Published
Heuristics-Based Energy Demand Forecasting with Scarce Data in the Department of Huila, Colombia
Pronóstico de la Demanda de Energía Basado en Heurística con Datos Escasos en el Departamento del Huila, Colombia
DOI:
https://doi.org/10.15446/ing.investig.109551Keywords:
demand forecasting, energy, heuristics, scarce data (en)pronóstico de la demanda, energía, heurística, datos escasos (es)
Downloads
Within the framework of the energy transition, electrical distribution grid operators require effective tools to predict the demand of individual users. These tools are necessary for an adequate planning of future generation resources and infrastructure modernization. However, understanding future electricity needs poses a significant challenge, especially in emerging economies, where historical data are manually collected on a monthly or bi-monthly basis and exhibit a significant amount of missing information. In response to the above, this work proposes a novel heuristics-based method for medium-term energy demand forecasting with scarce data. Qualitative and quantitative information was abstracted into a mathematical model representing the trend and noise components of historical energy consumption observations. In addition, external factors were considered as an additional layer for the mathematical model, in order to account for events that could not be foreseen by merely using the dataset. A train-test data split was proposed to iteratively search for the best parameters to predict electricity demand with respect to different categorical divisions of users (social stratum, rural or urban location, and municipality). For testing and validation, real historical data were used, as provided by the regional distribution system operator (DSO) of the department of Huila, Colomba. The results suggest a trade-off between accuracy and computational intensity, as well as the fact that a non-categorical approach leads to the algorithm with the best performance (average absolute error of 1.61%) at a low computational cost.
En el marco de la transición energética, los operadores de redes de distribución eléctrica requieren herramientas efectivas para predecir la demanda de usuarios individuales. Estas herramientas son necesarias para un planeamiento adecuado de los recursos futuros de generación y la modernización de la infraestructura. Sin embargo, entender las necesidades futuras de electricidad constituye un desafı́o significativo, especialmente en economı́as emergentes donde los datos históricos son recolectados manualmente en perı́odos mensuales o bimensuales y presentan una cantidad significativa de información faltante. En respuesta a esto, se propone un novedoso método basado en heurı́stica para el pronóstico de la demanda de energı́a en el mediano plazo con datos escasos. Se abstrajo información cualitativa y cuantitativa en un modelo matemático que representa las componentes de tendencia y ruido en observaciones históricas de consumo de energı́a. Adicionalmente, se consideraron factores externos como capa adicional para el modelo matemático, en aras de dar cuenta de eventos que no podrı́an ser previstos solamente con el conjunto de datos. Se propuso una división de datos de entrenamiento y prueba con el fin de buscar iterativamente los mejores parámetros para predecir la demanda de electricidad respecto a diferentes divisiones categóricas de usuarios (estrato social, ubicación rural o urbana y municipio). Para realizar pruebas y validaciones, se utilizaron datos históricos reales proporcionados por el operador del sistema de distribución (OSD) regional del departamento del Huila, Colombia. Los resultados sugieren que hay una compensación entre precisión e intensidad computacional, y que un enfoque no categórico resulta en el algoritmo con un mejor desempeño (error absoluto promedio de 1.61 %) y un bajo costo computacional.
References
Allen, M., and Isaacson, E. (2019). Numerical analysis for applied science. Wiley. https://books.google.be/books?id=PpB9cjOxQAQC.
Amber, K. P., Aslam, M. W., Mahmood, A., Kousar, A., Younis, M. Y., Akbar, B., Hussain, S. H. (2017). Energy consumption forecasting for university sector buildings. Enegries, 10(10). https://doi.org/10.3390/en10101579
Bennett, D. A. (2001). How can i deal with missing data in my study? Australian and New Zealand Journal of Public Health, 25(5), 464-469. https://doi.org/10.1111/j.1467-842X.2001.tb00294.x Biel, K., and Glock, C. H. (2016). Systematic literature review of decision support models for energy-efficient production planning. Computers & Industrial Engineering, 101, 243-259. https://oi.org/10.1016/j.cie.2016.08.021
Bimenyimana, S., and Asemota, G. N. O. (2018). Traditional vs smart electricity metering systems: A brief overview. Journal of Marketing and Consumer Research, 46, 1-7. https://www.iiste.org/Journals/index.php/JMCR/article/view/42505/43773. (Accessed: 2023-03-02)
Bunn, D., and Farmer, E. (1985). Comparative models for electrical load forecasting. Wiley. https://www.osti.gov/biblio/6256333. (Accessed: 2023-03-02)
Capitanescu, F., Ochoa, L. F., Margossian, H., and Hatziargyriou, N. D. (2015). Assessing the potential of network reconfiguration to improve distributed generation hosting capacity in active distribution systems. IEEE Transactions on Power Systems, 30(1), 346-356. https://doi.org/10.1109/TPWRS.2014.2320895
Chica-Olmo, J., Sánchez, A., and Sepúlveda-Murillo, F. H. (2020). Assessing colombia’s policy of socio-economic stratification: An intra-city study of self-reported quality of life. Cities, 97, 102560. https://www.sciencedirect.com/science/article/pii/S0264275119312995. https://doi.org/10.1016/j.cities.2019.102560
Cuenca, J. J., and Hayes, B. P. (2022). Non-bias allocation of export capacity for distribution network planning with high distributed energy resource integration. IEEE Transactions on Power Systems, 37(4), 3026-3035. https://doi.org/10.1109/TPWRS.2021.3124999
Cuenca, J. J., Jamil, E., and Hayes, B. P. (2023). Revenue-based allocation of electricity network charges for future distribution networks. IEEE Transactions on Power Systems, 38(2), 1728-1738. https://doi.org/10.1109/TPWRS.2022.3176186
Dong, Y., and Peng, C.-Y. J. (2013, May 14). Principled missing data methods for researchers. SpringerPlus, 2(1), 222. https://doi.org/10.1186/2193-1801-2-222
ElectroHuila S.A. E.S.P. (2021). Hackatón OpitaChallenge. https://reto.electrohuila.com.co/. (Accessed: 2023-03-02)
Escalera, A., Hayes, B., and Prodanović, M. (2018). A survey of reliability assessment techniques for modern distribution networks. Renewable and Sustainable Energy Reviews, 91, 344-357. https://doi.org/10.1016/j.rser.2018.02.031
Ghoddusi, H., Creamer, G. G., and Rafizadeh, N. (2019). Machine learning in energy economics and finance: A review. Energy Economics, 81, 709-727. https://doi.org/10.1016/j.eneco.2019.05.006
Gnatyuk, V. I., Polevoy, S. A., Kivchun, O. R., and Lutsenko, D. V. (2020, apr). Applying the potentiating procedure for optimal management of power consumption of technocenose. IOP Conference Series: Materials Science and Engineering, 837(1), 012001. https://doi.org/10.1088/1757-899X/837/1/012001
Hemmati, R., Hooshmand, R.-A., and Taheri, N. (2015). Distribution network expansion planning and dg placement in the presence of uncertainties. International Journal of Electrical Power & Energy Systems, 73, 665-673. https://doi.org/10.1016/j.ijepes.2015.05.024
Honarmand, M. E., Hosseinnezhad, V., Hayes, B., Shafie-Khah, M., and Siano, P. (2021). An overview of demand response: From its origins to the smart energy community. IEEE Access, 9, 96851-96876. https://doi.org/10.1109/ACCESS.2021.3094090 Hong,
T., and Fan, S. (2016). Probabilistic electric load forecasting: A tutorial review. International Journal of Forecasting, 32(3), 914-938. https://doi.org/10.1016/j.ijforecast.2015.11.011
Klyuev, R. V., Morgoev, I. D., Morgoeva, A. D., Gavrina, O. A., Martyushev, N. V., Efremenkov, E. A., and Mengxu,
Q. (2022). Methods of forecasting electric energy consumption: A literature review. Energies, 15(23). https://doi.org/10.3390/en15238919
Lindsey, J. K. (2004). Statistical analysis of stochastic processes in time. Cambridge University Press. https://doi.org/10.1017/CBO9780511617164
Medar, R., Rajpurohit, V. S., and Rashmi, B. (2017). Impact of training and testing data splits on accuracy of time series forecasting in machine learning [conference paper]. In 2017 international conference on computing, communication, control and automation (iccubea). https://doi.org/10.1109/ICCUBEA.2017.8463779
Mehigan, L., Zehir, M. A., Cuenca, J. J., Sengor, I., Geaney, C., and Hayes, B. P. (2022). Synergies between low carbon technologies in a large-cale mv/lv distribution system. IEEE Access, 10, 88655-88666. https://doi.org/10.1109/ACCESS.2022.3199872
Meng, M., Niu, D., and Sun, W. (2011). Fore-casting monthly electric energy consumption using feature extraction. Energies, 4(10), 1495–1507. https://doi.org/10.3390/en4101495
Migliavacca, G., Rossi, M., Siface, D., Marzoli, M., Ergun, H., Rodrı́guez-Sánchez, R., . . . Morch, A. (2021). The innovative flexplan grid planning methodology: How storage and flexible resources could help in de-bottlenecking the european system. Energies, 14(4).
https://doi.org/10.3390/en14041194
Ochoa, L. F., Dent, C. J., and Harrison, G. P. (2010). Distribution network capacity assessment: Variable dg and active networks. IEEE Transactions on Power Systems, 25(1), 87-95. https://doi.org/10.1109/TPWRS.2009.2031223
Schafer, J. L. (1999). Multiple imputation: A primer. Statistical Methods in Medical Research, 8(1), 3–15. https://doi.org/10.1191/096228099671525676
Shumilova, G., Gottman, N., and Starceva, T. (2008). Forecasting of electrical loads in the operational management of electric power systems based on neural network structures. KNC UrO RAS: Syktyvkar, Russia, 85.
vom Scheidt, F., Medinová, H., Ludwig, N., Richter, B., Staudt, P., and Weinhardt, C. (2020). Data analytics in the electricity sector. a quantitative and qualitative literature review. Energy and AI, 1, 100009. https://doi.org/10.1016/j.egyai.2020.100009
Wei, N., Li, C., Peng, X., Zeng, F., and Lu, X. (2019). Conventional models and artificial intelligence-based models for energy consumption forecasting: A review. Journal of Petroleum Science and Engineering, 181, 106187. https://doi.org/10.1016/j.petrol.2019.106187
Yuce, B., Mourshed, M., and Rezgui, Y. (2017). A smart forecasting approach to district energy management. Energies, 10(8). https://doi.org/10.3390/en10081073
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2024 Juan Cuenca, Diego Palacios-Castro, Rodolfo García
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors or holders of the copyright for each article hereby confer exclusive, limited and free authorization on the Universidad Nacional de Colombia's journal Ingeniería e Investigación concerning the aforementioned article which, once it has been evaluated and approved, will be submitted for publication, in line with the following items:
1. The version which has been corrected according to the evaluators' suggestions will be remitted and it will be made clear whether the aforementioned article is an unedited document regarding which the rights to be authorized are held and total responsibility will be assumed by the authors for the content of the work being submitted to Ingeniería e Investigación, the Universidad Nacional de Colombia and third-parties;
2. The authorization conferred on the journal will come into force from the date on which it is included in the respective volume and issue of Ingeniería e Investigación in the Open Journal Systems and on the journal's main page (https://revistas.unal.edu.co/index.php/ingeinv), as well as in different databases and indices in which the publication is indexed;
3. The authors authorize the Universidad Nacional de Colombia's journal Ingeniería e Investigación to publish the document in whatever required format (printed, digital, electronic or whatsoever known or yet to be discovered form) and authorize Ingeniería e Investigación to include the work in any indices and/or search engines deemed necessary for promoting its diffusion;
4. The authors accept that such authorization is given free of charge and they, therefore, waive any right to receive remuneration from the publication, distribution, public communication and any use whatsoever referred to in the terms of this authorization.