Hydropower production prediction using artificial neural networks: an Ecuadorian application case

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.

A Novel Load Forecast, and Sizing Model of a Hybrid PV-Hydroelectric Microgrid System Using Python

“…Furthermore, thorough examination of 42 NILM datasets with the help of comparison tables created to highlight the various characteristics of the datasets already in existence. Additionally, as a contribution to the eld of energy disaggregation and load identi cation, the advantages and disadvantages of the current NILM datasets are emphasized together with a forecast for current di culties and future research objectives [25]. Consequently, load demand data acquisition techniques can be summarized in Fig.…”

“…The mathematical modeling and electrical characteristic of PV cells have been described in [21][22][23][24][25][26][27][28]. The complete power circuit of the PV cell model consists of a current source, a shunt diode, and resistances associated with the series and shunt lines [28].…”

Average Daily Processing Prediction of Artificial Hydropower Station Based on Machine Learning

“…Linear programming (LP) method is one of the earliest introduced methods, which has simple principle, fixed solution method and can obtain the global optimal solution, and is widely used in the solution of reservoir optimization problems. However, linear programming requires both the objective expression and the constraint expression of the problem to be solved to be linear, so it is often restricted in practical use [10]. Different from linear programming, nonlinear programming (NLP) no longer has linear requirements and is more suitable for the actual reservoir group scheduling problem [11].…”

Special issue on deep learning for time series data

“…Barzola-Monteses et al [7] use artificial neural network models to analyze hydroelectric production in short and medium terms in Ecuador. The authors applied Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) models while considering the various factors influencing hydroelectric production.…”