The load flow is of great importance in assisting the process of decision making and planning of generation, distribution and transmission of electricity. Ignorance of the values in this indicator, as well as their inappropriate prediction, difficult decision making and efficiency of the electricity service, and can cause undesirable situations such as; the on demand, overheating of the components that make up a substation, and incorrect planning processes electricity generation and distribution. Given the need for prediction of flow of electric charge of the substations in Ecuador this research proposes the concept for the development of an automated prediction system employing the use of Artificial Neural Networks. El flujo de carga tiene gran relevancia en la asistencia del proceso de toma de decisiones y planificación de la generación, distribución y trasmisión de energía eléctrica. El desconocimiento de los valores de este indicador, así como su inadecuada predicción, dificulta la toma de decisiones y eficiencia del servicio eléctrico, además puede ocasionar situaciones indeseadas tales como; la sobre demanda, el sobre calentamiento de los componentes que integran una subestación, y la no correcta planificación de los procesos de generación y distribución eléctrica. Dada la necesidad de predicción de flujo de carga eléctrica de las subestaciones en el Ecuador la presente investigación propone la concepción para el desarrollo de un sistema automatizado de predicción empleando el uso de Redes Neuronales Artificiales.

Accurate electricity consumption forecasting is essential for the efficient planning and operation of modern power systems. The development of predictive models based on machine learning and deep learning strongly depends on the availability of well-documented and publicly accessible electricity consumption datasets. However, most existing databases are concentrated in Europe and North America and are typically focused on residential measurements obtained from smart meters, resulting in limited representation of equatorial regions. This work presents a structured review of public electricity consumption repositories, analyzing characteristics such as geographical coverage, temporal resolution, user type, and accessibility. Based on the limitations identified in the literature, a new electricity consumption dataset obtained from real measurements collected at distribution substations located in an equatorial region is presented. The dataset was organized through a systematic preprocessing workflow that included temporal standardization, construction of 48-h sliding windows, normalization, and stratified partitioning into training, validation, and test subsets. The descriptive statistical analysis confirms the consistency of the generated subsets and reveals differences between working-day and non-working-day consumption patterns. The proposed dataset provides a reproducible resource for the development and evaluation of multi-horizon electricity demand forecasting models, as well as for load analysis and energy management studies in equatorial regions.

In the present investigation, the authors propose a conceptual model for the analysis and the decision making of the corrective models to use in the mitigation of the harmonic distortion. The authors considered the setting of conventional models, and such adaptive models like the filters incorporation to networks neuronal artificial (RNA’s) for the mitigating effect. In addition to the present work is a showing of the experimental model that learns by means of a flowchart denoting the need to use artificial intelligence skills for the exposition of the proposed model. The other aspect considered and analyzed are the adaptability and usage of the same, considering a local reference of the laws and lineaments of energy quality that demands the Department of Electricity and Energy Renewable (MEER) of Equator.

Predicting electrical demand in distribution systems is a fundamental problem for the efficient operation of smart grids, especially under scenarios of high temporal variability. This study compares two multi-step forecasting strategies for 24-h horizons: a direct 24→24 strategy and a recursive strategy based on sequential 24→1 predictions. Four machine learning and deep learning architectures are evaluated: LSTM, N-HiTS, U-Net, and LightGBM, using real data from electrical feeders belonging to distribution systems in the equatorial region of Ecuador. The methodology includes constructing time windows, non-overlapping train/validation/test partitioning for evaluation, consistent normalization, and comparative analysis using MAE, RMSE, and MAPE metrics. The results show that the direct 24→24 strategy achieves the best overall performance, with LSTM standing out with an approximate MAPE of 4.12%. However, the recursive strategies exhibit greater stability in the face of atypical patterns observed during holidays and weekends. Furthermore, U-Net demonstrates competitive performance in both accuracy and temporal robustness, while LightGBM stands out for its computational efficiency. It is concluded that the selection of a forecasting strategy depends on the required balance between overall accuracy, temporal stability, and computational cost.

This article highlights the study and analysis of supercapacitors as an innovative contribution in the development of electronics and its applications in the modern world. It also includes the operating principle of supercapacitors and details all its generalities and particularities; In the same way the document makes a comparison between the supercapacitors and the conventional capacitors, a model of hybrid power supply is used for the purpose between an EDLC supercapacitor and a conventional battery, with the integration of DC-DC converters and a block power limiter, in order to evaluate the contribution of the transitory power given by the block of supercapacitors EDLC and specify the performance of this type of electrical components, the development of the model was made by the software based on the simulation "Matlab", which presents favorable results, fully adjusting to the desired load profile, analyzed in the present study case, with all the considerations of the implements associated with the proposed hybrid model, for the practical study of supercapacitors.