Multi-criteria selection of the optimal model for the forecast of the maximum daily electrical demand considering the satisfaction of the real demand
DOI:
https://doi.org/10.36825/RITI.13.29.004Keywords:
Electricity Demand, Optimal Model, Multi-Criteria, Forecast, Weighted SumAbstract
When forecasting electricity demand, it is expected not only that the results are close to the actual demand, but also that they are equal to or greater than this demand. Therefore, the objective of this research is to develop a multi-criteria methodology for the selection of the best forecast model for the maximum daily electricity demand considering the satisfaction of the real demand as a decision criterion. Forecast models were generated with daily resolution and weekly horizons, using the Box-Jenkins methodology, the Prophet technique, and the LSTM network, for ten weeks. In each week the models were evaluated, both in the testing stage and by comparing the forecast with actual demand, using the MAE, RMSE and MAPE metrics. The SAW multicriteria technique was used to select the optimal model, with the decision alternatives being the generated forecast models, and the decision criteria were the global MAPE, the number of times in which a respective model had the minimum MAPE value, and the number of days in which the forecasted demand was equal to or greater than the actual demand. The best model turned out to be the one corresponding to the LSTM network, with a value of 0.926, and the ARIMA model was next with a value of 0.814.
References
Hammad, M. A., Jereb, B., Rosi, B., Dragan, D. (2020). Methods and Models for Electric Load Forecasting: A Comprehensive Review. Logistics, Supply Chain, Sustainability and Global Challenges, 11 (1), 51-76. https://doi.org/10.2478/jlst-2020-0004
Weron, R. (2006). Modeling and Forecasting Electricity Loads and Prices - A Statistical Approach. John Wiley & Sons Ltd.
Islam, B., Ahmed, S. (2022). Short-Term Electrical Load Demand Forecasting Based on LSTM and RNN Deep Neural Networks. Mathematical Problems in Engineering, 1-10. https://doi.org/10.1155/2022/2316474
Groß, A., Lenders, A., Schwenker, F., Braun, D., Fischer, D. (2021). Comparison of short-term electrical load forecasting methods for different building types. 10th DACH+ Conference on Energy Informatics. https://energyinformatics.springeropen.com/articles/10.1186/s42162-021-00172-6
Filipova-Petrakieva, S., Dochev, V. (2022). Short-Term Forecasting of Hourly Electricity Power Demand. Engineering, Technology & Applied Science Research - Reggresion and Cluster Methods for Short-Term Prognosis, 12 (2), 8374-8381. https://etasr.com/index.php/ETASR/article/view/4787/2711.
Kim, Y., Son, H.-g., Kim, S. (2019). Short term electricity load forecasting for institutional buildings. Energy Reports, 5, 1270–1280. https://doi.org/10.1016/j.egyr.2019.08.086
Jales Melo, J. V., Soares Lira, G. R., Guedes Costa, E., Leite Neto, A. F., Oliveira, I. B. (2022). Short-Term Load Forecasting on Individual Consumers. Energies, 15 (16), 1-16. https://doi.org/10.3390/en15165856
Khan, S. (2023). Short-Term Electricity Load Forecasting Using a New Intelligence-Based Application. Sustainability, 15 (16), 1-12. https://doi.org/10.3390/su151612311
Yajure-Ramírez, C. A. (2023). Multi-criteria methodology based on data science for the selection of the optimal forecast model for residential electricity consumption. Scientia et Technica, 28 (3), 108-116. https://doi.org/10.22517/23447214.25335
Yajure Ramírez, C. A. (2023). Selección del modelo óptimo de predicción de la relación de desempeño de una planta solar fotovoltaica. Un enfoque multicriterio basado en algoritmos de aprendizaje automático. Ciencia, Ingenierías y Aplicaciones, 6 (2), 7-29. https://doi.org/10.22206/cyap.2023.v6i2.2935
Badulescu, Y., Hameri, A.-P., Cheikhrouhou, N. (2021). Evaluating demand forecasting models using multi-criteria decision-making approach. Journal of Advances in Management Research, 18 (5), 661-683. https://doi.org/10.1108/JAMR-05-2020-0080
Deina, C., Ferreira dos Santos, J., Biuk, L., Lizot, M., Converti, A., Valadares Siqueira, H., Trojan, F. (2023). Forecasting Electricity Demand by Neural Networks and Definition of Inputs by Multi-Criteria Analysis. Energies, 16 (4), 1-24. https://doi.org/10.3390/en16041712
Koubaa, Z., El-Amraoui, A., Frikha, A., Delmotte, F. (2024). Multicriteria Decision Making for Selecting Forecasting Electricity Demand Models. Sustainability, 16 (21), 1-15. https://doi.org/10.3390/su16219219
Jadon, A., Patil, A., Jadon, S. (2022). A Comprehensive Survey of Regression Based Loss Functions for Time Series Forecasting. ArXiv, 1-13. https://doi.org/10.48550/arXiv.2211.02989
Eltarabishi, F., Omar, O., Alsyouf, I., Bettayeb, M. (2020). Multi-Criteria Decision Making Methods And Their Applications– A Literature Review. International Conference on Industrial Engineering and Operations Management. Dubai, UAE. http://www.ieomsociety.org/ieom2020/papers/656.pdf.
Triantaphyllou, E., Shu, B., Nieto Sanchez, S., Ray, T. (1998). Multi-Criteria Decision Making: An Operations Research Approach. En J.G. Webster (Ed.) Encyclopedia of Electrical and Electronics Engineering (pp. 175-186). John Wiley & Sons. https://bit.csc.lsu.edu/trianta/EditedBook_CHAPTERS/EEEE1.pdf
Ishizaka, A., Nemery, P. (2013). Multi-Criteria Decision Analysis - Methods and Software. John Wiley & Sons, Ltd.
Taherdoost, H. (2023). Analysis of Simple Additive Weighting Method (SAW) as a Multi-Attribute Decision-Making Technique: A Step-by-Step Guide. Journal of Management Science & Engineering Research, 6 (1), 21-24. https://doi.org/10.30564/jmser.v6i1.5400
Sahoo, B., Behera, R., Pattnaik, P. (2022). A Comparative Analysis of Multi-Criteria Decision Making Techniques for Ranking of Attributes for e-Governance in India. International Journal of Advanced Computer Science and Applications, 13 (3), 65-70. https://dx.doi.org/10.14569/IJACSA.2022.0130311
Saaty, T. L. (2008). Decision making with the analytic hierarchy process. International Journal of Services Sciences, 1 (1), 83-98. https://dx.doi.org/10.1504/IJSSCI.2008.017590
López Osorio, R., Pérez Aguilar, L., Zambrano Medina, Y., Ávila Aceves, E. (2024). Aplicación de evaluación multicriterio para modelar factores climáticos y ambientales en la identificación de regiones áridas en el noroeste de México. Revista de Investigación en Tecnologías de la Información, 12 (28), 54-70. https://doi.org/10.36825/RITI.12.28.006
Gómez-Romero, J., Soto Flores, R., Garduño Román, S. (2019). Determination of theWeightings of Hydroelectric Sustainability Criteria by Combining AHP and GP Extended Methods. Ingeniería, 24 (2), 116-142. https://doi.org/10.14483/23448393.14469
Box, G., Jenkins, G., Reinsel, G., Ljung, G. (2016). Time Series Analysis - Forecasting and Control. John Wiley & Sons, Inc.
Prophet. (2024). Quick Start Python API. https://facebook.github.io/prophet/docs/quick_start.html#python-api
Taylor, S., Letham, B. (2017). Forecasting at Scale. PeerJ Preprints. https://doi.org/10.7287/peerj.preprints.3190v2
Peixeiro, M. (2022). Time Series Forecasting in Python. Manning Publications Co.
Cielen, D., Meysman, A., Ali, M. (2016). Introducing Data Science. Manning Publications Co.
Navlani, A., Fandango, A., Idris, I. (2021). Python Data Analysis. Packt Publishing Ltd.
Yajure Ramírez, C. (2016). Comparación de técnicas de ponderación de criterios en metodologías de toma de decisiones multicriterio aplicadas a la jerarquización de tecnologías renovables. Revista Tecnológica ESPOL, 29 (2), 12-27. https://rte.espol.edu.ec/index.php/tecnologica/article/view/463
Papathanasiou, J., Ploskas, N. (2018). Multiple Criteria Decision Aid - Methods, Examples and Python Implementations. Springer Nature Switzerland AG.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Revista de Investigación en Tecnologías de la Información
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Esta revista proporciona un acceso abierto a su contenido, basado en el principio de que ofrecer al público un acceso libre a las investigaciones ayuda a un mayor intercambio global del conocimiento.
El texto publicado en la Revista de Investigación en Tecnologías de la Información (RITI) se distribuye bajo la licencia Creative Commons (CC BY-NC
), que permite a terceros utilizar lo publicado citando a los autores del trabajo y a RITI, pero sin hacer uso del material con propósitos comerciales.
