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.

No abstract

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.