Energy Consumption Prediction in Smart Homes Using Machine Learning and Deep Learning Approaches

Ahmed Hamid  Saleh; Mohammed F Ibrahim  Alsarraj; Abdulwahhab F  Shareef

Authors

Ahmed Hamid Saleh Technical College of Management/Mosul, Northern Technical University, Mosul, 41001, Iraq
Mohammed F Ibrahim Alsarraj Technical Engineering College for Computer and AI–Mosul, Northern Technical University, Mosul, 41001, Iraq
Abdulwahhab F Shareef Technical Engineering College for Computer and AI–Mosul, Northern Technical University, Mosul, 41001, Iraq.

Keywords:

Smart homes, Energy consumption prediction, Machine learning, Deep learning, Sustainability

Abstract

The intelligent control of smart homes for energy savings and sustainability relies on accurate predictions of energy consumption. Many machine learning (ML) and deep learning (DL) models currently exist for this purpose; however, systematic investigations into their predictive performance, computational requirements, and cross-dataset validity are limited. This study proposes a household energy prediction benchmark to assess classical ML solutions (Support Vector Machine, Random Forest, Gradient Boosting), DL alternatives (Artificial Neural Networks, Long Short-Term Memory, Gated Recurrent Units), and a combined CNN-LSTM framework. Validations were performed using two of the most cited smart home datasets, REFIT and UK-DALE, for generalizability across homes with varied sampling resolutions. Assessments were made according to prediction effectiveness (RMSE, MAE, MAPE, and R²) and computational demand. The findings show that DL models outperform classical models, CNN-LSTM outperforms the other homogeneous networks tested on both datasets, and a robust analysis supports hybridized convolutional feature extraction and recurrent temporal modeling as superior to more straightforward alternatives. Finally, a discussion of the advantages of CNN-LSTM compared to the associated costs of its IoT-enabled smart home implementation indicates that energy consumption forecasting is necessary to assess the potential of peak load consumption and bolsters the call for sustainable metropolitan energy infrastructure systems.

References

O. Akbarzadeh et al., “Heating-Cooling Monitoring and Power Consumption Forecasting Using LSTM for Energy-Efficient Smart Management of Buildings: A Computational Intelligence Solution for Smart Homes,” Tsinghua Sci. Technol., vol. 29, no. 1, pp. 143–157, Feb. 2024, doi: 10.26599/tst.2023.9010008.

J. I. Janjua, A. Khan, T. Abbas, A. Q. Saeed, A. Ihsan, and S. Kousar, “Enhancing Scalability in Reinforcement Learning for Open Spaces,” Institute Of Electrical Electronics Engineers, Dec. 2024, pp. 1–8. doi: 10.1109/dasa63652.2024.10836237.

N. Dey, W. Song, K. Cho, and S. Fong, “Forecasting Energy Consumption from Smart Home Sensor Network by Deep Learning,” Springer Singapore, 2018, pp. 255–265. doi: 10.1007/978-981-13-1423-0_28.

R. A. Ramadan, “Internet of things dataset for home renewable energy management,” Feb. 10, 2024, Elsevier. doi: 10.1016/j.dib.2024.110166.

T. M. Ghazal et al., “Generative Federated Learning with Small and Large Models In Consumer Electronics for Privacy preserving Data Fusion in Healthcare Internet of Things,” IEEE Trans. Consumer Electron., p. 1, Jan. 2025, doi: 10.1109/tce.2025.3572629.

C. Ikegwu, M. O. Kama, D. U. Ebem, I. S. Nwokoro, and O. J. Obianuju, “Investigating the Impact of AI/ML for Monitoring and Optimizing Energy Usage in Smart Home,” Artificial Intelligence Evolution, pp. 30–43, Jan. 2025, doi: 10.37256/aie.6120256065.

F. Iqbal et al., “Blockchain-Modeled Edge-Computing-Based Smart Home Monitoring System with Energy Usage Prediction,” Sensors, vol. 23, no. 11, p. 5263, June 2023, doi: 10.3390/s23115263.

Y. Natarajan et al., “Enhancing Building Energy Efficiency with IoT-Driven Hybrid Deep Learning Models for Accurate Energy Consumption Prediction,” Sustainability, vol. 16, no. 5, p. 1925, Feb. 2024, doi: 10.3390/su16051925.

N. Roy, S. K. Das, and A. Roy, “Context-Aware Resource Management in Multi-Inhabitant Smart Homes: A Nash H-Learning based Approach,” Institute Of Electrical Electronics Engineers, Mar. 2006, pp. 148–158. doi: 10.1109/percom.2006.18.

N. A. Al-Dmour, T. Abbas, A. Khan, S. Kousar, A. Q. Saeed, and A. Ihsan, “Enhancing Email Spam Detection Using Advanced AI Techniques,” Institute Of Electrical Electronics Engineers, Dec. 2024, pp. 1–6. doi: 10.1109/dasa63652.2024.10836525.

H. Hamdoun, H. Youness, and A. Sagheer, “Energy time series forecasting-analytical and empirical assessment of conventional and machine learning models,” IFS, vol. 40, no. 6, pp. 12477–12502, Jan. 2021, doi: 10.3233/jifs-201717.

N. G. Paterakis, E. Mocanu, B. Stappers, M. Gibescu, and W. Van Alst, “Deep learning versus traditional machine learning methods for aggregated energy demand prediction,” Institute Of Electrical Electronics Engineers, Sept. 2017, pp. 1–6. doi: 10.1109/isgteurope.2017.8260289.

N. E. Benti, M. D. Chaka, and A. G. Semie, “Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects,” Sustainability, vol. 15, no. 9, p. 7087, Apr. 2023, doi: 10.3390/su15097087.

J. I. Janjua et al., “Enhancing smart grid electricity prediction with the fusion of intelligent modeling and XAI integration,” Int. j. adv. appl. sci., vol. 11, no. 5, pp. 230–248, May 2024, doi: 10.21833/ijaas.2024.05.025.

L. H. M. Truong et al., “Accurate Prediction of Hourly Energy Consumption in a Residential Building Based on the Occupancy Rate Using Machine Learning Approaches,” Applied Sciences, vol. 11, no. 5, p. 2229, Mar. 2021, doi: 10.3390/app11052229.

Y. Li, “Energy consumption forecasting with deep learning,” J. Phys.: Conf. Ser., vol. 2711, no. 1, p. 012012, Feb. 2024, doi: 10.1088/1742-6596/2711/1/012012.

S. Ardabili, B. Torok, A. Mosavi, L. Abdolalizadeh, and C. Mako, “Systematic Review of Deep Learning and Machine Learning for Building Energy,” Front. Energy Res., vol. 10, Mar. 2022, doi: 10.3389/fenrg.2022.786027.

Mosavi and A. Bahmani, “Energy Consumption Prediction Using Machine Learning; A Review,” Mar. 11, 2019, Mdpi Ag. doi: 10.20944/preprints201903.0131.v1.

R. Mathumitha, P. Rathika, and K. Manimala, “Intelligent deep learning techniques for energy consumption forecasting in smart buildings: a review,” Artif Intell Rev, vol. 57, no. 2, Feb. 2024, doi: 10.1007/s10462-023-10660-8.

D. Kaur, M. E. Haque, M. A. Mahmud, Z. Y. Dong, and S. N. Islam, “Energy forecasting in smart grid systems: recent advancements in probabilistic deep learning,” IET Generation Trans & Dist, vol. 16, no. 22, pp. 4461–4479, Sept. 2022, doi: 10.1049/gtd2.12603.