Deep Learning Framework for Joint Prediction of Energy Resources in an Industrial Building

Document Type : Original Research

Authors

1 Gorgan University of Agricultural Sciences and Natural Resources, Faculty of Water and Soil Engineering, Department of Biosystems Engineering, Gorgan, Iran.

2 Mechanics of Biosystems Engineering Department, College of Aburaihan, University of Tehran, Tehran, Iran.

Abstract

Renewable energy sources like solar photovoltaic (PV) systems are inherently volatile, necessitating accurate short-term forecasting for efficient grid management, energy storage, and consumption optimization. This study proposes a deep learning framework using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to simultaneously forecast PV generation (from roof and facade panels), on-site electrical consumption, and grid imports in an industrial building, relying solely on raw historical time-series data without meteorological or temporal features. The dataset, sourced from the Open Power System Data repository, comprises minute-by-minute measurements from a facility in Konstanz, Germany, preprocessed with Min-Max scaling and linear interpolation for gaps. The models were trained on 80% of the data using a 24-hour sequence length, with architectures featuring two recurrent layers (50 units each), dropout (0.2), ReLU activation, Adam optimizer, and MSE loss. Early stopping and learning rate reduction callbacks prevented overfitting. Evaluation via MSE, RMSE, MAE, and R² on test data showed strong performance, with GRU achieving an average R² of 0.906, MAE of 0.034, MSE of 0.0038, and RMSE of 0.062. Five-fold cross-validation confirmed model stability (mean R² ≈ 0.89 for both architectures), with GRU slightly outperforming LSTM. Results demonstrate the framework's ability to capture endogenous patterns, reducing data collection costs and enhancing applicability in legacy systems. Limitations include site-specific data, suggesting future enhancements via data augmentation, transfer learning, or hybrid models for broader generalizability. This approach supports sustainable energy management by minimizing fossil fuel reliance and operational costs.

Keywords

References

Agoua, X. G., Girard, R., & Kariniotakis, G. (2017). Short-term spatio-temporal forecasting of photovoltaic power production. IEEE Transactions on Sustainable Energy, 9(2), 538-546. https://doi.org/10.1109/TSTE.2017.2747765
Bar-Gera, H. (2017). The target parameter of adjusted R-squared in fixed-design experiments. The American Statistician, 71(2), 112-119. https://doi.org/10.1080/00031305.2016.1200489
Cao, H., Wang, T., Chen, P., Cheng, W., Cao, Y., & Liu, Z. (2022). Solar energy forecasting in short term based on the aso-bpnn model. Frontiers in Energy Research, 10, 902486. https://doi.org/10.3389/fenrg.2022.902486
Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature. Geoscientific model development, 7(3), 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014
Hodson, T. O. (2022). Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development Discussions, 2022, 1-10. https://doi.org/10.5194/gmd-15-5481-2022
Ishaq, M., & Kwon, S. (2021). Short-term energy forecasting framework using an ensemble deep learning approach. IEEE Access, 9, 94262-94271. https://doi.org/10.1109/ACCESS.2021.3093053
Jakoplić, A., Franković, D., Havelka, J., & Bulat, H. (2023). Short-term photovoltaic power plant output forecasting using sky images and deep learning. Energies, 16(14), 5428. https://doi.org/10.3390/en16145428
Jiang, Y., Gao, T., Dai, Y., Si, R., Hao, J., Zhang, J., & Gao, D. W. (2022). Very short-term residential load forecasting based on deep-autoformer. Applied Energy, 328, 120120. https://doi.org/10.1016/j.apenergy.2022.120120
Kristian, A., Goh, T. S., Ramadan, A., Erica, A., & Sihotang, S. V. (2024). Application of ai in optimizing energy and resource management: Effectiveness of deep learning models. International Transactions on Artificial Intelligence, 2(2), 99-105. https://doi.org/10.33050/italic.v2i2.530
Kumar, S., Kour, V., Raj, A., Tapung, T., Mishra, S., Misra, R., & Singh, T. (2025). Optimizing Air Pollution Forecasting Models Through Knowledge Distillation: A Novel GCN and TRANS_GRU Methodology for Indian Cities. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3546504
Li, J. (2017). Assessing the accuracy of predictive models for numerical data: Not r nor r2, why not? Then what? PloS one, 12(8), e0183250. https://doi.org/10.1371/journal.pone.0183250
Mazen, F. M. A., Shaker, Y., & Abul Seoud, R. A. (2023). Forecasting of solar power using GRU–temporal fusion transformer model and DILATE loss function. Energies, 16(24), 8105. https://doi.org/10.3390/en16248105
Mounir, N., Ouadi, H., & Jrhilifa, I. (2023). Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system. Energy and Buildings, 288, 113022. https://doi.org/10.1016/j.enbuild.2023.113022
Open Power System Data. (n.d.). A platform for open data of the European power system. https://open-power-system-data.org/
Oreshkin, B. N., Dudek, G., Pełka, P., & Turkina, E. (2021). N-BEATS neural network for mid-term electricity load forecasting. Applied Energy, 293, 116918. https://doi.org/10.1016/j.apenergy.2021.116918
Ramsebner, J., Haas, R., Auer, H., Ajanovic, A., Gawlik, W., Maier, C., Nemec-Begluk, S., Nacht, T., & Puchegger, M. (2021). From single to multi-energy and hybrid grids: Historic growth and future vision. Renewable and Sustainable Energy Reviews, 151, 111520. https://doi.org/10.1016/j.rser.2021.111520
Sami, S., Hassan-Beygi, S. R., & Massah, J. (2025). Accurate PV Power Forecasting Using a Lightweight LSTM Model: A Case Study. Biomechanism and Bioenergy Research, 4(3), 68-80. https://doi.org/10.22103/bbr.2025.25811.1132
Wang, R., Liu, X., Chang, Y., Liu, D., & Yao, H. (2024). Short-Term Photovoltaic System Output Power Prediction Based on Integrated Deep Learning Algorithms in the Clean Energy Sector. International Journal of e-Collaboration (IJeC), 20(1), 1-15. https://doi.org/10.4018/IJeC.346979
Xiuyun, G., Ying, W., Yang, G., Chengzhi, S., Wen, X., & Yimiao, Y. (2018). Short-term load forecasting model of GRU network based on deep learning framework. 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2),
Zhang, J., Huang, K., & Yang, Y. (2024). Short-term photovoltaic power prediction based on improved EMA variable weight combination. 2024 6th International Conference on Energy, Power and Grid (ICEPG),
Zhang, W. (2022). Short-term load forecasting of power model based on CS-Catboost algorithm. 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC),
Zhou, Z.-R., Wang, W.-W., Li, Y., Jin, K.-R., Wang, X.-Y., Wang, Z.-W., Chen, Y.-S., Wang, S.-J., Hu, J., & Zhang, H.-N. (2019). In-depth mining of clinical data: the construction of clinical prediction model with R. Annals of translational medicine, 7(23), 796. https://doi.org/10.21037/atm.2019.08.63
Biomechanism and Bioenergy Research
Volume 4, Issue 4 - Serial Number 10
December 2025
Pages 95-109

Files

History

  • Receive Date: 21 September 2025
  • Revise Date: 13 December 2025
  • Accept Date: 18 December 2025

Share

How to cite

Statistics