Citation :

Sneha Iyer, 2026. "Predicting Short-Term Cloud Workload Changes Using Historical Usage Patterns and Lightweight Machine Learnings" ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 3: 48-64.

Abstract :

Cloud computing platforms are now a vital tool used by businesses to host up-to-date applications; process large amounts of data; and provide users with scalable digital services. Cloud workload fluctuates often due to varying user demand; application behavior; scheduled activities; and unplanned traffic surges. Predicting accurately when a short-term increase or decrease in cloud workload will occur can assist cloud service providers to allocate resources effectively; lower operating costs; and ensure application performance. A method for predicting future cloud workload variations based on historical resource usage patterns and lightweight machine learning techniques is presented in this paper. The proposed method utilizes historical metrics (CPU utilization; memory consumption; network traffic; request frequencies; workload trends) to find repeating patterns in resource utilization and predict resource needs in the near future. Due to the need for fast predictions and low computational overhead, computationally efficient algorithms (linear regression; decision trees; lightweight time series prediction models) were selected for consideration. This method includes data preprocessing; feature selection; model training; prediction; and continuous updates to allow for dynamic resource allocation. Evaluation of the prediction accuracy of the method can be accomplished through Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). In addition to resource utilization and response times, these evaluation metrics provide operational measures. This research presents a conceptual model for implementing lightweight forecasting capabilities within existing cloud management systems. It identifies several issues related to improving resource allocation, service reliability, and overall efficiency of infrastructure.

References :

[1] Armrest, M. et al. (2010) ‘A view of cloud computing’, Communications of the ACM, 53(4), pp. 50–58.

[2] Beloglazov, A. and Buyya, R. (2012) ‘Optimal online deterministic algorithms and adaptive heuristics for energy and performance efficient dynamic consolidation of virtual machines in cloud data centers’, Concurrency and Computation: Practice and Experience, 24(13), pp. 1397–1420.

[3] Beloglazov, A., Abawajy, J. and Buyya, R. (2012) ‘Energy-aware resource allocation heuristics for efficient management of data centers for cloud computing’, Future Generation Computer Systems, 28(5), pp. 755–768.

[4] Buyya, R., Yeo, C.S., Venugopal, S., Broberg, J. and Brandic, I. (2009) ‘Cloud computing and emerging IT platforms: Vision, hype, and reality for delivering computing as the 5th utility’, Future Generation Computer Systems, 25(6), pp. 599–616.

[5] Calheiros, R.N., Ranjan, R., Beloglazov, A., De Rose, C.A.F. and Buyya, R. (2011) ‘CloudSim: A toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms’, Software: Practice and Experience, 41(1), pp. 23–50.

[6] Farahnakian, F., Liljeberg, P. and Plosila, J. (2015) ‘LiRCUP: Linear regression based CPU usage prediction algorithm for live migration of virtual machines in data centers’, 2013 IEEE 27th International Conference on Advanced Information Networking and Applications Workshops, pp. 1–6.

[7] Gao, J., Wang, H. and Shen, H. (2020) ‘Machine learning based workload prediction in cloud computing’, Proceedings of the IEEE International Conference on Computer Communications and Networks (ICCCN).

[8] Gmach, D., Rolia, J., Cherkasova, L. and Kemper, A. (2007) ‘Workload analysis and demand prediction of enterprise data center applications’, Proceedings of the 2007 IEEE International Symposium on Workload Characterization, pp. 171–180.

[9] Hu, R., Jiang, J., Liu, G. and Wang, L. (2014) ‘Efficient resources provisioning based on load forecasting in cloud’, The Scientific World Journal, 2014, Article ID 321231.

[10] Islam, S., Keung, J., Lee, K. and Liu, A. (2012) ‘Empirical prediction models for adaptive resource provisioning in the cloud’, Future Generation Computer Systems, 28(1), pp. 155–162.

[11] Kalman, R.E. (1960) ‘A new approach to linear filtering and prediction problems’, Journal of Basic Engineering, 82(1), pp. 35–45.

[12] Kaviani, M., Asghari, P. and Sabeti, M. (2026) ‘A comprehensive survey and taxonomy of workload forecasting techniques in cloud computing’, Computer Networks, 286, Article 112454.

[13] Kephart, J.O. and Chess, D.M. (2003) ‘The vision of autonomic computing’, Computer, 36(1), pp. 41–50.

[14] Kohavi, R. (1995) ‘A study of cross-validation and bootstrap for accuracy estimation and model selection’, Proceedings of the 14th International Joint Conference on Artificial Intelligence, 2, pp. 1137–1143.

[15] Makridakis, S., Spiliotis, E. and Assimakopoulos, V. (2018) ‘Statistical and machine learning forecasting methods: Concerns and ways forward’, PLoS ONE, 13(3), e0194889.

[16] Mitchell, T.M. (1997) Machine Learning. New York: McGraw-Hill.

[17] Montgomery, D.C., Jennings, C.L. and Kulahci, M. (2015) Introduction to Time Series Analysis and Forecasting. 2nd edn. Hoboken: John Wiley & Sons.

[18] NIST (2011) The NIST Definition of Cloud Computing. Special Publication 800-145. Gaithersburg, MD: National Institute of Standards and Technology.

[19] Quinlan, J.R. (1986) ‘Induction of decision trees’, Machine Learning, 1, pp. 81–106.

[20] Reiss, C., Tumanov, A., Ganger, G.R., Katz, R.H. and Kozuch, M.A. (2012) ‘Heterogeneity and dynamicity of clouds at scale: Google trace analysis’, Proceedings of the Third ACM Symposium on Cloud Computing, Article 7, pp. 1–13.

[21] Sridhar, P. and Sathiya, R.R. (2025) ‘Cloud workload forecasting via latency-aware time series clustering-based scheduling technique’, Concurrency and Computation: Practice and Experience, 37(15–17), Article e70151.

[22] Al-Sayed, M.M. (2022) ‘Workload time series cumulative prediction mechanism for cloud resources using neural machine translation technique’, Journal of Grid Computing, 20, Article 16.

[23] Vapnik, V.N. (1995) The Nature of Statistical Learning Theory. New York: Springer.

[24] Breiman, L. (2001) ‘Random forests’, Machine Learning, 45, pp. 5–32.

[25] Cortes, C. and Vapnik, V. (1995) ‘Support-vector networks’, Machine Learning, 20, pp. 273–297.

[26] Hyndman, R.J. and Athanasopoulos, G. (2021) Forecasting: Principles and Practice. 3rd edn. Melbourne: OTexts.

[27] Balaji, R. (2025) ‘Autonomous SRE: SLO-Aware Multi-Agent Root-Cause Analysis and Verified Self-Healing for Cloud-Native Systems’, ESP Journal of Engineering & Technology Advancements, 5(4), pp. 211-221. doi: 10.56472/25832646/JETA-V5I4P128.

[28] Box, G.E.P., Jenkins, G.M., Reinsel, G.C. and Ljung, G.M. (2015) Time Series Analysis: Forecasting and Control. 5th edn. Hoboken: John Wiley & Sons.

[29] Dixit, M.K. and Kumar, D. (2026) ‘Predictive workload forecasting models for energy-efficient resource provisioning in cloud data centres’, Next Research, 11, Article 102001.

[30] ‘Evaluating machine learning prediction techniques and their impact on proactive resource provisioning for cloud environments’ (2024) The Journal of Supercomputing, 80(15), pp. 21920–21951.

[31] ‘Enhancing the output of time series forecasting algorithms for cloud resource provisioning’ (2025) Future Generation Computer Systems, 170, Article 107833.

Keywords :

Cloud Computing, Workload Prediction, Machine Learning, Historical Usage Patterns, Resource Allocation, CPU Utilization, Memory Consumption, Time-Series Forecasting, Predictive Analytics, Cloud Resource Management