Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68981
Volume:
10 |
11 |
Nov 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Applications
D. Y. Patil Institute of MCA and Management, Akurdi Pune
Computer Applications
D. Y. Patil Institute of MCA and Management, Akurdi Pune
Computer Applications
D. Y. Patil Institute of MCA and Management, Akurdi Pune
Computer Applications
D. Y. Patil Institute of MCA and Management, Akurdi Pune
Computer Applications
D. Y. Patil Institute of MCA and Management, Akurdi Pune
Cloud applications experience fluctuating demand, requiring resource controllers to balance infrastructure cost against service performance. Reactive autoscaling changes capacity after monitored utilization crosses a threshold; predictive autoscaling attempts to provision resources before demand materializes. This paper evaluates a machine-learning-assisted autoscaling approach using a reproducible synthetic workload benchmark. A deterministic generator produces 40,000 five-minute observations with daily and weekly seasonality, autoregressive variation, noise, and burst events. Historical lag and rolling-window features support a 15-minute-ahead request-demand forecast. Persistence, Random Forest, histogram-based gradient boosting, and XGBoost are considered, with chronological train, validation, and test partitions. Across five random seeds, XGBoost obtains mean absolute error of 163.87 requests (standard deviation 1.97), root mean squared error of 208.83 (4.35), and coefficient of determination of 0.7373 (0.0086). In a separate single-seed controller replay, predictive scaling reduces normalized instance-hour cost by approximately 0.29% relative to a reactive threshold policy. However, the fraction of intervals above the 70% CPU proxy rises from 2.70% to 4.39%. These results show that forecast accuracy alone does not guarantee operational improvement. The benchmark is synthetic, cost is normalized, and CPU thresholds are not application-level service-level objectives. Real-trace validation and latency-aware queue simulation remain necessary before production conclusions can be drawn.
KEYWORDS
This paper evaluated machine-learning-assisted predictive autoscaling using a reproducible synthetic workload benchmark. A 15-minute-ahead demand forecaster was trained from calendar, lag, rolling-window, and demand-change features. Across five random seeds, XGBoost achieved mean MAE of 163.87 requests, mean RMSE of 208.83, and mean R² of 0.7373. In a separate single-seed simulation, predictive scaling reduced normalized instance-hour cost by approximately 0.29% compared with a reactive threshold controller. However, the CPU-overload proxy increased from 2.70% to 4.39%, showing that a small cost reduction can accompany a less favourable high-utilization profile. The main conclusion is that forecast quality and autoscaling effectiveness are related but distinct evaluation targets. A predictive controller must account for capacity readiness, workload uncertainty, threshold selection, and application-level service objectives. The present findings are limited to synthetic demand and a simplified CPU/cost model. They do not establish real cloud savings or latency compliance. Future work should replay the method on at least one documented public cloud trace, repeat full controller experiments across multiple seeds, include queueing and service-time distributions, report p50/p95/p99 latency and request drops, and compare against established statistical, machine-learning, Kubernetes, control-theoretic, and reinforcement-learning policies.
[1] P. Mell and T. Grance, “The NIST Definition of Cloud Computing,” NIST Special Publication 800-145, 2011. [2] M. Armbrust et al., “A View of Cloud Computing,” Communications of the ACM, vol. 53, no. 4, pp. 50–58, 2010, doi: 10.1145/1721654.1721672. [3] L. Qu et al., “A Survey of Auto-Scaling Techniques in the Cloud Computing,” ACM Computing Surveys, vol. 51, no. 3, 2018, doi: 10.1145/3148149. [4] A. Gandhi et al., “Autoscale: Dynamic, Robust Capacity Management for Multi-Tier Data Centers,” ACM Transactions on Computer Systems, vol. 30, no. 4, 2012, doi: 10.1145/2382553.2382556. [5] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proc. 22nd ACM SIGKDD, 2016, pp. 785–794, doi: 10.1145/2939672.2939785. [6] A. Verma et al., “Large-scale cluster management at Google with Borg,” in Proc. EuroSys, 2015, pp. 1–17, doi: 10.1145/2741948.2741964. [7] Y. Zheng, J. Li, and J. Zhang, “A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud,” in Proc. 28th ACM SIGKDD, 2022, pp. 4290–4299, doi: 10.1145/3534678.3539063. [8] Z. Zhou et al., “AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes,” in Proc. AAAI, vol. 37, no. 13, 2023, pp. 15621–15629, doi: 10.1609/aaai.v37i13.26852. [9] “Autoscaling Solutions for Cloud Applications Under Dynamic Workloads,” IEEE Transactions on Services Computing, vol. 17, no. 3, pp. 804–820, 2024, doi: 10.1109/TSC.2024.3354062. [10] C. Reiss et al., “Heterogeneity and Dynamicity of Clouds at Scale: Google Trace Analysis,” in Proc. ACM Symposium on Cloud Computing, 2012.
Publication Date
11/14/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...