A PREDICTIVE AI MODEL FOR INTELLIGENT RESOURCE ALLOCATION IN HYBRID CLOUD INFRASTRUCTURES

Paper ID: EIJTEM_2025_12_4_21-27

Author's Name: G. Priyamvada, Deepika Kumari

Volume: 12

Issue: 4

Year: 2025

Page No: 21-27

Abstract:

Cloud infrastructures that are hybrids are gaining popularity in order to strike a balance between economy of the computer enterprise, and flexibility and scalability. However, in the context of these heterogeneous environments, workload performance is a significant problem since the configuration varies, workload is heterogeneous and network conditions are also dynamic. This paper describes a predictive model on AI-based with Gradient Boosting techniques (XGBoost, LightGBM, and CatBoost) to forecast the execution time, the throughput, and resource consumption of hybrid workloads. The framework integrates the process of collecting information of containerized tasks and VM-based tasks on both public and private clouds, processes in a systematic manner in advance of acquiring resource-performance dependencies, and uses boosting models to perform precise forecasting. Exposure to experiments confirms the fact that Gradient Boosting is much more effective than classic regression, SVM, neural networks ( R 2 more than 0.92, errors of prediction (MAE and RMSE) are less by 30-40 %. Additionally, the feature importance analysis revealed that CPU allocation and request rate were dominating predictors which is helpful in scheduling a workload and satisfying the SLA. These results find Gradient Boosting to be a useful and explainable component that can be used to aid smart autoscaling and resource management in hybrid cloud environments.

Keywords: Hybrid Cloud, Performance Prediction, Gradient Boosting, XGBoost, LightGBM, CatBoost, Workload Scheduling, SLA Compliance, Resource Allocation, Cloud Computing, Machine Learning.

References:

1. T. K. Rohan, T. Padmakara and A. G, "Employee Attrition Using Gradient Boosting," 2025 8th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2025, pp. 821-825, doi: 10.1109/ICOEI65986.2025.11012971.
2. R. B. Tareaf, M. AbuJarour and F. Zinn, "Revolutionizing Credit Risk: A Deep Dive into Gradient-Boosting Techniques in AI-Driven Finance," 2024 International Conference on Information Networking (ICOIN), Ho Chi Minh City, Vietnam, 2024, pp. 322-327, doi: 10.1109/ICOIN59985.2024.10572140.
3. R. Khan, S. Akbar and T. A. Zahed, "Flight Delay Prediction Based on Gradient Boosting Ensemble Techniques," 2022 16th International Conference on Open Source Systems and Technologies (ICOSST), Lahore, Pakistan, 2022, pp. 1-5, doi: 10.1109/ICOSST57195.2022.10016828.
4. J. K.-U. Brock and F. von Wangenheim, “Demystifying AI: What Digital Transformation Leaders Can Teach You about Realistic Artificial Intelligence,” California Management Review, vol. 61, no. 4, pp. 110 - 134, 2019. Online. Available: https://doi.org/10.1177/1536504219865226.
5. Z. Tian, J. Xiao, H. Feng, and Y. Wei, “Credit Risk Assessment based on Gradient Boosting Decision Tree,” Procedia Computer Science, vol. 174, pp. 150 - 160, 2020, DOI: 10.1016/j.procs.2020.06.070.
6. D. Paschek, C. T. Luminosu, and A. Draghici, “Automated business process management - in times of digital transformation using machine learning or artificial intelligence,” MATEC Web Conf., vol. 121, p. 04007, 2017. Online. Available: https://doi.org/10.1051/matecconf/201712104007.
7. Lui and G. W. Lamb, “Artificial intelligence and augmented intelligence collaboration: regaining trust and confidence in the financial sector,” Journal Name, vol. x, no. x, pp. 267 - 283, 2018. [Online]. Available: https://doi.org/10.1080/13600834.2018.1488659.
8. Y.-C. Chang, K.-H. Chang, and G.-J. Wu, “Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions,” Applied Soft Computing, vol. 73, pp. 914 - 920, 2018, DOI: 10.1016/j.asoc.2018.09.029.
9. Y. Xia, L. He, Y. Li, Y. Fu, and Y. Xu, “A dynamic credit scoring model based on survival gradient boosting decision tree approach,” Technological and Economic Development of Economy, vol. 27, no. 1, pp. 96 - 119, 2021, DOI: 10.3846/tede.2020.13997.
10. R. B. Tareaf, P. Berger, P. Hennig, and C. Meinel, “Personality exploration system for online social networks: Facebook brands as a use case,” in 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI), Dec. 2018, pp. 301 - 309.
11. A. Howard, A. Amex, D. Xu, H. Vashani, N. Inversion, N. Negin, and S. Dane, “American Express - Default Prediction,” Kaggle, 2022, Online. Available: https://kaggle.com/competitions/amex-default-prediction.
12. L. Höbe, “The changing landscape of the financial services,” International Journal of Trade, Economics and Finance, vol. 6, no. 2, p. 145, 2015
13. Luthi, W. B. Wyckoff, and A. Cybulski, “8 biggest U.S. credit card companies this year,” US News World Report, May 02, 2023. Accessed: Sep. 20, 2023.
14. G. Ke, Q. Meng, T. Finley, T Wang, W. Chen, W. Ma, Q. Ye, and T. -Y. Liu, “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems 30 (NIPS 2017), December 2017.
15. T Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2016, pp. 785 - 794.

View PDF