Abstract
In many systems that are studied and developed in the field of Electrical Engineering, analyzes are carried out that have as one of their main purposes the prediction of their variables, both for planning and decision-making processes. With the advent of Artificial Intelligence, it has been observed how different techniques related to machine learning and optimization have been incorporated into these prediction tasks. Those new techniques generally obtained better results in the estimation of values than those generated from more traditional techniques. The objective of this research is to review what has been published on predictions of variables in Electrical Engineering systems in the databases EBSCO, SciELO, RedAlyc, Springer Link, IEEE Xplorer, and Google Scholar, given specific temporal and keyworks delimitations for the area. From the analysis of the literature, the trend on the subject was obtained from the most productive years, areas of impact, and most frequent languages. It was observed that the studies developed have grown in recent years and that the areas of greatest impact, according to the number of publications and citations, are the prediction of electricity consumption and production, and the variables related to renewable energy.
References
Arrestegui, L. B. (2012). Fundamentos históricos y filosóficos de la inteligencia artificial. UCV-HACER. Revista de Investigación y Cultura, 1(1), 87-92. Recuperado de https://www.redalyc.org/articulo.oa?id=521752338014
Barney, H. B. (agosto, 2019). What is electrical engineering? IEEE Potentials, 38(5), 52-52. Recuperado de https://ieeexplore.ieee.org/document/8821595
Brockwell, P. J. y Davis, R. A. (2002). Introduction to time series and forecasting. Suiza: Springer International Publishing.
Kitchenham, B. (2004). Procedures for performing systematic reviews. Recuperado de http://www.elizabete.com.br/rs/Tutorial_IHC_2012_files/Conceitos_RevisaoSistematica_kitchenham_2004.pdf
García, A. (2012). Inteligencia Artificial. Fundamentos, práctica y aplicaciones. Madrid, España: RC Libros.
Hitam, N. A., y Ismail, A. R. (2018). Comparative performance of machine learning algorithms for cryptocurrency forecasting. Ind. J. Electr. Eng. Comput. Sci, 11(3), 1121-1128.
Jesiek, B. K., y Jamieson, L. H. (2017). The expansive (dis) integration of electrical engineering education. IEEE Access, 5, 4561-4573.
Maiti, M., Vyklyuk, Y., y Vuković, D. (2020). Cryptocurrencies chaotic co‐movement forecasting with neural networks. Internet Technology Letters, 3(3), e157.
Roberts, J., Demarest, K., y Prescott, G. (2008). What is electrical engineering today and what is it likely to become? 2008 38th Annual Frontiers in Education Conference. Nueva York, Estados Unidos. DOI: 10.1109/FIE.2008.4720588
Russell, S., y Norvig, P. (2002). Artificial Intelligence: A Modern Approach. New Jersey, Estados Unidos: Pearson.
Serna, A., Acevedo, E., y Serna, E. (2017). Principios de la inteligencia artificial en las ciencias computacionales. En E. Serna (Ed.), Desarrollo e Innovación en Ingeniería (pp.161-172). Medellín, Colombia: Editorial IAI
Sharma, V., Cali, U., Hagenmeyer, V., Mikut, R., y Ordiano, J. N. G. (Junio, 2018). Numerical Weather Prediction Data Free Solar Power Forecasting with Neural Networks. In Proceedings of the Ninth International Conference on Future Energy Systems (pp. 604-609). El Karlsruhe, Alemania. doi: 10.1145/3208903.3210279
Ushakov, V. Y. (2018). Electrical Power Engineering: Current State, Problems and Perspectives. Suiza: Springer.
Vegega, C., Pytel, P. y Pollo, M. F. (2017). Método basado en el emparrillado para evaluar los datos aplicables para entrenar algoritmos de aprendizaje automático. En E. Serna (Ed.), Desarrollo e Innovación en Ingeniería (pp. 106-137). Medellín, Colombia: Editorial IAI
Comments
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) 2021 Joseline Sánchez Solís, Marvin Coto Jiménez