributed, Parallel, and Cluster Computing. arXiv. https://arxiv.org/abs/1209.3356
16. Sharma, U., Shenoy, P., Sahu, S., & Shaikh, A. (2011). A cost-aware elasticity provisioning system for the cloud. Proceedings of the 31st International Conference on Distributed Computing Systems (ICDCS), 559-570. DOI: https://doi.org/10.1109/ICDCS.2011.59
17. Islam, S., Keung, J., Lee, K., & Liu, A. (2012). Empirical prediction models for adaptive resource provisioning in the cloud. Future Generation Computer Systems, 28(1), 155–162. DOI: https://doi.org/10.1016/j.future.2011.05.027
18. Shen, Z., Subbiah, S., Gu, X., & Wilkes, J. (2011). CloudScale: elastic resource scaling for multi-tenant cloud systems. Proceedings of the ACM Symposium on Cloud Computing (SoCC), Article No.5, 1-14. DOI: https://doi.org/10.1145/2038916.2038921
19. Ali-Eldin, A., Tordsson, J., & Elmroth, E. (2012). An adaptive hybrid elasticity controller for cloud infrastructures. Proceedings of the IEEE Network Operations and Management Symposium (NOMS), 204–212. DOI: https://doi.org/10.1109/NOMS.2012.6211900
20. Lama, P., & Zhou, X. (2012). AROMA: Automated resource allocation and configuration of MapReduce environment in the cloud. Proceedings of the 9th International Conference on Autonomic Computing (ICAC), 63–72. DOI: https://dl.acm.org/doi/10.1145/2371536.2371547
