Abstract
The problem of this research is increasing electricity consumption in buildings has become a significant challenge in energy management and electricity load planning due to dynamic usage patterns influenced by operational schedules, environmental conditions, and temporal factors. The research gap identified is that machine learning techniques have been widely applied for electricity forecasting, but studies that integrate temporal, environmental, and historical consumption features within a unified prediction framework are still relatively limited. This study proposes an Artificial Intelligence-based building electricity consumption prediction framework using Light Gradient Boosting Machine (LightGBM) and time series regression techniques. The proposed approach integrates data preprocessing, feature engineering, environmental variables, temporal information, building identifiers, and historical electricity consumption records to improve forecasting accuracy. The dataset was processed chronologically and divided into training and validation sets without shuffling to preserve temporal dependencies. Model performance was evaluated using Root Mean Squared Error (RMSE). Experimental results demonstrate that the proposed model achieved an average RMSE of 143.36 and successfully captured the overall trend of electricity consumption across different buildings. The findings indicate that the integration of temporal, environmental, and historical consumption features contributes to effective forecasting performance and supports data-driven energy management applications. Future research may focus on incorporating occupancy information, real-time sensor measurements, and advanced deep learning approaches to further improve forecasting accuracy.
References
Adebayo Olusegun Aderibigbe, Emmanuel Chigozie Ani, Peter Efosa Ohenhen, Nzubechukwu Chukwudum Ohalete, & Donald Obinna Daraojimba. (2023). Enhancing Energy Efficiency with AI: A Review of Machine Learning Models in Electricity Demand Forecasting. Engineering Science & Technology Journal, 4(6), 341–356. https://doi.org/10.51594/estj.v4i6.636
Akhtar, S., Shahzad, S., Zaheer, A., Ullah, H. S., Kilic, H., Gono, R., Jasiński, M., & Leonowicz, Z. (2023). Short-Term Load Forecasting Models: A Review of Challenges, Progress, and the Road Ahead. Energies, 16(10), 4060. https://doi.org/10.3390/en16104060
Al-Jamimi, H. A., BinMakhashen, G. M., Worku, M. Y., & Hassan, M. A. (2023). Advancements in Household Load Forecasting: Deep Learning Model with Hyperparameter Optimization. Electronics, 12(24), 4909. https://doi.org/10.3390/electronics12244909
Bashir, T., Haoyong, C., Tahir, M. F., & Liqiang, Z. (2022). Short term electricity load forecasting using hybrid prophet-LSTM model optimized by BPNN. Energy Reports, 8, 1678–1686. https://doi.org/10.1016/j.egyr.2021.12.067
Baul, A., Sarker, G. C., Sikder, P., Mozumder, U., & Abdelgawad, A. (2024). Data-Driven Short-Term Load Forecasting for Multiple Locations: An Integrated Approach. Big Data and Cognitive Computing, 8(2), 12. https://doi.org/10.3390/bdcc8020012
Čegovnik, T., Dobrovoljc, A., Povh, J., Rogar, M., & Tomšič, P. (2023). Electricity consumption prediction using artificial intelligence. Central European Journal of Operations Research, 31(3), 833–851. https://doi.org/10.1007/s10100-023-00844-6
Cordeiro-Costas, M., Villanueva, D., Eguía-Oller, P., Martínez-Comesaña, M., & Ramos, S. (2023). Load Forecasting with Machine Learning and Deep Learning Methods. Applied Sciences, 13(13), 7933. https://doi.org/10.3390/app13137933
Dudek, G. (2022). A Comprehensive Study of Random Forest for Short-Term Load Forecasting. Energies, 15(20), 7547. https://doi.org/10.3390/en15207547
Gassar, A. A. (2024). Short-Term Energy Forecasting to Improve the Estimation of Demand Response Baselines in Residential Neighborhoods: Deep Learning vs. Machine Learning. Buildings, 14(7), 2242. https://doi.org/10.3390/buildings14072242
Hu, Y., Li, J., Hong, M., Ren, J., & Man, Y. (2022). Industrial artificial intelligence based energy management system: Integrated framework for electricity load forecasting and fault prediction. Energy, 244, 123195. https://doi.org/10.1016/j.energy.2022.123195
Ibrahim, B., Rabelo, L., Gutierrez-Franco, E., & Clavijo-Buritica, N. (2022). Machine Learning for Short-Term Load Forecasting in Smart Grids. Energies, 15(21), 8079. https://doi.org/10.3390/en15218079
Koukaras, P., Mustapha, A., Mystakidis, A., & Tjortjis, C. (2024). Optimizing Building Short-Term Load Forecasting: A Comparative Analysis of Machine Learning Models. Energies, 17(6), 1450. https://doi.org/10.3390/en17061450
Pallonetto, F., Jin, C., & Mangina, E. (2022). Forecast electricity demand in commercial building with machine learning models to enable demand response programs. Energy and AI, 7, 100121. https://doi.org/10.1016/j.egyai.2021.100121
Raviprabhakaran, V., Pranay, P., Nendralla, B., & Pranay, L. S. (2024). Household Power Consumption Analysis using Machine Learning. 2024 IEEE 4th International Conference on Sustainable Energy and Future Electric Transportation (SEFET), 1–6. https://doi.org/10.1109/SEFET61574.2024.10718254
Rodrigues, F., Cardeira, C., Calado, J. M. F., & Melicio, R. (2023). Short-Term Load Forecasting of Electricity Demand for the Residential Sector Based on Modelling Techniques: A Systematic Review. Energies, 16(10), 4098. https://doi.org/10.3390/en16104098
Ullah, K., Ahsan, M., Hasanat, S. M., Haris, M., Yousaf, H., Raza, S. F., Tandon, R., Abid, S., & Ullah, Z. (2024). Short-Term Load Forecasting: A Comprehensive Review and Simulation Study With CNN-LSTM Hybrids Approach. IEEE Access, 12, 111858–111881. https://doi.org/10.1109/ACCESS.2024.3440631
Yao, X., Fu, X., & Zong, C. (2022). Short-Term Load Forecasting Method Based on Feature Preference Strategy and LightGBM-XGboost. IEEE Access, 10, 75257–75268. https://doi.org/10.1109/ACCESS.2022.3192011
Yazici, I., Beyca, O. F., & Delen, D. (2022). Deep-learning-based short-term electricity load forecasting: A real case application. Engineering Applications of Artificial Intelligence, 109, 104645. https://doi.org/10.1016/j.engappai.2021.104645
Zhang, L., & Jánošík, D. (2024). Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches. Expert Systems with Applications, 241, 122686. https://doi.org/10.1016/j.eswa.2023.122686
Zini, M., & Carcasci, C. (2023). Machine learning-based monitoring method for the electricity consumption of a healthcare facility in Italy. Energy, 262, 125576. https://doi.org/10.1016/j.energy.2022.125576