Artificial intelligence models for predicting electric demand growth in urban energy systems of Riobamba, Ecuador
DOI:
https://doi.org/10.63688/ek1dhd94Keywords:
artificial intelligence, electricity demand forecasting, neural networks, predictive models, energy planningAbstract
The sustained growth in electricity consumption in intermediate cities such as Riobamba has highlighted the need for more accurate predictive tools to support efficient energy system planning. In this context, this study aimed to analyze the performance of artificial intelligence models in forecasting the future behavior of electricity demand using historical data from the 2020–2024 period. The research followed a quantitative and applied approach, with a non-experimental longitudinal design based on time series analysis. The dataset underwent preprocessing stages, including cleaning, normalization, and segmentation into training, validation, and testing sets. Subsequently, models based on artificial neural networks, support vector machines, and a hybrid approach were implemented within a computational simulation environment and evaluated using error metrics. The results demonstrated a high level of predictive accuracy. Neural networks achieved the best performance, with minimum errors of 1.8% and an average of approximately 2.5%. Meanwhile, the hybrid model and support vector machines obtained errors of 2.1% and 2.7%, respectively. These findings confirm the effectiveness of artificial intelligence techniques in capturing nonlinear patterns and seasonal variations in electricity demand.
References
Achy, J. Al, Harb, H., & Makhoul, A. (2026a). Leveraging cutting-edge technologies into energy management smart buildings: An era of revolution. Engineering Applications of Artificial Intelligence, 164, 112938. https://doi.org/https://doi.org/10.1016/j.engappai.2025.112938
Achy, J. Al, Harb, H., & Makhoul, A. (2026b). Leveraging cutting-edge technologies into energy management smart buildings: An era of revolution. Engineering Applications of Artificial Intelligence, 164, 112938. https://doi.org/https://doi.org/10.1016/j.engappai.2025.112938
Ahajjam, M. A., Bonilla Licea, D., Ghogho, M., & Kobbane, A. (2022). Experimental investigation of variational mode decomposition and deep learning for short-term multi-horizon residential electric load forecasting. Applied Energy, 326, 119963. https://doi.org/https://doi.org/10.1016/j.apenergy.2022.119963
Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., Muneer, A., Sumiea, E. H., Alqushaibi, A., & Ragab, M. G. (2024). RNN-LSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud University - Computer and Information Sciences, 36(5), 102068. https://doi.org/https://doi.org/10.1016/j.jksuci.2024.102068
Al-Shobaki, S., & Mohsen, M. (2008). Modeling and forecasting of electrical power demands for capacity planning. Energy Conversion and Management, 49(11), 3367–3375. https://doi.org/https://doi.org/10.1016/j.enconman.2008.05.005
Ardakani, F. J., & Ardehali, M. M. (2014). Novel effects of demand side management data on accuracy of electrical energy consumption modeling and long-term forecasting. Energy Conversion and Management, 78, 745–752. https://doi.org/https://doi.org/10.1016/j.enconman.2013.11.019
Badhon, N. H., Salehin, I., Sajib, M. T. A., Rifat, M. S. H., Noman, S. M., & Moon, N. N. (2025). TLCNN: Tabular data-based lightweight convolutional neural network for electricity energy demand prediction. Global Energy Interconnection, 8(6), 1010–1029. https://doi.org/https://doi.org/10.1016/j.gloei.2025.07.005
Bakare, M. S., Abdulkarim, A., Shuaibu, A. N., & Muhamad, M. M. (2024). A hybrid long-term industrial electrical load forecasting model using optimized ANFIS with gene expression programming. Energy Reports, 11, 5831–5844. https://doi.org/https://doi.org/10.1016/j.egyr.2024.05.045
Bampoulas, A., Pallonetto, F., Mangina, E., & Finn, D. P. (2023). A Bayesian deep-learning framework for assessing the energy flexibility of residential buildings with multicomponent energy systems. Applied Energy, 348, 121576. https://doi.org/https://doi.org/10.1016/j.apenergy.2023.121576
Barros, E. B. C., Souza, W. O., Costa, D. G., Filho, G. P. R., Figueiredo, G. B., & Peixoto, M. L. M. (2025). Energy management in smart grids: An Edge-Cloud Continuum approach with Deep Q-learning. Future Generation Computer Systems, 165, 107599. https://doi.org/https://doi.org/10.1016/j.future.2024.107599
Chen, B., Zhu, L., Hu, L., Zhang, R., Wu, Y., Li, H., Wen, X., Zhang, Y., & Gao, K. (2026). Adaptive energy management of electric vehicles via attention-enhanced LSTM networks for load power demand prediction. Energy, 344, 139797. https://doi.org/https://doi.org/10.1016/j.energy.2025.139797
Chen, H., Zhu, M., Hu, X., Wang, J., Sun, Y., & Yang, J. (2023). Research on short-term load forecasting of new-type power system based on GCN-LSTM considering multiple influencing factors. Energy Reports, 9, 1022–1031. https://doi.org/https://doi.org/10.1016/j.egyr.2023.05.048
Chen, Y., Xu, P., Chu, Y., Li, W., Wu, Y., Ni, L., Bao, Y., & Wang, K. (2017). Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings. Applied Energy, 195, 659–670. https://doi.org/https://doi.org/10.1016/j.apenergy.2017.03.034
Corradini, F., Gerosa, F., Gori, M., Lucheroni, C., Piangerelli, M., & Zannotti, M. (2026). A systematic literature review of spatio-temporal graph neural network models for time series forecasting and classification. Neural Networks, 195, 108269. https://doi.org/https://doi.org/10.1016/j.neunet.2025.108269
Criado-Ramón, D., Ruiz, L. G. B., & Pegalajar, M. C. (2022). Electric demand forecasting with neural networks and symbolic time series representations. Applied Soft Computing, 122, 108871. https://doi.org/https://doi.org/10.1016/j.asoc.2022.108871
Erlangga, G., & Cho, S.-B. (2025). Causally explainable artificial intelligence on deep learning model for energy demand prediction. Engineering Applications of Artificial Intelligence, 162, 112620. https://doi.org/https://doi.org/10.1016/j.engappai.2025.112620
Gao, Y., Xu, X., Yiu, T. W., & Wang, J. (2025). Transfer learning for smart construction: Advances and future directions. Automation in Construction, 175, 106238. https://doi.org/https://doi.org/10.1016/j.autcon.2025.106238
Ghosh, S., Kumar, N., & Chattopadhyay, S. (2025). Electrically conductive “SMART” hydrogels for on-demand drug delivery. Asian Journal of Pharmaceutical Sciences, 20(1), 101007. https://doi.org/https://doi.org/10.1016/j.ajps.2024.101007
Liu, G., Yu, J., Luo, X., Del Pero, C., Zhao, S., Huang, W., & Zhao, X. (2026). An integrated method for electric load forecasting in large public buildings based on load patterns clustering and multi-scale temporal feature selection. Energy, 347, 140438. https://doi.org/https://doi.org/10.1016/j.energy.2026.140438
Liu, G., Zhang, C., Wang, Y., Cao, D., Zhang, X., Jing, Y., & Zhu, H. (2025). Medium- and long-term load reliability forecasting method of power system based on CNN-GRU hybrid neural network. Results in Engineering, 28, 108263. https://doi.org/https://doi.org/10.1016/j.rineng.2025.108263
Liu, X., Zou, L., Han, Z., Jiang, J., Wang, Y., & Wang, R. (2026). A novel U-Net-physical informed neural network model for load forecasting of hydrogen power boat power system combined multi-source information spatiotemporal matrix construction. Engineering Applications of Artificial Intelligence, 167, 113807. https://doi.org/https://doi.org/10.1016/j.engappai.2026.113807
López Santos, M., Díaz García, S., García-Santiago, X., Ogando-Martínez, A., Echevarría Camarero, F., Blázquez Gil, G., & Carrasco Ortega, P. (2023). Deep learning and transfer learning techniques applied to short-term load forecasting of data-poor buildings in local energy communities. Energy and Buildings, 292, 113164. https://doi.org/https://doi.org/10.1016/j.enbuild.2023.113164
Mansoor, A., Liu, S., Ali, G. M., Bouferguene, A., & Al-Hussein, M. (2022). Scientometric analysis and critical review on the application of deep learning in the construction industry. Canadian Journal of Civil Engineering, 50(4), 253–269. https://doi.org/https://doi.org/10.1139/cjce-2022-0379
Mavromatidis, G., Orehounig, K., & Carmeliet, J. (2017). Designing electrically self-sufficient distributed energy systems under energy demand and solar radiation uncertainty. Energy Procedia, 122, 1027–1032. https://doi.org/https://doi.org/10.1016/j.egypro.2017.07.470
Miraki, A., Parviainen, P., & Arghandeh, R. (2024). Electricity demand forecasting at distribution and household levels using explainable causal graph neural network. Energy and AI, 16, 100368. https://doi.org/https://doi.org/10.1016/j.egyai.2024.100368
Mohammad, A. A. S., Oraini, B. Al, Mohammad, S. I., Alenazi, S. A., Al-Fawwaz, T. M., & Vasudevan, A. (2026). Mathematical and statistical modelling of electricity demand forecasting using artificial neural networks and SARIMA: Implications for energy supply chain planning. Alexandria Engineering Journal, 139, 98–108. https://doi.org/https://doi.org/10.1016/j.aej.2026.01.046
Mohammed, N. A. (2018). Modelling of unsuppressed electrical demand forecasting in Iraq for long term. Energy, 162, 354–363. https://doi.org/https://doi.org/10.1016/j.energy.2018.08.030
Morales-Acevedo, A. (2014). Forecasting Future Energy Demand: Electrical Energy in Mexico as an Example Case. Energy Procedia, 57, 782–790. https://doi.org/https://doi.org/10.1016/j.egypro.2014.10.286
Morteza, A., Yahyaeian, A. A., Mirzaeibonehkhater, M., Sadeghi, S., Mohaimeni, A., & Taheri, S. (2023). Deep learning hyperparameter optimization: Application to electricity and heat demand prediction for buildings. Energy and Buildings, 289, 113036. https://doi.org/https://doi.org/10.1016/j.enbuild.2023.113036
Na, N. (2024). Research on Supply Chain Demand Prediction Model Based on LSTM. Procedia Computer Science, 243, 313–322. https://doi.org/https://doi.org/10.1016/j.procs.2024.09.039
Panales-Pérez, A., Flores-Tlacuahuac, A., & Hernández-Romero, I. M. (2025). Prediction of electricity demand in weakly interconnected power systems using an ensemble time series model with a Bayesian Optimization approach. Chemical Engineering Research and Design, 220, 652–666. https://doi.org/https://doi.org/10.1016/j.cherd.2025.07.022
Peng, J., Kimmig, A., Wang, J., Liu, X., Niu, Z., & Ovtcharova, J. (2021). Dual-stage attention-based long-short-term memory neural networks for energy demand prediction. Energy and Buildings, 249, 111211. https://doi.org/https://doi.org/10.1016/j.enbuild.2021.111211
Qin, Q., & Evins, R. (2026). Deep temporal convolutional residual neural network (ResNet)–based surrogate models for time-series load prediction and fast demand response evaluation across buildings and climates. Energy Conversion and Management, 354, 121278. https://doi.org/https://doi.org/10.1016/j.enconman.2026.121278
Ramos, D., Faria, P., & Vale, Z. (2026). Linking short-term electricity demand forecasting and explainable AI: A review for building energy applications. Applied Energy, 412, 127658. https://doi.org/https://doi.org/10.1016/j.apenergy.2026.127658
Sarker, M. A. A., Shanmugam, B., Azam, S., & Thennadil, S. (2024). Enhancing smart grid load forecasting: An attention-based deep learning model integrated with federated learning and XAI for security and interpretability. Intelligent Systems with Applications, 23, 200422. https://doi.org/https://doi.org/10.1016/j.iswa.2024.200422
Satpathy, P. R., & Ramachandaramurthy, V. K. (2026). Artificial intelligence and machine learning for distributed energy resource management systems: Applications, frameworks, and future directions. Applied Energy, 403, 127109. https://doi.org/https://doi.org/10.1016/j.apenergy.2025.127109
Serrano-Guerrero, X., Briceño-León, M., Clairand, J.-M., & Escrivá-Escrivá, G. (2021). A new interval prediction methodology for short-term electric load forecasting based on pattern recognition. Applied Energy, 297, 117173. https://doi.org/https://doi.org/10.1016/j.apenergy.2021.117173
Shaqour, A., & Hagishima, A. (2026). Residential electrical demand data synthesis using the DGAN model: performance evaluation for diverse dwellings. Energy and Buildings, 351, 116722. https://doi.org/https://doi.org/10.1016/j.enbuild.2025.116722
Shaqour, A., Ono, T., Hagishima, A., & Farzaneh, H. (2022). Electrical demand aggregation effects on the performance of deep learning-based short-term load forecasting of a residential building. Energy and AI, 8, 100141. https://doi.org/https://doi.org/10.1016/j.egyai.2022.100141
Vinayagam, A., T, S. S., Amalorpavaraj, R. A. J., Aziz, N. F. A., Mansor, M. H., C, D., & Kamwa, I. (2026). A hyperband optimized Bi-LSTM model for electric demand forecasting in diversified power systems. Results in Engineering, 29, 109891. https://doi.org/https://doi.org/10.1016/j.rineng.2026.109891
Zhang, D., Wang, S., Liang, Y., & Du, Z. (2023). A novel combined model for probabilistic load forecasting based on deep learning and improved optimizer. Energy, 264, 126172. https://doi.org/https://doi.org/10.1016/j.energy.2022.126172
Zhou, Y., Wang, J., Liu, Y., Yan, R., & Ma, Y. (2021). Incorporating deep learning of load predictions to enhance the optimal active energy management of combined cooling, heating and power system. Energy, 233, 121134. https://doi.org/https://doi.org/10.1016/j.energy.2021.121134
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Samantha Marlene Puente Bosquez, Carlos Isaac Machuca Valverde, Danner Anderson Figueroa Guerra, Josué Lenin Fuentes Véliz (Autor/a)
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
