Abstract—Predicting the generation and efficiency of motor generators is a challenge in energy planning due to variable operating conditions and the need to optimize resources. This article addresses the aforementioned problem from a prediction approach based on Artificial Neural Networks (ANN). The object of study is a Hyundai motor generator used in electricity generation, for which the history of operating variables was used. The methodology employed consisted of the collection, normalization and training of an ANN with the respective validation of the prediction model using statistical metrics, such as the Mean Squared Error (MSE), which had a value of 0.0039 with a coefficient of determination of 0.9237 and an acceptable confusion matrix, since it was able to classify the data with 100% accuracy. In addition, the efficiency indicator was analyzed using the ratio between the energy generated and fuel consumption, with an average of 3.34 and a deviation of 0.17. The final results show a good prediction of the model with a low MSE of 0.000450, which allows the energy performance of the system to be evaluated. Therefore, the use of ANNs is very useful for planning and predicting electricity generation in these machines, as they present an error of less than one, which expresses greater accuracy. 

Index Terms—resource optimization, energy planning, generation, fuel consumption, model validation

Cite: Stiven Ismael Veintimilla Herrera, Secundino Marrero Ramírez, Damian Alban Andrade, and Enrique Torres Tamayo, "Enhancing Cybersecurity in Internet of Things Networks Using Advanced Deep Learning Techniques for Intrusion Detection," International Journal of Electrical and Electronic Engineering & Telecommunications, vol. 15, no. 3, pp. 184-191, 2026. doi: 10.18178/ijeetc.15.3.184-191

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).