Hydropower is among the most efficient technologies to produce renewable electrical energy. Hydropower systems present multiple advantages since they provide sustainable and controllable energy. However, hydropower plants’ effectiveness is affected by multiple factors such as river/reservoir inflows, temperature, electricity price, among others. The mentioned factors make the prediction and recommendation of a station’s operational output a difficult challenge. Therefore, reliable and accurate energy production forecasts are vital and of great importance for capacity planning, scheduling, and power systems operation. This research aims to develop and apply artificial neural network (ANN) models to predict hydroelectric production in Ecuador’s short and medium term, considering historical data such as hydropower production and precipitations. For this purpose, two scenarios based on the prediction horizon have been considered, i.e., one-step and multi-step forecasted problems. Sixteen ANN structures based on multilayer perceptron (MLP), long short-term memory (LSTM), and sequence-to-sequence (seq2seq) LSTM were designed. More than 3000 models were configured, trained, and validated using a grid search algorithm based on hyperparameters. The results show that the MLP univariate and differentiated model of one-step scenario outperforms the other architectures analyzed in both scenarios. The obtained model can be an important tool for energy planning and decision-making for sustainable hydropower production.

Electrical generation in Ecuador mainly comes from hydroelectric and thermo-fossil sources, with the former amounting to almost half of the national production. Even though hydroelectric power sources are highly stable, there is a threat of droughts and floods affecting Ecuadorian water reservoirs and producing electrical faults, as highlighted by the 2009 Ecuador electricity crisis. Therefore, predicting the behavior of the hydroelectric system is crucial to develop appropriate planning strategies and a good starting point for energy policy decisions. In this paper, we developed a time series predictive model of hydroelectric power production in Ecuador. To this aim, we used production and precipitation data from 2000 to 2015 and compared the Box-Jenkins (ARIMA) and the Box-Tiao (ARIMAX) regression methods. The results showed that the best model is the ARIMAX (1,1,1) (1,0,0)₁₂, which considers an exogenous variable precipitation in the Napo River basin and can accurately predict monthly production values up to a year in advance. This model can provide valuable insights to Ecuadorian energy managers and policymakers.

Students at the University of Guayaquil pursuing a degree in software engineering who struggle to obtain information on enrollment and tuition payments are the target audience for the application developed in this study. To do this, a chatbot is proposed. It uses Machine Learning (ML) and Natural Language Processing (NLP) to answer student’s questions. To evaluate the ease of use of the system from a quantitative point of view, the time used by 6 students to complete user registration (T1), make five searches (T2), and unsubscribe (T3), was measured in minutes, with an average duration of three minutes for each activity. To assess the students’ perception with the use of the proposed chatbot, a sample of sixty students who had previously interacted with the proposed solution. Aspects assessed included: Ease of use of the system (A), speed (B), appropriate behavior (C), confidence to use it again (D), and quality of the answer provided (E). Each evaluated characteristic (A-E) was rated above 3 out of 5 in most cases. Thus, the chatbot solution achieved good acceptance by students, even considering its use in future academic semesters.

The development of several strategies to control Direct Current (DC) motors have been facilitated by the improvement of the technology. To decide an optimal controller for position control in DC motors, it is fundamental to study the behavior of the system by looking at some parameters such as steady-state error, overshoot percentage, torque load rejection, rise and settling time. Proportional, integrative and derivative controller (PID) provides an easy tuning of its gains and offers a stable output. Fuzzy Logic Controller (FLC) imitates the human knowledge by replacing mathematical calculation for linguistic ideology. This controller provides suitable responses, but they are not ideal due to each of them suffer from slow response or torque load increment. On one hand, Self-tuning controller has been developed by scientist as a system that links PID and FLC. Self-tuning controller works by setting the FLC as a master meanwhile the PID gains can be set applying a linguistic interpretation of the behavior of the variables. On the other hand, Genetic Algorithm (GA) is a robust optimizer that emulates the natural selection and is applied for tuning PID controller coefficients to guarantee optimal performance. This research provides a comparative examination between GA PID and Fuzzy self-tuning controllers by looking at the above-mentioned variables to present the benefits and drawbacks of each controllers.

Buildings have a dominant presence in energy consumption for the transition to clean energy. During 2017, construction and operation of buildings worldwide represented more than a third (36%) of final energy used and 40% of the emissions of carbon dioxide. Hence, there is great interest in reducing energy use in this sector, and energy efficiency in buildings to enhance energy performances is a suitable way. In this paper, black-box approaches based on artificial neural networks to predict the electric load of a selected educational building are proposed. The potential and robustness of long short-term memory (LSTM) applied to a dataset with a limited number of days of observations are analyzed. The results in our scenario showed that the LSTM surpasses in accuracy to other techniques such as feed-forward neural networks.