Citation:

Siddhesh Amrale, 2023. "Proactive Resource Utilization Prediction for Scalable Cloud Systems with Machine Learning", ESP Journal of Engineering & Technology Advancements  3(4): 166-175.

Abstract:

Cloud computing's unexpected and dynamic workload fluctuations, which have a substantial influence on system performance, operating costs, and user experience, make efficient and scalable resource management an ongoing problem. To address these challenges, this study proposes a proactive resource utilization prediction framework leveraging machine learning to enable adaptive, intelligent, and timely resource allocation in cloud environments. The framework utilizes the Microsoft Azure Traces 2017 dataset, which provides realistic telemetry data, to accurately forecast CPU usage trends. A comprehensive preprocessing pipeline—including data cleaning, feature engineering, and feature scaling—ensures high-quality input for model training and reliable predictive performance. Two proposed models, Linear Regression (LiR) and Bidirectional Long Short-Term Memory (Bi-LSTM), are employed to capture both linear patterns and complex temporal dependencies in data. For benchmarking, established comparison models—Autoregressive Neural Network, SVM, and VARGRU—are evaluated. Performance metrics include R², RMSE, MSE, and MAE. LiR achieved R² = 0.9834, RMSE = 0.0170, MSE = 0.00029, and MAE = 0.0125, while Bi-LSTM achieved R² = 0.9733, RMSE = 0.0217, MSE = 0.00047, and MAE = 0.0168, clearly outperforming the comparison models. Future work will focus on extending the framework to multiresource forecasting, incorporating memory, network, and GPU metrics, and further enhancing cost-effectiveness and adaptive scaling in large-scale cloud environments.

References:

[1] Y. C. Lee and A. Y. Zomaya, “Energy efficient utilization of resources in cloud computing systems,” J. Supercomput., vol. 60, no. 2, pp. 268-280, 2012.

[2] D. Buchaca, J. Ll. Berral, C. Wang, and A. Youssef, “Proactive container auto-scaling for cloud native machine learning services,” in 2020 IEEE 13th International Conference on Cloud Computing (CLOUD), 2020, pp. 475–479.

[3] S. Srinivasan, R. Sundaram, K. Narukulla, S. Thangavel, and S. B. Venkata Naga, “Cloud-Native Microservices Architectures: Performance, Security, and Cost Optimization Strategies,” Int. J. Emerg. Trends Comput. Sci. Inf. Technol., vol. 4, no. 1, pp. 16–24, 2023, doi: 10.63282/3050-9246.IJETCSIT-V4I1P103.

[4] B. R. Cherukuri, “Quantum machine learning: Transforming cloud-based AI solutions,” Int. J. Sci. Res. Arch., vol. 1, no. 1, pp. 110–122, 2020, doi: 10.30574/ijsra.2020.1.1.0041.

[5] T. Mehmood, S. Latif, and S. Malik, “Prediction of Cloud Computing Resource Utilization,” in 2018 15th International Conference on Smart Cities: Improving Quality of Life Using ICT and IoT, HONET-ICT 2018, 2018. doi: 10.1109/HONET.2018.8551339.

[6] V. M. L. G. Nerella, “A Database-Centric CSPM Framework for Securing Mission-Critical Cloud Workloads,” Int. J. Intell. Syst. Appl. Eng., vol. 10, no. 1, pp. 209–217, 2022.

[7] R. Tandon and D. Patel, “Evolution of Microservices Patterns for Designing HyperScalable Cloud-Native Architectures,” ESP J. Eng. Technol. Adv., vol. 1, no. 1, pp. 288–297, 2021, doi: 10.56472/25832646/JETA-V1I1P131.

[8] A. Kushwaha, P. Pathak, and S. Gupta, “Review of optimize load balancing algorithms in cloud,” Int. J. Distrib. Cloud Comput., vol. 4, no. 2, pp. 1–9, 2016.

[9] A. P. and S. Pandya, “Compliance-Driven Data Governance: A Survey on GDPR, and HIPAA in Cloud Databases,” Int. J. Curr. Eng. Technol., vol. 12, no. 6, pp. 828–836, 2022, doi: https://doi.org/10.14741/ijcet/v.12.6.18.

[10] V. K. Singh, “Lessons Learned from Large-Scale Oracle Fusion Cloud Data Migrations,” Int. J. Sci. Res., vol. 10, no. 10, pp. 1662–1666, Oct. 2021, doi: 10.21275/SR21101083620.

[11] G. Modalavalasa and S. Pillai, “Exploring Azure Security Center : A Review of Challenges and Opportunities in Cloud Security,” ESP J. Eng. Technol. Adv., vol. 2, no. 2, 2022, doi: 10.56472/25832646/JETA-V2I2P120.

[12] V. Verma, “Big Data and Cloud Databases Revolutionizing Business Intelligence,” TIJER – Int. Res. J., vol. 9, no. 1, 2022.

[13] V. M. L. G. Nerella, “Automated cross-platform database migration and high availability implementation,” Turkish J. Comput. Math. Educ., vol. 9, no. 2, pp. 823–835, 2018.

[14] S. Garg, “AI/ML driven proactive performance monitoring, resource allocation and effective cost management in saas operations,” Int. J. Core Eng. Manag., vol. 6, no. 6, 2019, [Online]. Available: https://www.ssrn.com/abstract=5267257

[15] D. R. Avresky, P. Di Sanzo, A. Pellegrini, B. Ciciani, and L. Forte, “Proactive scalability and management of resources in hybrid clouds via machine learning,” in 2015 IEEE 14th International Symposium on Network Computing and Applications, 2015, pp. 114–119.

[16] M. P. Yadav, Rohit, and D. K. Yadav, “Resource provisioning through machine learning in cloud services,” Arab. J. Sci. Eng., vol. 47, no. 2, pp. 1483–1505, 2022.

[17] M. S. Al-Asaly, M. A. Bencherif, A. Alsanad, and M. M. Hassan, “A deep learning-based resource usage prediction model for resource provisioning in an autonomic cloud computing environment,” Neural Comput. Appl., 2022, doi: 10.1007/s00521-021-06665-5.

[18] M. Cioca and I. C. Schuszter, “A System for Sustainable Usage of Computing Resources Leveraging Deep Learning Predictions,” Appl. Sci., vol. 12, no. 17, 2022, doi: 10.3390/app12178411.

[19] Anupama, K. C, Shivakumar, B. R, Nagaraja, and R, “Resource Utilization Prediction in Cloud Computing using Hybrid Model,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 4, 2021, doi: 10.14569/IJACSA.2021.0120447.

[20] P. Ntambu and S. A. Adeshina, “Machine Learning-Based Anomalies Detection in Cloud Virtual Machine Resource Usage,” in 2021 1st International Conference on Multidisciplinary Engineering and Applied Science (ICMEAS), 2021, pp. 1–6. doi: 10.1109/ICMEAS52683.2021.9692308.

[21] G. Yeung, D. Borowiec, A. Friday, R. Harper, and P. Garraghan, “Towards {GPU}utilization prediction for cloud deep learning,” in 12th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 20), 2020.

[22] L. Abdullah, H. Li, S. Al-Jamali, A. Al-Badwi, and C. Ruan, “Predicting Multi-Attribute Host Resource Utilization Using Support Vector Regression Technique,” IEEE Access, vol. 8, pp. 66048–66067, 2020, doi: 10.1109/ACCESS.2020.2984056.

[23] N. Marie-Magdelaine and T. Ahmed, “Proactive autoscaling for cloud-native applications using machine learning,” in GLOBECOM 2020-2020 IEEE Global Communications Conference, 2020, pp. 1–7.

[24] P. J. M. Ali, “Investigating the Impact of min-max data normalization on the regression performance of K-nearest neighbor with different similarity measurements,” ARO-The Sci. J. Koya Univ., vol. 10, no. 1, pp. 85–91, 2022.

[25] M. Daraghmeh, S. B. Melhem, A. Agarwal, N. Goel, and M. Zaman, “Linear and logistic regression based monitoring for resource management in cloud networks,” in 2018 IEEE 6th international conference on future internet of things and cloud (FiCloud), 2018, pp. 259–266.

[26] J. Peter, “Improving the Auto scaling mechanism in Cloud computing environment using Support Vector regression and Bi-LSTM,” Dublin, National College of Ireland, 2022.

[27] N.-M. Dang-Quang and M. Yoo, “An efficient multivariate autoscaling framework using bi-lstm for cloud computing,” Appl. Sci., vol. 12, no. 7, p. 3523, 2022.

[28] Y. Zhang, Y. Liu, X. Guo, Z. Liu, X. Zhang, and K. Liang, “A BiLSTM-Based DDoS Attack Detection Method for Edge Computing,” Energies, vol. 15, no. 21, 2022, doi: 10.3390/en15217882.

[29] P. Nehra and A. Nagaraju, “Host utilization prediction using hybrid kernel based support vector regression in cloud data centers,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 8, Part B, pp. 6481–6490, 2022, doi: https://doi.org/10.1016/j.jksuci.2021.04.011.

[30] V. Chudasama and M. Bhavsar, “A dynamic prediction for elastic resource allocation in hybrid cloud environment,” Scalable Comput., vol. 21, no. 4, pp. 661–672, 2020, doi: 10.12694:/scpe.v21i4.1805.

[31] Q. Zia Ullah, S. Hassan, and G. M. Khan, “Adaptive Resource Utilization Prediction System for Infrastructure as a Service Cloud,” Comput. Intell. Neurosci., vol. 2017, 2017, doi: 10.1155/2017/4873459.

[32] S. Banerjee, S. Roy, and S. Khatua, “Efficient resource utilization using multi-step-ahead workload prediction technique in cloud.,” J. Supercomput., vol. 77, no. 9, 2021.

[33] S. Ouhame, Y. Hadi, and A. Ullah, “An efficient forecasting approach for resource utilization in cloud data center using CNN-LSTM model,” Neural Comput. Appl., vol. 33, no. 16, pp. 10043–10055, 2021.

Keywords:

Resource Management, Machine Learning, Resource Utilization, Proactive Scaling, Resource Allocation, Cloud Computing.