Optimizing AWS Cloud Resource Management: Predicting EC2 Instance CPU Utilization using LSTM and ARIMA Models

Article Sidebar

PDF
DOI: https://doi.org/10.28924/2291-8639-23-2025-261
Published: Oct 29, 2025
Cite as:
Hanita Daud, Nazleeni Samiha Haron, Nor Farisha M Krishnan, Sieow Yeek Tan, Mohd Amirul Faiz Abdul Wahab, Ahmad Amirul Adlan Azhar, Anis Zahirah Zubir, Sofea Balqis Sri Emirlee, Diaa S. Metwally, Ahmad Abubakar Suleiman, Optimizing AWS Cloud Resource Management: Predicting EC2 Instance CPU Utilization using LSTM and ARIMA Models, Int. J. Anal. Appl., 23 (2025), 261.

Main Article Content

Hanita Daud, Nazleeni Samiha Haron, Nor Farisha M Krishnan, Sieow Yeek Tan, Mohd Amirul Faiz Abdul Wahab, Ahmad Amirul Adlan Azhar, Anis Zahirah Zubir, Sofea Balqis Sri Emirlee, Diaa S. Metwally, Ahmad Abubakar Suleiman

Abstract

Amazon Web Services (AWS) Elastic Compute Cloud (EC2) instances offer scalable computing resources crucial for various applications. Accurate prediction of CPU utilization is essential for efficient resource management and cost optimization in cloud environments. This study investigates the performance of machine learning models, specifically Long Short-Term Memory (LSTM) networks and AutoRegressive Integrated Moving Average (ARIMA) models, for forecasting CPU utilization of AWS EC2 instances in both development and production environments. By employing historical data from both environments, the research aims to extend predictive horizons and improve forecasting accuracy. We evaluate and compare model performance using Mean Squared Error (MSE) and fitting times. Results reveal that ARIMA models consistently outperform LSTM models in terms of MSE and computational efficiency, demonstrating superior performance in both environments. LSTM models, despite their potential, show higher variability and longer fitting times, especially with hyperparameter tuning. This paper highlights the critical role of model selection and tuning in enhancing forecasting capabilities and operational efficiency in cloud resource management. The findings contribute valuable insights for optimizing resource allocation and cost management in AWS cloud services.

Article Details

References

  1. P.P. Ray, An Introduction to Dew Computing: Definition, Concept and Implications, IEEE Access 6 (2018), 723-737. https://doi.org/10.1109/access.2017.2775042.
  2. S. Goyal, Public Vs Private Vs Hybrid Vs Community - Cloud Computing: A Critical Review, Int. J. Comput. Netw. Inf. Secur. 6 (2014), 20-29. https://doi.org/10.5815/ijcnis.2014.03.03.
  3. A. Suleiman, A. Usman, H. Daud, F.A. Idris, R. Sokkalingam, et al., A Voting Regressor Ensemble Model for Crude Oil Price Prediction, J. Stat. Sci. Comput. Intell. 1 (2025), 61-72. https://doi.org/10.64497/jssci.4.
  4. U. Danjuma Maiwada, R. Yusuf Zakari, A.A. Janisar, Distribution Function-Driven Handover Solutions for 5g Mobile Networks, J. Stat. Sci. Comput. Intell. 1 (2025), 46-60. https://doi.org/10.64497/jssci.1.
  5. A.A. Suleiman, H. Daud, N.S.S. Singh, M. Othman, A.I. Ishaq, et al., A Novel Odd Beta Prime-Logistic Distribution: Desirable Mathematical Properties and Applications to Engineering and Environmental Data, Sustainability 15 (2023), 10239. https://doi.org/10.3390/su151310239.
  6. J. George, Comparing Scalable Serverless Analytics Architecture on Amazon Web Services and Google Cloud, Int. J. Nov. Res. Dev. 9 (2024), a689-a696.
  7. M. Zubair, A.A. Suleiman, A.K. Yousafzai, T. Alazemi, Prediction of Oxide Glass Refractive Index Using a Novel Deep Learning Architecture, Dualnet (U-Net and ANN) with Hybrid Loss Function, Opt. Quantum Electron. 57 (2025), 387. https://doi.org/10.1007/s11082-025-08300-2.
  8. S. Nabi, M. Ibrahim, J.M. Jimenez, DRALBA: Dynamic and Resource Aware Load Balanced Scheduling Approach for Cloud Computing, IEEE Access 9 (2021), 61283-61297. https://doi.org/10.1109/access.2021.3074145.
  9. M. Zubair, H.B. Rais, F. Ullah, A.A. Suleiman, Enhancing Image Reconstruction Fidelity in Low-Dose CT Scans: A Comprehensive MPS-UNet Framework, in: Lecture Notes in Electrical Engineering, Springer Nature Singapore, Singapore, 2025: pp. 59-70. https://doi.org/10.1007/978-981-96-5848-0_6.
  10. A.I. Ishaq, A.U. Usman, H.N. Alqifari, A. Almohaimeed, H. Daud, et al., A New Log-Lomax Distribution, Properties, Stock Price, and Heart Attack Predictions Using Machine Learning Techniques, AIMS Math. 10 (2025), 12761-12807. https://doi.org/10.3934/math.2025575.
  11. L.C. George, Y. Guo, D. Stepanov, V.K. Reddy Peri, et al., Usage Visualisation for the AWS Services, Procedia Comput. Sci. 176 (2020), 3710-3717. https://doi.org/10.1016/j.procs.2020.09.016.
  12. G.A.G. Mireles, M.A. Moraga, F. Garcia, M. Piattini, A Classification Approach of Sustainability Aware Requirements Methods, in: 2017 12th Iberian Conference on Information Systems and Technologies (CISTI), IEEE, 2017, pp. 1-6. https://doi.org/10.23919/cisti.2017.7975813.
  13. A.A. Suleiman, H. Daud, A.G. Usman, S.I. Abba, M. Othman, et al., A New Two-Parameter Half-Logistic Distribution with Numerical Analysis and Applications, J. Stat. Sci. Comput. Intell. 1 (2025), 1-28. https://doi.org/10.64497/jssci.2.
  14. A.G. Usman, S. Mati, H. Daud, A.A. Suleiman, S.I. Abba, et al., Optimized Svr with Nature-Inspired Algorithms for Environmental Modelling of Mycotoxins in Food Virtual-Water Samples, Sci. Rep. 15 (2025), 16569. https://doi.org/10.1038/s41598-025-99908-7.
  15. A.A. Suleiman, H. Daud, A.I. Ishaq, N.S.S. Singh, D.S. Metwally, et al., An Extension of the Gompertz Distribution for Modeling Covid-19 Mortality Dynamics, Int. J. Anal. Appl. 23 (2025), 206. https://doi.org/10.28924/2291-8639-23-2025-206.
  16. A.A. Suleiman, H. Daud, A.I. Ishaq, A.U. Farouk, A.S. Mohammed, et al., A New Statistical Model for Advanced Modeling of Cancer Disease Data, Kuwait J. Sci. 52 (2025), 100429. https://doi.org/10.1016/j.kjs.2025.100429.
  17. U. Panitanarak, A. Ismail Ishaq, A. Adewole Abiodun, H. Daud, A. Abubakar Suleiman, A New Maxwell-Log Logistic Distribution and Its Applications for Mortality Rate Data, J. Niger. Soc. Phys. Sci. (2025), 1976. https://doi.org/10.46481/jnsps.2025.1976.
  18. U. Panitanarak, A.I. Ishaq, N.S.S. Singh, A. Usman, A.U. Usman, et al., Machine Learning Models in Predicting Failure Times Data Using a Novel Version of the Maxwell Model, Eur. J. Stat. 5 (2025), 1. https://doi.org/10.28924/ada/stat.5.1.
  19. A.A. Suleiman, H. Daud, A.I. Ishaq, M. Othman, H.M. Alshanbari, et al., A Novel Extended Kumaraswamy Distribution and Its Application to COVID‐19 Data, Eng. Rep. 6 (2024), e12967. https://doi.org/10.1002/eng2.12967.
  20. M. Duggan, K. Mason, J. Duggan, E. Howley, E. Barrett, Predicting Host CPU Utilization in Cloud Computing Using Recurrent Neural Networks, in: 2017 12th International Conference for Internet Technology and Secured Transactions (ICITST), IEEE, 2017, pp. 67-72. https://doi.org/10.23919/icitst.2017.8356348.
  21. U. Panitanarak, A.I. Ishaq, A.A. Suleiman, H. Daud, N.S.S. Singh, et al., A New Beta Distribution with Interdisciplinary Data Analysis, AIMS Math. 10 (2025), 8495-8527. https://doi.org/10.3934/math.2025391.
  22. S.S. Panwar, M.M.S. Rauthan, V. Barthwal, A Systematic Review on Effective Energy Utilization Management Strategies in Cloud Data Centers, J. Cloud Comput. 11 (2022), 95. https://doi.org/10.1186/s13677-022-00368-5.
  23. H. Daud, A.S. Mohammed, A.I. Ishaq, B. Abba, Y. Zakari, et al., Modeling and Prediction of Exchange Rates Using Topp-Leone Burr Type X, Machine Learning and Deep Learning Models, Eur. J. Stat. 4 (2024), 11. https://doi.org/10.28924/ada/stat.4.11.
  24. Praveen Borra, Advancing Artificial Intelligence with Aws Machine Learning: A Comprehensive Overview, Int. J. Adv. Res. Sci. Commun. Technol. 4 (2024), 71-78. https://doi.org/10.48175/ijarsct-18810.
  25. M. Balaji, C. Aswani Kumar, G.S.V. Rao, Predictive Cloud Resource Management Framework for Enterprise Workloads, J. King Saud Univ. - Comput. Inf. Sci. 30 (2018), 404-415. https://doi.org/10.1016/j.jksuci.2016.10.005.
  26. L.M. Kaufman, Data Security in the World of Cloud Computing, IEEE Secur. Priv. Mag. 7 (2009), 61-64. https://doi.org/10.1109/msp.2009.87.
  27. A. Ates, K. Suppayah, Disciplined Innovation: A Case Study of the Amazon Working Backwards Approach to Internal Corporate Venturing, Res. Manag. 67 (2024), 23-33. https://doi.org/10.1080/08956308.2024.2326805.
  28. N. Preetham, S. Chhetri, S.R. Kini, G.G. Mishra, S. Kumar, Resource Provisioning in Cloud Using Arima and LSTM Technique, in: 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), IEEE, 2022, pp. 1-7. https://doi.org/10.1109/mysurucon55714.2022.9972689.
  29. T. Nguyen, T. Do, K. Le, S. Go, S. Na, et al., An Lstm-Based Approach for Predicting Resource Utilization in Cloud Computing, in: The 11th International Symposium on Information and Communication Technology, ACM, New York, NY, USA, 2022, pp. 173-179. https://doi.org/10.1145/3568562.3568647.
  30. P. Osypanka, P. Nawrocki, Resource Usage Cost Optimization in Cloud Computing Using Machine Learning, IEEE Trans. Cloud Comput. 10 (2022), 2079-2089. https://doi.org/10.1109/tcc.2020.3015769.
  31. Y. Yu, Y. Jia, M.A. Alshahrani, O.A. Alamri, H. Daud, et al., Adopting a New Sine-Induced Statistical Model and Deep Learning Methods for the Empirical Exploration of the Music and Reliability Data, Alex. Eng. J. 104 (2024), 396-408. https://doi.org/10.1016/j.aej.2024.07.104.
  32. A.A. Suleiman, A.K. Yousafzai, M. Zubair, Comparative Analysis of Machine Learning and Deep Learning Models for Groundwater Potability Classification, 4th Int. Electron. Conf. Appl. Sci. (2023), 249. https://doi.org/10.3390/asec2023-15506.
  33. A.I. Ishaq, A.A. Abiodun, A.A. Suleiman, A. Usman, A.S. Mohammed, et al., Modelling Nigerian Inflation Rates from January 2003 to June 2023 Using Newly Developed Inverse Power Chi-Square Distribution, in: 2023 4th International Conference on Data Analytics for Business and Industry (ICDABI), IEEE, 2023, pp. 644-651. https://doi.org/10.1109/icdabi60145.2023.10629442.
  34. S.F. Salleh, A.A. Suleiman, H. Daud, M. Othman, R. Sokkalingam, et al., Tropically Adapted Passive Building: A Descriptive-Analytical Approach Using Multiple Linear Regression and Probability Models to Predict Indoor Temperature, Sustainability 15 (2023), 13647. https://doi.org/10.3390/su151813647.
  35. A.A. Suleiman, H. Daud, M. Othman, A. Husin, A.I. Ishaq, et al., Forecasting the Southeast Asian Currencies Against the British Pound Sterling Using Probability Distributions, Data Sci. Insights 1 (2023), 31-51. https://doi.org/10.63017/jdsi.v1i1.5.
  36. A.A. Suleiman, M. Othman, H. Daud, M.L. Abdullah, E.A. Kadir, et al., Forecasting the Volatility of Real Residential Property Prices in Malaysia: A Comparison of Garch Models, Real Estate Manag. Valuat. 31 (2023), 20-31. https://doi.org/10.2478/remav-2023-0018.
  37. M. Othman, R. Indawati, A.A. Suleiman, M.B. Qomaruddin, R. Sokkalingam, Model Forecasting Development for Dengue Fever Incidence in Surabaya City Using Time Series Analysis, Processes 10 (2022), 2454. https://doi.org/10.3390/pr10112454.
  38. A.A. Suleiman, A. Suleiman, U.A. Abdullahi, S.A. Suleiman, Estimation of the Case Fatality Rate of COVID-19 Epidemiological Data in Nigeria Using Statistical Regression Analysis, Biosaf. Health 3 (2021), 4-7. https://doi.org/10.1016/j.bsheal.2020.09.003.
  39. D. Janardhanan, E. Barrett, CPU Workload Forecasting of Machines in Data Centers Using LSTM Recurrent Neural Networks and ARIMA Models, in: 2017 12th International Conference for Internet Technology and Secured Transactions (ICITST), IEEE, 2017. https://doi.org/10.23919/icitst.2017.8356346.
  40. X. Le, H.V. Ho, G. Lee, S. Jung, Application of Long Short-Term Memory (lstm) Neural Network for Flood Forecasting, Water 11 (2019), 1387. https://doi.org/10.3390/w11071387.
  41. X. Le, H.V. Ho, G. Lee, S. Jung, Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting, Water 11 (2019), 1387. https://doi.org/10.3390/w11071387.
  42. S. Phawandee, N. Sangurai, N. Putpuek, N. Cooharojananone, A Comparative Analysis of Deep Learning Approaches for Fire Hotspots Prediction in Thailand, in: 2024 23rd International Symposium on Communications and Information Technologies (ISCIT), IEEE, 2024, pp. 134-139. https://doi.org/10.1109/ISCIT63075.2024.10793656.
  43. M. Ayitey Junior, P. Appiahene, O. Appiah, Forex Market Forecasting with Two-Layer Stacked Long Short-Term Memory Neural Network (LSTM) and Correlation Analysis, J. Electr. Syst. Inf. Technol. 9 (2022), 14. https://doi.org/10.1186/s43067-022-00054-1.
  44. H. Alibrahim, S.A. Ludwig, Hyperparameter Optimization: Comparing Genetic Algorithm Against Grid Search and Bayesian Optimization, in: 2021 IEEE Congress on Evolutionary Computation (CEC), IEEE, 2021, pp. 1551-1559. https://doi.org/10.1109/cec45853.2021.9504761.
  45. A. Nugroho, H. Suhartanto, Hyper-parameter Tuning Based on Random Search for Densenet Optimization, in: 2020 7th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), IEEE, 2020, pp. 96-99. https://doi.org/10.1109/icitacee50144.2020.9239164.