Journal of Soft Computing and Information Technology

Journal of Soft Computing and Information Technology

A Hybrid Meta-Heuristic Clustering and Deep Transfer Learning Model for Cloud Energy Consumption Prediction

Document Type : Persian Original Article

Authors
Habeeb naji Atiyah 1
behnam barzegar 2
Mohammadreza soltanaghaei 1
Hassan Falah Fakhruldeen 3
1 Department of Computer Engineering, Isf.C., Islamic Azad University, Isfahan, Iran
2 Department of Computer Engineering, Bab.C., Islamic Azad University Babol, Iran
3 Computer Techniques Engineering Department, Faculty of Information Technology, Imam Ja'afar Al sadiq University, Baghdad, Iraq
10.22034/jscit.2026.569591.2215
Abstract
Despite the popularity and availability of a wide range of cloud service providers, cloud computing faces challenges that need to be addressed. One of these challenges primarily includes the incredible energy consumption due to reasons such as the use of proper cooling systems, which is considered the biggest threat to the environment and its electricity consumption cost for cloud providers. Therefore, it is necessary to provide solutions to improve or predict energy consumption in cloud computing. Therefore, the aim of this paper is to present a hybrid approach based on optimized clustering and deep transfer learning for predicting energy load in cloud computing. The proposed method is tested on three Google Cluster datasets, European PV Load and IESO datasets and in total with five datasets, CPU usage from Google Cluster dataset; hourly load from the dataset and PV load (solar energy forecast) from the London dataset; Hourly load and consumption load price in Canadian dollars from the IESO dataset have been evaluated with MSE, RMSE, MAPE and MAE metrics. The results show that among the datasets, the Google Cluster dataset in the training data has performed very well and the errors have been at the lowest possible level (MSE = 0.0199, RMSE = 0.1411, MAPE = 0.4293 and MAE = 0.1195). In the test data, the error values also remain low and acceptable (MSE = 0.0356, RMSE = 0.1886, MAPE = 0.6460 and MAE = 0.1647), which indicates the high generalization ability of the model and increased prediction accuracy in complex and voluminous data.
Keywords
Clustering with Meta-Heuristic Algorithm
Deep Transfer Learning
Load Forecasting
Cloud Computing
[1] M. Chiregi and N. J. Navimipour, “Cloud computing and trust evaluation: A systematic literature review of the state-of-the-art mechanisms,” J. Electr. Syst. Inf. Technol., vol. 3, no. 3, pp. 608–622, 2018, doi: 10.1016/j.jesit.2017.09.001.
[2] V. K. Damera, A. Nagesh, and M. Nagaratna, “Trust evaluation models for cloud computing,” Int. J. Sci. Technol. Res., vol. 9, no. 2, pp. 1964–1971, 2020.
[3] A. Agashe, S. Pande, and R. C. Jaiswal, “A survey paper on cloud computing and migration to the cloud,” J. Emerg. Technol. Innov. Res., vol. 9, no. 10, pp. 258–265, 2022.
[4] S. S. Panwar, M. M. S. Rauthan, V. Barthwal, N. Mehra, and A. Semwal, “Machine learning approaches for efficient energy utilization in cloud data centers,” Procedia Comput. Sci., vol. 235, pp. 1782–1792, 2024, doi: 10.1016/j.procs.2024.04.169.
[5] A. Singh and K. Chatterjee, “USTrust: A user and service trust evaluation model for cloud computing environment,” Int. J. Comput. Intell. IoT, vol. 2, no. 4, pp. 771–776, 2019.
[6] A. Katal, S. Dahiya, and T. Choudhury, “Energy efficiency in cloud computing data centers: A survey on software technologies,” Cluster Comput., vol. 26, pp. 1845–1875, 2023, doi: 10.1007/s10586-022-03713-0.
[7] N. Gupta, K. Gupta, A. Singh, A. Kaur, and D. Gupta, “Cloud computing: A walk through in models, challenges, and energy solutions,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 1022, pp. 1–10, 2021, doi: 10.1088/1757-899X/1022/1/012070.
[8] A. Mosavi and A. Bahmani, “Energy consumption prediction using machine learning: A review,” Preprints, vol. 11, pp. 1–61, 2019, doi: 10.20944/preprints201903.0131.v1.
[9] S. Saxena, K. M. Zubair, R. Singh, A. Agarwal, and P. Pramanik, “Clustering-based prediction for VM workload in green computation,” Educ. Adm.: Theory Pract., vol. 30, no. 5, pp. 9657–9666, 2024, doi: 10.53555/kuey.v30i5.2585.
[10] A. A. Khan and M. Zakarya, “Energy, performance and cost efficient cloud datacentres: A survey,” Comput. Sci. Rev., vol. 40, Art. no. 100390, pp. 1–31, 2021, doi: 10.1016/j.cosrev.2021.100390.
[11] K. Zhang, W. Guo, J. Feng, and M. Liu, “Load forecasting method based on improved deep learning in cloud computing environment,” Sci. Program., pp. 1–11, 2021, doi: 10.1155/2021/3250732.
[12] A. K. Yadav and M. L. Garg, “The issues of energy efficiency in cloud computing based data centers,” Biosci. Biotechnol. Res. Commun., vol. 12, no. 2, pp. 1–10, 2019, doi: 10.21786/bbrc/12.2/35.
[13] X. Wang, H. Wang, B. Bhandari, and L. Cheng, “AI-empowered methods for smart energy consumption: A review of load forecasting, anomaly detection and demand response,” Int. J. Precis. Eng. Manuf.-Green Technol., vol. 11, pp. 963–993, 2024, doi: 10.1007/s40684-023-00537-0.
[14] J. Dogani, F. Khunjush, and M. Seydali, “Host load prediction in cloud computing with discrete wavelet transformation and bidirectional gated recurrent unit network,” Comput. Commun., vol. 198, pp. 157–174, 2023, doi: 10.1016/j.comcom.2022.11.018.
[15] A. O. Aderibigbe et al., “Enhancing energy efficiency with AI: A review of machine learning models in electricity demand forecasting,” Eng. Sci. Technol. J., vol. 4, no. 6, pp. 341–356, 2023, doi: 10.51594/estj.v4i6.636.
[16] V. K. Saini, A. S. Al-Sumaiti, and R. Kumar, “Data-driven net load uncertainty quantification for cloud energy storage management in residential microgrid,” Electr. Power Syst. Res., vol. 226, Art. no. 109920, 2024, doi: 10.1016/j.epsr.2023.109920.
[17] R. Heidarykiany and C. Ababei, “HVAC energy cost minimization in smart grids: A cloud-based demand side management approach with game theory optimization and deep learning,” Energy AI, vol. 16, Art. no. 100362, 2024, doi: 10.1016/j.egyai.2024.100362.
[18] Z. Yang, “Renewable energy management in smart grid with cloud security analysis using multi-agent machine learning model,” Comput. Electr. Eng., vol. 116, Art. no. 109177, 2024, doi: 10.1016/j.compeleceng.2024.109177.
[19] B. Predic et al., “Cloud-load forecasting via decomposition-aided attention recurrent neural network tuned by modified particle swarm optimization,” Complex Intell. Syst., vol. 10, pp. 2249–2269, 2024, doi: 10.1007/s40747-023-01265-3.
[20] P. Li and J. Cao, “Virtual machine consolidation with multi-step prediction and affinity-aware technique for energy-efficient cloud data centers,” Comput. Mater. Continua, vol. 76, no. 1, pp. 81–105, 2023, doi: 10.32604/cmc.2023.039076.
[21] A. A. Almazro and N. Ayub, “Multi-task learning for electricity price forecasting and resource management in cloud-based industrial IoT systems,” IEEE Access, vol. 11, pp. 54280–54295, 2023, doi: 10.1109/ACCESS.2023.3280857.
[22] M. Thirunavukkarasu, D. S. G. Phanish Chandra, and G. Sai Rahul, “Electricity price forecasting for cloud computing using machine learning model,” Int. J. Sci. Res. Eng. Manag., vol. 7, no. 5, pp. 1–5, 2023, doi: 10.55041/IJSREM21372.
[23] D. G. Rosero, N. L. Díaz, and C. L. Trujillo, “Cloud and machine learning experiments applied to the energy management in a microgrid cluster,” Appl. Energy, vol. 304, Art. no. 117770, 2021, doi: 10.1016/j.apenergy.2021.117770.
[24] B. Hrnjica and A. Danandeh Mehr, “Energy demand forecasting using deep learning,” in Smart Cities Performability, Cognition, & Security, 2020, pp. 71–104, doi: 10.1007/978-3-030-14718-1_4.
[25] S. Albahli, M. Shiraz, and N. Ayub, “Electricity price forecasting for cloud computing using an enhanced machine learning model,” IEEE Access, vol. 8, pp. 1–12, 2020, doi: 10.1109/ACCESS.2020.3035328.
[26] T. Deepika and P. Prakash, “Power consumption prediction in cloud data center using machine learning,” Int. J. Electr. Comput. Eng., vol. 10, no. 2, pp. 1524–1532, 2020, doi: 10.11591/ijece.v10i2.pp1524-1532.
[27] C. F. J. Wu and M. Hamada, Experiments: Planning, Analysis, and Optimization. Hoboken, NJ, USA: Wiley, 2021, doi: 10.1002/9781119470007.
[28] M. Iman, H. R. Arabnia, and K. Rasheed, “A review of deep transfer learning and recent advancements,” Technologies, vol. 11, no. 2, Art. no. 40, 2023, doi: 10.3390/technologies11020040.
[29] Q. Zhu, C. Wang, W. Jin, J. Ren, and X. Yu, “Deep transfer learning based on LSTM model for reservoir flood forecasting,” Int. J. Data Warehous. Min., vol. 20, no. 1, pp. 1–17, 2023, doi: 10.4018/IJDWM.338912.
Journal of Soft Computing and Information Technology
Volume 15, Issue 3
Autumn - October
Autumn 2026
Pages 52-72