Electricity Energy Consumption Forecasting Using Different Deep Learning Models

Karwan  Salih Rasul; Nzar  Abdulqadir Ali

doi:10.25098/9.1.29

Authors

Karwan Salih Rasul Technical Institute of Sulaimani, Sulaimani Polytechnic University, Sulaimani, Iraq
Nzar Abdulqadir Ali Department of Statistics and Informatics, University of Sulaimani, Sulaimani, Iraq

DOI:

https://doi.org/10.25098/9.1.29

Keywords:

Electricity Energy Demand Forecasting, LSTM, RNN, Machine Learning, Deep Learning, Forecasting

Abstract

Accurate forecasting of electricity energy requirements has become critical for current energy systems, which are facing increasing challenges due to industrial development, population growth and the integration of green energy. The research evaluates the capacity of machine learning and deep learning algorithms to forecast demand of electricity energy consumption using dataset information from central electricity control office of Iraqi Kurdistan Region Government (KRG). Electricity energy consumption data analysis requires predictive models that are more sophisticated than traditional methods such as Autoregressive Integrated Moving Average (ARIMA) and exponential sequences, as these methods fail to deal with complex nonlinear patterns and high-frequency oscillations. Therefore, this study presents deep learning models using Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN), where the test results on the electricity energy data from KRG showed the superiority of the LSTM model in terms of accuracy and stability compared to RNN, the data was analyzed using multiple performance measures such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to confirm the efficiency of the proposed model. The results show LSTM superior performance than the RNN model based on the metrics provided, as the RMSE (187.25) and MAE (139.78) values are lower compared to the RNN (RMSE = 230.34, MAE = 232.276), indicating that LSTM forecasts are more accurate with fewer errors. In addition, the coefficient of determination (R²) of the LSTM model (0.961) is higher than that of RNN (0.941) Finally, this model can be applied in intelligent energy systems to improve load management efficiency and reduce waste.

References

Zhou, Y., Li, X., Wang, J., & Chen, H. Advances in energy consumption forecasting for smart buildings and cities: Methods and applications. Renewable and Sustainable Energy Reviews, 169, 113012, 2023

A. O. Aderibigbe, E. C. Ani, P. E. Ohenhen, N. C. Ohalete, and D. O. Daraojimba. "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.

S. F. Ahmed, M. S. B. Alam, M. Hassan, M. R. Rozbu, T. Ishtiak, N. Rafa, M. Mofijur, A. B. M. Shawkat Ali, and A. H. Gandomi. “Deep learning modelling techniques: current progress, applications, advantages, and challenges”. Artif Intell Rev vol 56, no 11, pp. 13521–13617, 2023.

Zhang, W., Liu, H., Zhang, J., & Wang, Y. A hybrid deep learning model for short-term load forecasting using improved VMD and CNN–BiLSTM with attention mechanism. Expert Systems with Applications, 239, 121837. (2025).

W. Zhao, Y. Gao, T. Ji, X. Wan, F. Ye and G. Bai, "Deep Temporal Convolutional Networks for Short-Term Traffic Flow Forecasting," IEEE Access, vol. 7, pp. 114496-114507, 2019.

Utku, A., & Kaya, S. K. Deep learning based on a comprehensive analysis for waste prediction. Operational Research in Engineering Sciences: Theory and Applications, 5(2), 176-189,2022.

Z. A. Khan, et al. “Short-Term Electricity Price Forecasting Through Convolutional Neural Network (CNN). In: Barolli, L., Amato, F., Moscato, F., Enokido, T., Takizawa, M. (eds) Web, Artificial Intelligence and Network Applications. WAINA 2020. Advances in Intelligent Systems and Computing, vol 1150. Springer, Cham,2020.

S. Ghimire, R. C. Deo, D. Casillas-Pérez, and S. Salcedo-Sanz. “Two-step deep learning framework with error compensation technique for short-term, half-hourly electricity price forecasting”. Appl. Energy, vol. 353, p.122059, 2024.

M. Bilgili, N. Arslan, A. ŞEKERTEKİN, and A. YAŞAR. “Application of long short-term memory (LSTM) neural network based on deep learning for electricity energy consumption forecasting”. Turkish J. of Elect. Eng. Com. Sci., vol. 30, no.1, pp.140-157, 2022.

P-H. Kuo, C-J. Huang. “An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks”. Sustainability, vol. 10, no. 4, p. 1280, 2018.

M. Heidarpanah, F. Hooshyaripor, and M. Fazeli. “Daily electricity price forecasting using artificial intelligence models in the Iranian electricity market. Energy, vol, 263, p.126011. 2023.

B. Farsi, M. Amayri, N. Bouguila and U. Eicker, "On Short-Term Load Forecasting Using Machine Learning Techniques and a Novel Parallel Deep LSTM-CNN Approach". IEEE Access, vol. 9, pp. 31191-31212, 2021,

N. Al Khafaf, M. Jalili, and P. Sokolowski, "Application of Deep Learning Long Short-Term Memory in Energy Demand Forecasting. In: Macintyre, J., Iliadis, L., Maglogiannis, I., Jayne, C. (eds) Engineering Applications of Neural Networks. EANN 2019. Communications in Computer and Information Science, vol, 1000. Springer, Cham. https://doi.org/10.1007/978-3-030-20257-6_3 ,2019.

M. Azzone and R. Baviera, "Neural Network Middle-Term Probabilistic Forecasting of Daily Power Consumption," J. Energy Mark., vol. 14, no. 1, 2020.

Mahjoub, S., Chrifi-Alaoui, L., Marhic, B., & Delahoche, L. Predicting energy consumption using

LSTM, multi-layer GRU and Drop-GRU neural networks. Sensors, 22(11), 4062, 2022.

B. Ghojogh and A. Ghodsi, "Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey," Available at: http://arxiv.org/abs/2304.11461, 2023.

Fatovatikhah, F., Ahmedy, I., & Noor, R. M. (2024). Waste Prediction Approach Using Hybrid Long Short-Term Memory with Support Vector Machine. International Journal of Computational Intelligence Systems, 17(1), 103.

Yazdani, M., Kabirifar, K., & Haghani, M. (2024). Optimizing post-disaster waste collection by a deep learning-enhanced differential evolution approach. Engineering Applications of Artificial Intelligence, 132, 107932.

Siami-Namini, Sima, Neda Tavakoli and Akbar Siami Namin. "The performance of LSTM and BiLSTM in forecasting time series." IEEE International conference on big data (Big Data). IEEE, 2019.

Zheng, Jian, et al. Mar. "Electric Load Forecasting in Smart Grid Using Long-Short-Term-Memory

based Recurrent Neural Network." IEEE Global Smart Grid Conference (GSS),2017