Optimization of energy consumption in data centers using multiple regression models based on processing load and network metrics
DOI:
https://doi.org/10.55204/trc.v6i2.e723Keywords:
Multiple Linear Regression, data centers, energy efficiency, dynamic consolidation, causal discovery, symbolic regressionAbstract
Global digitalization has established data centers as critical infrastructure, yet their energy consumption is increasing disproportionately, posing significant sustainability challenges. The absence of physical measurement sensors in virtualized servers has driven the adoption of software-based predictive models. This study conducted a systematic review using the PRISMA protocol (2021-2026) focused on Multiple Linear Regression (MLR) models for estimating energy consumption in data centers. SNMP metrics from CPU, network, and memory were analyzed, with preprocessing steps including imputation, normalization, and mitigation of multicollinearity. Hybrid MLR models incorporating Gradient Boosting achieved a mean absolute error (MAE) of 1.46 and an R² exceeding 95%. These findings demonstrate that software models can effectively replace physical sensors, supporting dynamic virtual machine consolidation and predictive HVAC control. Future research directions include the application of Causal ML to identify the etiological origins of thermal stress, Symbolic Regression adaptable to hardware changes, and extrapolation to hybrid renewable networks in rural edge computing environments. Hybrid MLR serves as a precise substitute for physical instrumentation, reduces idle consumption to within 10% of the ideal limit, and enables proactive climate control. The integration of Causal ML and Symbolic Regression is necessary to address stochasticity in future architectures.Downloads
References
Afrianto, Y., Munadi, R., Setyorini, & Widyanto, T. (2025). Ŷ UGO: Enhancing Power Consumption Predictions in Data Centers Through Combined Multiple Linear Regression and Gradient Boosting Techniques on Hypervisor Load. IEEE Access, 13, 210025-210039. https://doi.org/10.1109/ACCESS.2025.3604711
Al-Essa, L. A. & others. (2024). Bayesian regression modeling and inference of energy efficiency data: The effect of collinearity and sensitivity analysis. Frontiers in Energy Research. https://doi.org/10.3389/fenrg.2024.1416126
Arellanos-Tafur, E., Gutierrez Rupay, H., Rojas-Arquiñego, F., & Damas-Niño, R. (2025). Impact of energy efficiency on reducing consumption in data centers with power purchase agreements (PPAs). LACCEI International Multi-Conference for Engineering, Education, and Technology. https://laccei.org/LACCEI2025-Mexico/full-papers/Contribution_2072_final_a.pdf
Bautista Sánchez, J. V. (2022). Sistema de medición en tiempo real y gestión del consumo energético de máquinas industriales mediante habilitadoras digitales de la industria 4.0.
Biehl, M. (2023). The Shallow and the Deep: A biased introduction to neural networks and old school machine learning. University of Groningen Press. https://doi.org/10.21827/648c59c1a467e
Biswas, N. Kr., Banerjee, S., Biswas, U., & Ghosh, U. (2021). An approach towards development of new linear regression prediction model for reduced energy consumption and SLA violation in the domain of green cloud computing. Sustainable Energy Technologies and Assessments, 45, 101087. https://doi.org/10.1016/j.seta.2021.101087
Cesario, E., Lindia, P., Lobello, F., Vinci, A., & Capalbo, S. (2025). Enhancing energy efficiency in cloud computing through regression models: A data-driven approach with experimental validation. Future Generation Computer Systems, 177. https://doi.org/10.1016/j.future.2025.108245
Crespo, G. & others. (2021). Modelos de regresión y diseño de línea base para indicadores energéticos en una empresa siderúrgica. Ingeniería Energética, 42(1), 1-10.
De Brito, J. L. R., Matai, P. H. L. D. S., & Dos Santos, M. R. (2023). Data Center e Eficiência Energética: Data Center and Energy Efficiency. Brazilian Journal of Business, 5(2), 786-795. https://doi.org/10.34140/bjbv5n2-002
Dudek, G. (Ed.). (2023). Applied Machine Learning. MDPI - Multidisciplinary Digital Publishing Institute. https://doi.org/10.3390/books978-3-0365-7907-8
Ennio, F. T. L., Cruz, A. R. D. L., & Rodelas, N. C. (2025). JANUS: Study and analysis of the cooling and power requirements of an NFV telecommunications data center using machine learning. En Emerging Technologies In Sustainable Innovation, Management and Development. Routledge.
Gabrielli, G., Melioli, A., & Bertini, F. (2026). Corporate financial distress prediction: A machine learning approach in the era of big data. Journal of Accounting and Organizational Change, 22(7), 31-65. https://doi.org/10.1108/JAOC-05-2025-0166
George, N., K. Anoop, B., & P. Vijayan, V. (2023). Tricube Weighted Linear Regression and Interquartile for Cloud Infrastructural Resource Optimization. Computer Systems Science and Engineering, 45(3), 2281-2297. https://doi.org/10.32604/csse.2023.028117
Georgiev, G. V., & Nanjappan, V. (2024). Predicting the Energy Consumption of Blockchain Operations: A Multiple Linear Regression Approach. Sustainability, 16(4), 1519. https://doi.org/10.3390/su16041519
Guañuna, G. F., Granda, N. V., Cepeda, J. C., Vargas, W., & Echeverría, D. E. (2023). Estimación del Margen de Estabilidad de Voltaje Utilizando Herramientas de Aprendizaje Automático. Revista Técnica “energía”, 20(1), 1-8. https://doi.org/10.37116/revistaenergia.v20.n1.2023.570
Jin, T. & others. (2023). Energy consumption prediction and optimization of data centers based on multiple linear regression. Energy Reports, 9, 150-162. https://doi.org/10.1016/j.egyr.2023.01.020
Karantoumanis, E., & Ploskas, N. (2020). Power Consumption Estimation in Data Centers Using Machine Learning Techniques (pp. 195-200). https://doi.org/10.1007/978-3-030-53552-0_20
Khan, T., Tian, W., Ilager, S., & Buyya, R. (2022). Workload forecasting and energy state estimation in cloud data centres: ML-centric approach. Future Generation Computer Systems, 128, 320-332. https://doi.org/10.1016/j.future.2021.10.019
Kim, J. H., Shin, D. U., & Kim, H. (2024). Data Center Energy Evaluation Tool Development and Analysis of Power Usage Effectiveness with Different Economizer Types in Various Climate Zones. Buildings, 14(1), 299. https://doi.org/10.3390/buildings14010299
Kumar, R., Khatri, S. K., & Diván, M. J. (2021). Power Usage Efficiency (PUE) Optimization with Counterpointing Machine Learning Techniques for Data Center Temperatures. International Journal of Mathematical, Engineering and Management Sciences, 6(6), 1594-1611. https://doi.org/10.33889/IJMEMS.2021.6.6.095
Lascano, J., Saraguro, R., Chiza, L., Astudillo, J., & Guañuna, G. (2023). Estimación de la Demanda de una Estación de Carga para Vehículos Eléctricos Mediante la Aplicación de Métodos Probabilísticos y Predictivos. Revista Técnica “energía”, 20(1), 52-64. https://doi.org/10.37116/revistaenergia.v20.n1.2023.569
Liao, X., Li, Y., Zhang, S., Wei, X., & Hu, J. (2026). Predicting GPU Training Energy Consumption in Data Centers Using Task Metadata via Symbolic Regression. Energies, 19(2), 448. https://doi.org/10.3390/en19020448
Liu, J., Fan, R., Li, Z., Harnpornchai, N., & Qian, J. (2026). Proactive Cooling Control Algorithm for Data Centers Based on LSTM-Driven Predictive Thermal Analysis. Applied System Innovation, 9(1), 21. https://doi.org/10.3390/asi9010021
Ma, H., & Ding, A. (2022). Method for evaluation on energy consumption of cloud computing data center based on deep reinforcement learning. Electric Power Systems Research, 208, 107899. https://doi.org/10.1016/j.epsr.2022.107899
Misaghian, M. S. & others. (2023). Assessment of Carbon-Aware Flexibility Measures From Data Centres Using Machine Learning. IEEE Transactions on Industry Applications, 59(1), 70-81.
Muraku, B., Haveriku, A., Deliu, A., & Mece, E. K. (2024). Data-Driven Prediction of Power Usage Effectiveness: A Machine Learning Case Study. 2024 32nd International Conference on Software, Telecommunications and Computer Networks (SoftCOM). https://doi.org/10.23919/SoftCOM62040.2024.10721988
Ortega-Díaz, L. P., Cárdenas, J., & Osma-Pinto, G. (2023). Estrategias de predicción de consumo energético en edificaciones: Una revisión. TecnoLógicas, 26(58), e2650.
Rafique, A., Yu, X., Jawad, M., Song, Q., Yuan, Z., Sadiq, M. T., Daniel, K., & Shabbir, N. (2026). Two-Stage Optimization-Learning Framework for Uncertainty-Aware Multi-Zonal Data Center Energy Management. Energies, 19(7), 1736. https://doi.org/10.3390/en19071736
Rantini, D., Najiyya, S. I., Ghani, M., Yasmirullah, S. D. P., Fahmiyah, I., Ramadan, A., Othman, F., & Alya, N. A. (2026). Understanding the Spatial Distribution of Stunting in East Java, Indonesia: A Comparison of GWR and MS-GWR Models. Statistics, Optimization and Information Computing, 15(1), 311-323. https://doi.org/10.19139/soic-2310-5070-3066
Reyes Almeida, F. J. (2021). Implementación de un algoritmo para el seguimiento del punto de potencia máxima en un panel solar mediante un control predictivo por modelo.
Tarafdar, A., Sarkar, S., Das, R. K., & Khatua, S. (2023). Power Modeling for Energy-Efficient Resource Management in a Cloud Data Center. Journal of Grid Computing, 21(1), 10. https://doi.org/10.1007/s10723-023-09642-5
Tenenaula Cunduri, M. R. (2025). Desarrollo de un software simulador basado en modelos matemáticos y machine learning para analizar y optimizar redes híbridas de energía renovable [Tesis de Posgrado, Universidad Nacional de Chimborazo (UNACH)]. http://dspace.unach.edu.ec/handle/51000/16460
Teresa Riccio Barbosa, A., & Santiago Do Nascimento Lima, R. (2025). Estratégia de eficiência energética em data centers: Revisão sistemática. Latin American Journal of Energy Research, 12(4), 73-82. https://doi.org/10.21712/lajer.2025.v12.n4.p73-82
Vergara, R. & others. (2025). Optimización del rendimiento de plantas solares en azotea mediante monitoreo IoT de bajo costo: Un estudio de caso en Montería, Colombia. Revista de Ingeniería, Matemáticas y Ciencias de la Información. http://www.scielo.org.co/scielo.php?script=sci_arttext&pid=S1909-83672025000100071
Wang, X. & others. (2023). Energy Consumption Modeling in High-Performance Computing Racks. Information Systems Research. https://doi.org/10.1287/isre.2023.1208
Wang, X., Zhou, S., Gong, Y., Liu, Y., & Liu, J. (2025). A Hierarchical Control Framework for HVAC Systems: Day-Ahead Scheduling and Real-Time Model Predictive Control Co-Optimization. Energies, 18(23), 6266. https://doi.org/10.3390/en18236266
Yan, L., & Ming, T. (2023). Analysis on the Influence Factors of Heat Dissipation of Undersea Data Center Based on Multiple Linear Regression. Procedia Comput. Sci., 228, 920-926. https://doi.org/10.1016/j.procs.2023.11.121
Zapata, D., Meyer, M., & Müller, O. (2024). Combining Causal Discovery and Machine Learning for Modeling Data Center Operations. arXiv preprint. https://doi.org/10.48550/arXiv.2410.09516
Zhang, Y., & Liu, J. (2022). Prediction of Overall Energy Consumption of Data Centers in Different Locations. Sensors, 22(10), 3704. https://doi.org/10.3390/s22103704
Zheng, Z. & others. (2022). Joinpoint–Multiple Linear Regression (JP–MLR) Model for Building Electricity Usage. Energies, 15(22), 8543. https://doi.org/10.3390/en15228543
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jaime David Camacho Castillo, Joel Geovanny Bonifaz Mendoza, Juan Sebastián Montesdeoca Guzñay, Samanta Kassiel Narvaez Coba, Alexis Xavier Nicolalde Carrasco, John Omar Yugcha Guevara
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors retain the moral and patrimonial rights of their works. They only give to the magazine Tesla Revista Científica the right to the first publication of this. Since Tesla Revista Científica is an open access publication, readers can fully or partially reproduce its content as long as they properly credit the corresponding authors and the journal itself. Tesla Revista Científica undertakes not to make commercial use of the texts it receives and/or publishes.
Our journal is governed by the international policies SHERPA/RoMEO: Green journal: They allow the self-archiving of both the pre-print (draft of a paper) and the post-print (the version corrected and reviewed by peers) and even the final version ( layout as it will be published in the journal).
See also "Copyright and licences".
